From 169e01b87f62f01f7bd56c86ee354ea602c8ea64 Mon Sep 17 00:00:00 2001
From: Asaf Yehudai <Asaf.Yehudai@ibm.com>
Date: Wed, 11 Feb 2026 10:37:54 +0200
Subject: [PATCH 1/2] Update to v0.2

---
 .../623bae1f-19e9-47f9-bc7b-80a859218d07.json |  37 +++++-
 .../fbba98c5-5d56-4837-9044-d4e5ac610c2c.json |  37 +++++-
 .../dc6e1164-c9d7-4dd5-b8dc-fbc4e3f45011.json |  37 +++++-
 .../c62a913b-3101-4ce3-a5c5-a1ac844e55f8.json |  37 +++++-
 .../3101726d-fd51-436d-8adf-cbdf0d534834.json |  42 ++++++-
 .../f878a52a-fa80-4113-ae7d-0cb11e3ef9fd.json |  32 ++++-
 .../904c6359-bd7b-4448-9f16-bc115d0629c4.json |  42 ++++++-
 .../49511052-6881-4151-9b46-686c75f73c22.json |  42 ++++++-
 .../b289e2e6-d57b-4a2b-aa61-e2974d193909.json |  37 +++++-
 .../aeeca919-71a1-42a0-a6d0-6779d77750e6.json |  32 ++++-
 .../db29538d-f40e-42d0-b3c0-e622f92112d2.json |  42 ++++++-
 .../ab0cdc4f-47dd-4dcc-b506-982ce3924105.json |  37 +++++-
 .../44da63b6-d934-4330-bc20-33464bae61dd.json |  42 ++++++-
 .../c930cbe0-f429-4b61-9abe-86dcb7266cf7.json |  42 ++++++-
 .../c84b27b2-2dd9-48ee-9a53-ec27ae62ae7a.json |  32 ++++-
 .../73ee9408-e669-4b8a-9419-76bd6051ce8d.json |  32 ++++-
 .../0deed2f4-770e-4033-a65d-e1da19e00611.json |  42 ++++++-
 .../e727cb77-f229-4aaa-909f-99c7aa06676b.json |  37 +++++-
 .../da9264cd-2fa3-4121-81de-eef994e15993.json |  37 +++++-
 .../79cc5cd4-bfed-466d-9fbe-2f27e8aab175.json |  42 ++++++-
 .../28c35831-679d-489a-b2c4-fd2c7f333fbc.json |  42 ++++++-
 .../9db7907d-7b22-480c-86a5-f88ec2b302e7.json |  37 +++++-
 .../2faddf79-41e6-47e9-9c26-17bc987bc870.json |  37 +++++-
 .../20989a47-6556-4e3b-8909-d0a419cb159b.json |  37 +++++-
 .../f3d0010f-efed-4f87-9582-b9c87b4de99a.json |  37 +++++-
 .../a0ce3ed6-2a2c-46ad-be86-6f6701533e36.json |  37 +++++-
 .../d54c4830-23c8-4c12-aea1-4f5b5245464f.json |  37 +++++-
 .../b5853278-edd9-4bc8-bbeb-d6dab515b562.json |  37 +++++-
 .../74188e30-1e49-47d8-af01-b80e430dafa0.json |  37 +++++-
 .../93974286-0497-46a2-a2e8-404c1e89dba0.json |  37 +++++-
 .../02c0020c-7d69-4701-a606-4bc79ad87afd.json |  37 +++++-
 .../5dcb7c54-64e7-4f76-8903-8f57b35cdb0c.json |  37 +++++-
 .../4887256e-0545-40dd-9756-ff850e003a29.json |  37 +++++-
 .../d2b70870-9cbc-4666-bbd4-097fcebe716e.json |  37 +++++-
 .../f420f432-2291-40a9-8ebd-b91241970113.json |  37 +++++-
 .../02e68d1b-86f3-4344-ad8d-45df878b744c.json |  42 ++++++-
 .../f712ab4a-1127-44ba-b6b9-7a40290f3322.json |  42 ++++++-
 .../b4175f0f-f9f4-4418-b4aa-a31e7f1f93f4.json |  37 +++++-
 .../9879e9a7-ddbc-4338-abc7-e3bc394869e9.json |  37 +++++-
 .../d7d8a5cb-e295-4ced-b528-d99d814ff008.json |  37 +++++-
 .../bff86a1f-71c3-4f27-aeae-bba6d03635ef.json |  37 +++++-
 .../723281f8-54b7-4db6-8253-5a6dcf4f3d4a.json |  37 +++++-
 .../0ce7dc54-f608-4985-9904-75cee09b6288.json |  32 ++++-
 .../5bb0aaa4-2cc5-4622-8235-993bc4178f12.json |  32 ++++-
 .../85ab22b8-0587-4e2b-857f-3d6d84d571a4.json |  42 ++++++-
 .../37aa6702-b2fa-43bf-b5a9-36740f627217.json |  32 ++++-
 .../57f48d0c-e424-410d-b9ee-4707e2add036.json |  32 ++++-
 .../8643b4dd-e18c-442c-adb5-84ef756534f8.json |  42 ++++++-
 .../2f3d2e46-1f9e-4b1c-9729-ab0a93cc245c.json |  37 +++++-
 .../4aec78d3-a38c-48e0-b9e2-b6dc063bd37e.json |  42 ++++++-
 .../f9b60945-8b14-4564-9d44-3eb6db675ab9.json |  32 ++++-
 .../56703c11-eccb-4f66-af13-60f972a5068f.json |  37 +++++-
 .../fbd8be7e-5670-4729-a77d-83472510b734.json |  37 +++++-
 .../2e18ee77-9c46-4cf9-9521-303ad15e5be4.json |  37 +++++-
 .../ec5b296e-03e8-4371-a8c1-eca0b0b9759d.json |  42 ++++++-
 .../07b61a55-a8e3-4a6f-9806-a4100f8d5297.json |  37 +++++-
 .../3d534c25-5016-44de-9c47-24b7d7399b0f.json |  42 ++++++-
 .../4de91433-05b3-4f88-9d0f-66691c671f62.json |  42 ++++++-
 .../dc71f1ba-f4b8-4231-ac72-0acf9a22d73e.json |  37 +++++-
 .../36c4adc9-c2fb-4bc3-81ba-88478d30332e.json |  37 +++++-
 .../f0827b15-20d0-4986-b5a0-bb4bc9be768e.json |  42 ++++++-
 .../aeaa8b33-e327-4c65-9641-5dfc63feee3b.json |  42 ++++++-
 .../c97c79f3-fd92-49db-9131-5e45834a7eaf.json |  37 +++++-
 .../687099cb-c1bf-49ec-a902-329c2b818369.json |  42 ++++++-
 .../8da4f5eb-6264-4503-b9bc-fcf843b638be.json |  37 +++++-
 .../28a68b87-5412-4374-9e61-896b0fff7669.json |  42 ++++++-
 .../3209c869-03c5-4801-8e4b-4c8bcde3d58f.json |  37 +++++-
 .../9d1e124c-e133-41d3-8ac7-5c8c5027aa02.json |  32 ++++-
 .../633d499b-58bd-4fca-9b56-0f005a5a21b8.json |  37 +++++-
 .../5c4f3caf-6af3-48c6-83e2-4710d31e6acf.json |  37 +++++-
 .../77d1edc1-fb54-4371-bf7c-baebbb351163.json |  37 +++++-
 .../e7eecdb0-bc17-4d9f-b3e8-9ee777d2f595.json |  37 +++++-
 .../3f3915b3-0d6e-451c-9185-fa4372b93f2b.json |  37 +++++-
 .../e534d37b-3009-4a7d-82d8-d7c85b95649e.json |  37 +++++-
 .../bd8f0ed1-75fc-48c1-996e-655d205c027c.json |  37 +++++-
 .../e9effaf6-e48b-4b35-b035-430be81b316b.json |  42 ++++++-
 .../d2132eea-eb88-41e5-b8e6-2e8e8a623ed1.json |  32 ++++-
 .../ffd05bc7-3724-40ba-85b9-c25ebe71fba2.json |  32 ++++-
 .../43f0e93d-f0b8-46af-a549-e1ac315d96ea.json |  42 ++++++-
 .../9ccab7bd-d2ed-4ab3-ad81-656650c29a3b.json |  37 +++++-
 .../c10d4213-f1fa-41e6-92d9-0d5337c1362b.json |  37 +++++-
 .../63b08ba0-eeb9-48ae-a5d1-d7d3792aa1c0.json |  37 +++++-
 .../d724076d-509f-4ad4-894c-976b0472de85.json |  37 +++++-
 .../54d34f25-1cd9-4995-8e56-c36981842fc8.json |  32 ++++-
 .../63ae1c75-fd4d-4f40-afd0-b9f91d700014.json |  37 +++++-
 .../1d5ebbce-8cfe-446b-82c0-a227d4e9247f.json |  32 ++++-
 .../3f9c81ac-5c76-43b4-a27d-7eaa055139c4.json |  42 ++++++-
 .../680098fb-76cf-47b6-a0ea-a1a06ca46dca.json |  42 ++++++-
 .../6ec21338-9908-4ce4-a1f2-dac14c5e27ab.json |  32 ++++-
 .../592ad1e3-8a48-4c39-8013-81d7c731780f.json |  37 +++++-
 .../5b36f0af-7ff6-4564-9714-08fbf41d261f.json |  42 ++++++-
 .../04f120c6-b648-4c83-81d8-05118efb0904.json |  37 +++++-
 .../c907e494-ab2e-4a28-a28d-aeb68eb818ed.json |  42 ++++++-
 .../d9eed240-ebbe-482f-8dae-c5251ed6d067.json |  32 ++++-
 .../670865e1-f219-465b-9fbe-6da6f73ac9e6.json |  37 +++++-
 .../88953298-b63e-499f-a31e-f0f586c4772d.json |  32 ++++-
 .../3acb690c-ffc0-4e67-8ae1-e79bcee4f824.json |  37 +++++-
 .../6ad2cb6a-f9a3-424e-aed2-9493899872e3.json |  32 ++++-
 .../1892bf75-916b-4d4f-96ab-fda36872ae5d.json |  32 ++++-
 .../e06e1863-c28f-4c96-a672-b1073c80aa71.json |  32 ++++-
 .../d923f7aa-a9d4-406a-b5d7-bdab508f04f7.json |  32 ++++-
 .../5c5e40b1-e86a-4d30-b93c-f8f9e73cdca8.json |  32 ++++-
 .../59299d8c-e468-490f-8a52-eef49b0aaeea.json |  42 ++++++-
 .../3ce9612f-9b57-476e-9fa4-6e63f14568a7.json |  32 ++++-
 .../9c605bf1-2533-43db-a610-e71c0aaecdb5.json |  42 ++++++-
 .../c289f778-92b8-44df-a079-3bced33c8ab5.json |  32 ++++-
 .../329d4101-e740-490c-9fbc-1708f76a2f61.json |  32 ++++-
 .../3e87f52e-b136-4cb3-8cbb-d8d8a8571051.json |  42 ++++++-
 .../62b9adca-db38-46c0-a68a-ed7a8e735035.json |  32 ++++-
 .../4d2f43eb-e6f3-4686-a9d9-6b6c6b68b86c.json |  42 ++++++-
 .../830df3fd-d479-4af8-a92b-93d82e804fec.json |  32 ++++-
 .../0e6d85b8-aa37-448c-adb2-0da2bd13e322.json |  32 ++++-
 .../45f0bd9c-e939-4b83-a623-1db61f431500.json |  42 ++++++-
 .../0f710903-7dd8-44ea-914d-d43bbfe894f1.json |  42 ++++++-
 .../b9ddd960-f6f7-4962-8297-88ec7fbbbd1f.json |  32 ++++-
 .../25a4520b-c780-45fc-a00f-36db1776c6a8.json |  42 ++++++-
 .../96d7e5c1-2f43-4f09-9702-0af090afa141.json |  42 ++++++-
 .../5a47f8bd-401a-4b6b-91b0-9593b36e5996.json |  42 ++++++-
 .../c27e98d4-f5ea-48f9-babc-3ccda2d21d2a.json |  42 ++++++-
 .../060bf847-e7b5-4e30-934f-5306d01c499a.json |  42 ++++++-
 .../e648e6c2-18bb-49d7-b08f-47ce41a67d4f.json |  42 ++++++-
 .../537e92cb-25db-47f5-916a-6f666e14639a.json |  42 ++++++-
 .../e59ca33f-c6ce-44d4-9cb4-2fd65608313b.json |  32 ++++-
 .../fc99848b-82c7-459e-8327-1867a332ff28.json |  42 ++++++-
 .../357f4f03-9542-495f-b575-4274111bbe1f.json |  32 ++++-
 .../d78c42d6-fc0d-4719-bbb6-7a53dbb0d017.json |  32 ++++-
 .../c94ddbe5-2bc0-4a33-b06b-10671fb22b70.json |  27 ++++-
 .../cc2ac405-1710-46fa-aeba-dd86797c666c.json |  27 ++++-
 .../49fcb3e2-2883-4c3d-b519-d511c6b10162.json |  27 ++++-
 .../0ba5ce6c-f311-4b02-a67a-d49539119a8e.json |  27 ++++-
 .../49029c9e-a831-4219-8e26-df20862ad3e1.json |  27 ++++-
 .../6dedd117-eab0-4c31-b50b-4890099d9904.json |  27 ++++-
 .../71c20c06-efb8-428e-9e9d-e4fedf11041a.json |  27 ++++-
 .../862f3d57-8f5f-4372-b6fb-876fb35efba4.json |  27 ++++-
 .../93ea2bfa-e058-42d5-afac-0d3fc50fce91.json |  27 ++++-
 .../c1331fa1-7793-4526-b24b-02261bb4437f.json |  27 ++++-
 .../c3cab72a-47b3-47ec-bb2d-986903ab8c26.json |  27 ++++-
 .../cd0452a7-0370-4024-a51f-b3deff290db9.json |  27 ++++-
 .../6fd85045-d600-451f-8d27-da637add4081.json |  27 ++++-
 .../a15ca8c3-fd90-4ef9-80c5-40eeac60d785.json |  27 ++++-
 .../5f43832f-14fa-49e1-a851-949163aec826.json |  27 ++++-
 .../1f8869e7-e434-469e-906d-d34621582cba.json |  42 ++++++-
 .../8f9d05db-9bb0-4998-bc75-96dbfa695548.json |  37 +++++-
 .../2681e475-da0a-48a9-ab68-e0bf59240f90.json |  42 ++++++-
 .../e2986d78-100d-417a-9f38-9a570a335d95.json |  37 +++++-
 .../1bc5cd51-5a3a-46ea-bc78-56f9b3081f69.json |  37 +++++-
 .../1d1127ee-7a0e-4915-b8bf-0b22f8ba338b.json |  42 ++++++-
 .../4bb55ff5-5adf-407f-a9d6-910c6c9d2770.json |  42 ++++++-
 .../daebee0b-3856-4270-94c6-c14bd84f5cf5.json |  37 +++++-
 .../1be99417-352e-4a94-8108-b43123553667.json |  42 ++++++-
 .../8d3fbc68-2ee7-4989-a40c-f4a45e579b5c.json |  37 +++++-
 .../9533891f-c2f7-4e82-9f39-131768dbc28a.json |  37 +++++-
 .../b8a47660-f0a5-4136-a743-979863c53e3a.json |  42 ++++++-
 .../2673bea2-42eb-42a5-9dc2-13d43341c9b2.json |  42 ++++++-
 .../6f5555c2-588a-48d1-811c-be53634bbdef.json |  37 +++++-
 .../9c96fa7b-52e8-4aed-9fdd-f389091d5e6f.json |  42 ++++++-
 .../0519d9fb-f220-40ab-8257-f20ed98a8b47.json |  37 +++++-
 .../ece70375-447f-41e8-aa03-8f4b26abea73.json |  37 +++++-
 .../7bbaffdd-f822-48cf-a0f2-e66b16db678d.json |  37 +++++-
 .../27c5c441-64ce-41dd-8384-f84c8f6ccc14.json |  37 +++++-
 .../38a14e6a-2094-4e0b-be22-45181ede2a63.json |  37 +++++-
 .../cee37c2c-2766-47b7-9192-a141e5d22f2d.json |  42 ++++++-
 .../d1d69392-8717-462d-9ce0-c7ddf5faf97d.json |  42 ++++++-
 .../72071bb1-57c0-4727-8100-ba24d8da10f5.json |  42 ++++++-
 .../7626c158-edaf-48f3-9ac3-1188be0c6032.json |  42 ++++++-
 .../c37be7a8-dc10-4fea-962b-202986a4581e.json |  42 ++++++-
 .../223dc616-b20f-4065-91a7-3c35bfd11c94.json |  42 ++++++-
 .../4236b0a9-9d1e-41f6-8364-a7e8ebf51635.json |  42 ++++++-
 .../c8030a87-0cdf-4918-b0d5-d1fb0e284656.json |  42 ++++++-
 .../e6ecc1eb-7ff1-46aa-bf03-37bad1b391b7.json |  42 ++++++-
 .../64872b1a-1eae-4171-95ec-a80c782b69f0.json |  42 ++++++-
 .../37484401-c7fe-469d-889a-e70f7cadbf82.json |  42 ++++++-
 .../8cf36288-3add-4fcd-a012-0df9eae2a059.json |  42 ++++++-
 .../f2c8f979-c331-4b9b-b0a7-5efa82c17d3b.json |  42 ++++++-
 .../de409ce8-fb68-4113-8879-23712769cbde.json |  42 ++++++-
 .../264f20d7-1574-448c-8917-eb3f20810819.json |  42 ++++++-
 .../0ebaec42-9190-4326-95dd-5ecb48bf1a72.json |  42 ++++++-
 .../29515933-c60b-4686-b475-70ef53d75457.json |  42 ++++++-
 .../414174a9-7e44-4f7b-94ce-0757639f5af7.json |  42 ++++++-
 .../48513083-f854-455e-8455-ddbd2698ec03.json |  42 ++++++-
 .../0b373560-854f-4482-81d0-6c984e130144.json |  42 ++++++-
 .../1a021cab-d569-4077-af5e-1643f45de03d.json |  42 ++++++-
 .../e26e230d-59b3-4243-a6c4-3845ab74b89b.json |  42 ++++++-
 .../aa0991d0-9c5e-4f94-bc12-3342ca389e99.json |  42 ++++++-
 .../397abe47-d5e9-487d-b883-ec49db16c584.json |  42 ++++++-
 .../82f52a35-41b5-4b9c-bb3e-4bf18eed0b92.json |  42 ++++++-
 .../670382ab-a8a1-43f3-a572-b9a5aeae23ef.json |  42 ++++++-
 .../a4b3c031-7c01-4f7a-8cfe-52b3260d6ecc.json |  42 ++++++-
 .../7fcd3fce-2296-4b5c-8362-24b1c70ccb8f.json |  42 ++++++-
 .../4f164e8b-55a1-498f-b586-cf78da7d0b57.json |  42 ++++++-
 .../a84d3d61-6e05-4d4d-bc89-7f663e9667fb.json |  42 ++++++-
 .../7aa98f71-8262-4c1f-a71c-1ef36f2ef04c.json |  42 ++++++-
 .../93398c1f-3129-4be4-83b5-62a4a45c6b84.json |  42 ++++++-
 .../62493784-f899-4736-bdce-2107ec99a752.json |  42 ++++++-
 .../9b68ecaa-cf9d-414e-9cf1-c662c765bb5c.json |  42 ++++++-
 .../76f3d0bd-2b71-4406-a0d4-b01b6c91c4ff.json |  42 ++++++-
 .../2dc5ab6f-2427-42ae-9582-a0e6139f451a.json |  42 ++++++-
 .../0db97be6-6562-47d8-bd1a-5b469250e54b.json |  42 ++++++-
 .../228e4dc4-e517-4023-b690-7f0c321286b2.json |  42 ++++++-
 .../9442b27c-c94d-41c0-a752-3bd82385272d.json |  42 ++++++-
 .../561039ac-b156-40eb-bf53-21a275b858ca.json |  42 ++++++-
 .../d801d700-7b4d-4a62-883b-3d85b05385ea.json |  42 ++++++-
 .../b8f24058-4441-4d19-898e-80470cc7b685.json |  42 ++++++-
 .../1f372e00-e7a8-43ef-8e14-ef1b08e5e957.json |  42 ++++++-
 .../0200a1b3-71f1-4633-96a5-4ca9883a67a7.json |  42 ++++++-
 .../55479901-aec7-4875-b792-ba73b54aa37a.json |  42 ++++++-
 .../872597b2-4392-4f23-b5b2-41d418b6cf89.json |  42 ++++++-
 .../5cb437b5-5993-418d-bd9f-81dea71d9edf.json |  42 ++++++-
 .../c471cdf7-73f9-48c9-a970-baa66b609093.json |  42 ++++++-
 .../794a71b4-8a43-4c69-a663-369eea6a84a3.json |  42 ++++++-
 .../2ad22375-4ed8-4be6-a012-a6f6799581e2.json |  42 ++++++-
 .../a8df0dc2-d16c-4e1a-b0b5-abe2a4a1d803.json |  42 ++++++-
 .../ca0a010a-fe3a-4b87-8c80-4a8d3e2597fb.json |  42 ++++++-
 .../5d1c166c-6a22-4afb-b1b1-f7db9ec38bd8.json |  42 ++++++-
 .../10a432fa-dfef-4c9c-bdf7-ce0f81fd1895.json |  42 ++++++-
 .../a550663c-2a04-4dfb-8663-b177a7181f3d.json |  42 ++++++-
 .../72b6196e-0a2b-4ec9-80a3-a7eb14f7be09.json |  42 ++++++-
 .../5e41f068-f009-4e32-bac1-9de5220a2ce2.json |  42 ++++++-
 .../eca1331f-6503-481a-b77b-3d96791f54e8.json |  42 ++++++-
 .../69def7de-a916-4d23-984b-e676e91e1d8c.json |  42 ++++++-
 .../679c6e0b-9e0b-4224-b1e3-59df149739a0.json |  42 ++++++-
 .../2335433d-37c6-47f0-ad3b-5e0a42e9488f.json |  42 ++++++-
 .../fe84f8a3-5fe9-4385-b6d4-0436fb7e5197.json |  42 ++++++-
 .../70d2697e-0df5-40ae-9268-b906c9cabd9d.json |  42 ++++++-
 .../0a30fd70-2381-4a4b-89aa-dbd169c856f0.json |  42 ++++++-
 .../b9c787f9-3bcd-4215-a157-7fcfa2df82cc.json |  42 ++++++-
 .../bdd98f27-fbfd-4de7-bd4e-3b8c3e4e7cc0.json |  42 ++++++-
 .../44b20109-d534-4aa9-867d-fa59935ef6d0.json |  42 ++++++-
 .../d1196312-4153-4a38-aa46-2940d63d7924.json |  42 ++++++-
 .../4b1e3070-04ef-47e7-b720-739320194e7b.json |  42 ++++++-
 .../247f400e-dca8-4dab-bebf-092f778f02c9.json |  42 ++++++-
 .../d043ad21-102b-49f0-9e8e-6daef7cc3a2e.json |  42 ++++++-
 .../d45ec8b8-1ee6-49bb-9237-a7271ba9d13c.json |  42 ++++++-
 .../05a4c6aa-9af2-44f0-8c55-8aeed2e75eaf.json |  42 ++++++-
 .../a6ef712e-014e-470e-8d5b-f3b51f677aee.json |  42 ++++++-
 .../35a039ba-06be-4ec2-9bde-a6a6db2eefec.json |  42 ++++++-
 .../97cb96f8-ce4c-403f-bfbc-386d3c611c81.json |  42 ++++++-
 .../3a1621e9-75ee-4b34-9c0d-ae15399b1dab.json |  42 ++++++-
 .../237218ac-4c74-4647-82b1-700360ddfdbd.json |  42 ++++++-
 .../2858d126-d2ef-4512-8fc8-c39faf24b908.json |  42 ++++++-
 .../d118ddb1-aafc-4ddf-b5c7-f3ff921bbe0c.json |  42 ++++++-
 .../379ec82f-a6a7-4976-a4a6-ab80cb9da293.json |  42 ++++++-
 .../c4df42d1-a838-4717-a814-40559fcd7342.json |  42 ++++++-
 .../f022d826-3252-4def-b37b-3ce44d78f4ce.json |  42 ++++++-
 .../cecc321b-efbd-434e-8a31-a97bbb8bbb3b.json |  42 ++++++-
 .../278c2132-3415-48f4-a839-ed09d71e9240.json |  42 ++++++-
 .../92bbda1a-ecb1-493d-aa39-a29522c1a11e.json |  42 ++++++-
 .../f43b2dff-9e73-4779-86e0-b2cc30ae8b40.json |  42 ++++++-
 .../59a98f5d-d017-4b1a-a563-5abd113337e9.json |  42 ++++++-
 .../a41597ed-fbab-41af-9625-c277ca988546.json |  42 ++++++-
 .../e311eb59-f217-4bc2-b69b-dcea434797a8.json |  42 ++++++-
 .../69b037c3-bae2-4889-b10d-e732c45851e9.json |  42 ++++++-
 .../adeee000-0b62-4a0c-afaa-5e8c5f29ff6d.json |  42 ++++++-
 .../4464d588-62b2-440b-8188-2450bd7a94c5.json |  42 ++++++-
 .../bf358648-a41d-43ee-8c14-f8b8eef41871.json |  42 ++++++-
 .../afd99f12-f739-40d3-aa11-ef3a45316931.json |  42 ++++++-
 .../49b4a24b-ddf1-47f0-ba39-9366892a1213.json |  42 ++++++-
 .../ea14a487-39c3-488b-b52b-998e57135487.json |  42 ++++++-
 .../02f74b6a-7f63-484e-a7c1-0c53bd801b87.json |  42 ++++++-
 .../e492c59d-4b03-4dce-983e-a8724de35a60.json |  42 ++++++-
 .../53de0394-8516-4882-b2bc-c7e62e3d8ef0.json |  42 ++++++-
 .../56d4c1c5-5238-45dc-8331-64a14b830779.json |  42 ++++++-
 .../7003c9d4-c758-4373-a7a3-04822978bf35.json |  42 ++++++-
 .../75a7dcb6-789c-49de-b209-4cf7d27465e4.json |  42 ++++++-
 .../e91d3910-4f20-4e82-b1fb-8605f5d2b8ac.json |  42 ++++++-
 .../f18bfd44-3097-4eb8-a09c-2372c3ecd738.json |  42 ++++++-
 .../9ca974b9-c5fb-4fc4-ab3e-1246e31ecdb2.json |  42 ++++++-
 .../fb1ab5e0-18db-4e5f-add3-2352d9a1f260.json |  42 ++++++-
 .../60ba1f0d-7e85-49e4-8c73-330d74de6707.json |  42 ++++++-
 .../29d1c194-8b87-466c-8701-e0fcf267665c.json |  42 ++++++-
 .../31e8f616-7b64-4d1a-b395-20bf8bb4629c.json |  42 ++++++-
 .../cc3f315d-3cea-47e4-83b4-b5045e778c5e.json |  42 ++++++-
 .../5d20dbf8-bb14-46af-adcd-b7ba05f8352c.json |  42 ++++++-
 .../06f2cb33-3937-4fde-84e2-6b5467f051c6.json |  42 ++++++-
 .../f35c4efa-3767-4a0e-8769-06230cda2512.json |  42 ++++++-
 .../6cb65d6a-6c46-4991-8154-f28b101954f6.json |  42 ++++++-
 .../6e15a49b-7dc4-4d69-965e-cb962c084e4a.json |  42 ++++++-
 .../9f5591f4-751d-48d3-a348-4bb59f6bb1a3.json |  42 ++++++-
 .../b609c002-fa0a-46a8-b5a1-9213ee89606c.json |  42 ++++++-
 .../b147fc7f-0e31-49ca-abfd-ba990a925097.json |  42 ++++++-
 .../e4fbfe23-2b70-459e-821b-db0116d43d8c.json |  42 ++++++-
 .../2ab7dc14-af3e-4fb2-8c0c-fe0e14100321.json |  42 ++++++-
 .../aca2c665-79f2-4226-b806-307be277ed08.json |  42 ++++++-
 .../d37a63df-6d38-4083-bf87-11064162efde.json |  42 ++++++-
 .../16e550cc-e59d-4aaa-b221-8cf71e1b26d2.json |  42 ++++++-
 .../47058e2a-dc41-45f8-8c32-bc496a8d3bc5.json |  37 +++++-
 .../7199c8b3-8346-4200-b07e-4362ad13a7db.json |  37 +++++-
 .../de7e59d5-e2ce-4479-bbd9-ab9deb3beed3.json |  37 +++++-
 .../17e011c3-1a53-40ae-b7b4-cb24c23df3de.json |  37 +++++-
 .../1125dd05-2f0d-48ca-825c-f5efa18564aa.json |  37 +++++-
 .../88014e0d-e89b-4fed-9eb6-5276bd7658df.json |  37 +++++-
 .../7cc9bfc2-570d-456c-918f-68fd4b711f05.json |  37 +++++-
 .../77b0957f-8779-4dbe-a6ea-cff50c4ee73b.json |  37 +++++-
 .../ba0ce7ce-a755-4337-bfec-0391680d3625.json |  32 ++++-
 .../4eb460eb-b3ad-4e0d-b131-5b59ef54015c.json |  32 ++++-
 .../6868a1e5-ee86-4f89-8452-5e939ac19169.json |  32 ++++-
 .../4a151d43-5fac-4afe-9c23-ba0e86a60849.json |  32 ++++-
 .../5f16d574-adef-4016-abcf-9e7936771ba7.json |  32 ++++-
 .../f3e0300f-39ed-4cfd-bd03-218904836037.json |  37 +++++-
 .../42c82c00-b74e-4152-a222-15d481a13e0c.json |  42 ++++++-
 .../68096be8-c49f-4a23-824e-1275248369f7.json |  32 ++++-
 .../c91270bd-3731-452a-b429-6cd4943d1194.json |  32 ++++-
 .../337c7a43-46a7-4acb-b7f1-936e1f2cf46f.json |  42 ++++++-
 .../3b00f881-8f73-4608-8cbb-846fe7d1cfea.json |  42 ++++++-
 .../2821dfdc-291b-405e-bd81-cf536c802885.json |  42 ++++++-
 .../7d441240-7e85-4776-b51c-3c1bc84456ba.json |  42 ++++++-
 .../840d35d9-441e-4ba3-bbc3-1f4ff2627517.json |  32 ++++-
 .../0127f3c5-9657-4eb6-a77a-5a6476a8fc79.json |  37 +++++-
 .../b72e2988-75e4-4d26-9a47-daae4786b02f.json |  42 ++++++-
 .../643cf5a3-8992-4126-87c9-814887314266.json |  42 ++++++-
 .../f81f1f67-6506-481f-87ce-a17a6a7578f3.json |  32 ++++-
 .../32b35218-a099-410e-8a65-a0d6e2f380a6.json |  42 ++++++-
 .../deec1e7c-0cb8-4e6f-b3ac-d37790b709f3.json |  32 ++++-
 .../e42a9986-4dcc-4017-be97-8135646c7424.json |  32 ++++-
 .../ffc92063-606a-4f31-bfdd-5683aa748ccc.json |  42 ++++++-
 .../23a5398c-0911-4a66-930d-abada12bf985.json |  42 ++++++-
 .../80b0bbcb-a57a-453c-8fff-502646520b1d.json |  32 ++++-
 .../e383c939-b952-4fdd-94e3-eb3716691860.json |  37 +++++-
 .../daf873f9-ab03-49df-96cb-a0f5a8613048.json |  37 +++++-
 .../f4cff132-3b2f-4e03-bb49-098b16d87cef.json |  32 ++++-
 .../f80685de-058c-4ab8-aa35-dc7321d1cea6.json |  37 +++++-
 .../c8e4349d-a084-4eb5-990f-403ba930a9ad.json |  37 +++++-
 .../729ca9c0-0680-49f1-97b9-5581be17a352.json |  32 ++++-
 .../fdd4add5-b44d-46f9-8c98-da3120df4161.json |  32 ++++-
 .../6b5ef643-30dd-4381-b66f-e9ecd6b0d06e.json |  32 ++++-
 .../95271b8c-4135-48bf-bbad-ae94baa37640.json |  32 ++++-
 .../f437e790-efe1-4dc5-8ccc-5b0bfd800069.json |  32 ++++-
 .../7d0f761a-2650-4029-b1e9-13af2f0cc69d.json |  37 +++++-
 .../49fc601e-4ac6-4672-a53d-0e89f19959c1.json |  37 +++++-
 .../6195e81a-d5a5-40af-96f6-259252009ad7.json |  32 ++++-
 .../2dec0f50-d374-4af3-9d27-80fcf50dac2c.json |  42 ++++++-
 .../96722888-0cc9-4dfd-b38d-91f4118c0be2.json |  32 ++++-
 .../683abc2a-fce0-4d3d-bdcc-5cac2c76a46a.json |  32 ++++-
 .../121344ec-61ef-49c5-a74b-b86f605d513e.json |  42 ++++++-
 .../8594f86b-a7f2-4046-a3a7-830d7ac20690.json |  32 ++++-
 .../c0c5e5e1-801c-48fd-a994-a4a69c0b1213.json |  32 ++++-
 .../0411ac30-1536-4639-8350-fc11d53298e3.json |  32 ++++-
 .../92281e58-4160-4d76-9119-b38fb47ffd8f.json |  32 ++++-
 .../43687871-2e19-4d2b-9754-1cb6527496c1.json |  32 ++++-
 .../1debe1de-b394-4856-a946-9d14bd867bf6.json |  37 +++++-
 .../80c589d2-c1eb-4dcf-8be8-042f4f66b7eb.json |  37 +++++-
 .../62478772-bb85-4d3f-a916-c3d17db3ee61.json |  37 +++++-
 .../a070bae2-c927-418b-91cc-161781c4f5b7.json |  42 ++++++-
 .../b884c919-a272-4f67-9a09-3d232f56d083.json |  42 ++++++-
 .../deac33dd-187b-4406-a76a-b33caf417380.json |  42 ++++++-
 .../185bd742-d7d4-4600-86bd-bcda75ed2ebc.json |  37 +++++-
 .../901e4de6-3ef6-4c2a-873c-cdcc47201974.json |  32 ++++-
 .../a051d5d6-18e6-483d-a000-4a52a06de676.json |  42 ++++++-
 .../94d77182-8952-4a63-b02b-3d8bd8a8dead.json |  32 ++++-
 .../9a48d808-0280-4175-a28a-7e9ba8ac6deb.json |  42 ++++++-
 .../f0d9f57d-d552-44ea-a91c-751854133316.json |  37 +++++-
 .../561cfba1-856d-4809-b5c7-41481735e1d6.json |  42 ++++++-
 .../995d1caf-b735-44dd-adff-875e3203aa46.json |  37 +++++-
 .../81767043-23c2-4229-b3b5-1c24e470d52a.json |  37 +++++-
 .../4f6344bc-af30-46f9-b6f8-41ff925d064e.json |  37 +++++-
 .../abac8640-40be-4eb5-9035-2bf6fd436a7a.json |  42 ++++++-
 .../6fd972ab-c45f-4ccd-a5cf-4aac5e703342.json |  32 ++++-
 .../8eb1bcf2-a6bd-467c-bc37-090fdb7a9460.json |  32 ++++-
 .../5ad53725-ed5a-41f3-8ff6-7404f3f981db.json |  32 ++++-
 .../ae2d05b4-5e80-4b00-af67-b94609b073eb.json |  32 ++++-
 .../592f2811-c197-423e-89d4-e25ee5a324fb.json |  32 ++++-
 .../17795e7b-e912-440f-a80e-63233d3b6d8c.json |  32 ++++-
 .../375cf55f-64f6-42f6-a947-1487feffb196.json |  37 +++++-
 .../94d2eddd-f7db-4360-ac58-0af39ce66935.json |  42 ++++++-
 .../996ca604-e01c-4a95-9286-60b6dc04f67d.json |  37 +++++-
 .../b6f0089f-d04b-4bcd-be84-ce3bc0d6c2b9.json |  37 +++++-
 .../83e15cba-4fec-48f2-9be4-78decbd96f66.json |  37 +++++-
 .../493617c0-37eb-4c83-b175-2507a3647b5e.json |  37 +++++-
 .../97f494ce-3c9c-4a19-a237-d458be611a0a.json |  37 +++++-
 .../f8bf1e92-3cc3-4c7e-9770-485a3074e85f.json |  37 +++++-
 .../5bf73fba-520f-4a2f-9296-8240847eb8ec.json |  37 +++++-
 .../3dd2c89f-64f5-4bbc-a621-791a9f0538b2.json |  37 +++++-
 .../ef987556-7277-48d8-ac07-532586773a3a.json |  32 ++++-
 .../add7eddb-7a8b-4c78-9864-c4316a97ce5e.json |  37 +++++-
 .../caf02954-1eed-44eb-b5f4-df47c90828d7.json |  37 +++++-
 .../00798930-daa2-4e79-82c6-2cccf1c3a0cb.json |  37 +++++-
 .../71658cf8-0189-49dc-847f-b9a9b5faee4a.json |  42 ++++++-
 .../3d506b91-5b0d-47e3-a3a0-bc09808bf5b5.json |  37 +++++-
 .../04c71231-2025-4e1a-b7ed-56b245868089.json |  37 +++++-
 .../08b2edd0-f8e9-47cd-b19d-53fdc7209917.json |  42 ++++++-
 .../79a43841-4032-4a20-8b5a-83b4b446d107.json |  37 +++++-
 .../a2c16ab8-1098-490a-8d0a-392d835427e0.json |  42 ++++++-
 .../0aa12860-7ebe-49c2-a5af-1926d23e34f8.json |  37 +++++-
 .../796d3ec1-9c26-4ead-87cb-4eb866209120.json |  42 ++++++-
 scripts/rewardbench/adapter.py                |  24 +++-
 scripts/rewardbench/migrate_to_v020.py        | 113 ++++++++++++++++++
 scripts/utils/__init__.py                     |   8 ++
 scripts/utils/schema.py                       |  97 +++++++++++++--
 388 files changed, 13016 insertions(+), 1934 deletions(-)
 create mode 100644 scripts/rewardbench/migrate_to_v020.py

diff --git a/data/reward-bench/0-hero/Matter-0.1-7B-DPO-preview/623bae1f-19e9-47f9-bc7b-80a859218d07.json b/data/reward-bench/0-hero/Matter-0.1-7B-DPO-preview/623bae1f-19e9-47f9-bc7b-80a859218d07.json
index a27298ad0..cef912137 100644
--- a/data/reward-bench/0-hero/Matter-0.1-7B-DPO-preview/623bae1f-19e9-47f9-bc7b-80a859218d07.json
+++ b/data/reward-bench/0-hero/Matter-0.1-7B-DPO-preview/623bae1f-19e9-47f9-bc7b-80a859218d07.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/0-hero_Matter-0.1-7B-DPO-preview/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7247
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8939
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5768
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6378
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8854
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5348
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/0-hero/Matter-0.1-7B-boost-DPO-preview/fbba98c5-5d56-4837-9044-d4e5ac610c2c.json b/data/reward-bench/0-hero/Matter-0.1-7B-boost-DPO-preview/fbba98c5-5d56-4837-9044-d4e5ac610c2c.json
index c4e185274..2e9c3f43d 100644
--- a/data/reward-bench/0-hero/Matter-0.1-7B-boost-DPO-preview/fbba98c5-5d56-4837-9044-d4e5ac610c2c.json
+++ b/data/reward-bench/0-hero/Matter-0.1-7B-boost-DPO-preview/fbba98c5-5d56-4837-9044-d4e5ac610c2c.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/0-hero_Matter-0.1-7B-boost-DPO-preview/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7448
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9106
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6096
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7135
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8395
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5566
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Ahjeong/MMPO_Gemma_7b/dc6e1164-c9d7-4dd5-b8dc-fbc4e3f45011.json b/data/reward-bench/Ahjeong/MMPO_Gemma_7b/dc6e1164-c9d7-4dd5-b8dc-fbc4e3f45011.json
index b43b13f02..89456cf7f 100644
--- a/data/reward-bench/Ahjeong/MMPO_Gemma_7b/dc6e1164-c9d7-4dd5-b8dc-fbc4e3f45011.json
+++ b/data/reward-bench/Ahjeong/MMPO_Gemma_7b/dc6e1164-c9d7-4dd5-b8dc-fbc4e3f45011.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Ahjeong_MMPO_Gemma_7b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7587
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9693
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.614
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7135
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7756
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6831
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3/c62a913b-3101-4ce3-a5c5-a1ac844e55f8.json b/data/reward-bench/Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3/c62a913b-3101-4ce3-a5c5-a1ac844e55f8.json
index 0e64d13ad..f147a68de 100644
--- a/data/reward-bench/Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3/c62a913b-3101-4ce3-a5c5-a1ac844e55f8.json
+++ b/data/reward-bench/Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3/c62a913b-3101-4ce3-a5c5-a1ac844e55f8.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Ahjeong_MMPO_Gemma_7b_gamma1.1_epoch3/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7652
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9721
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6338
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7635
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6913
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Anthropic/claude-3-5-sonnet-20240620/3101726d-fd51-436d-8adf-cbdf0d534834.json b/data/reward-bench/Anthropic/claude-3-5-sonnet-20240620/3101726d-fd51-436d-8adf-cbdf0d534834.json
index 619ba0c5a..9aaa4ec32 100644
--- a/data/reward-bench/Anthropic/claude-3-5-sonnet-20240620/3101726d-fd51-436d-8adf-cbdf0d534834.json
+++ b/data/reward-bench/Anthropic/claude-3-5-sonnet-20240620/3101726d-fd51-436d-8adf-cbdf0d534834.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/anthropic_claude-3-5-sonnet-20240620/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6466
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3875
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5683
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8519
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8697
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.674
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Anthropic/claude-3-5-sonnet-20240620/f878a52a-fa80-4113-ae7d-0cb11e3ef9fd.json b/data/reward-bench/Anthropic/claude-3-5-sonnet-20240620/f878a52a-fa80-4113-ae7d-0cb11e3ef9fd.json
index e8c404a58..4e001bb6c 100644
--- a/data/reward-bench/Anthropic/claude-3-5-sonnet-20240620/f878a52a-fa80-4113-ae7d-0cb11e3ef9fd.json
+++ b/data/reward-bench/Anthropic/claude-3-5-sonnet-20240620/f878a52a-fa80-4113-ae7d-0cb11e3ef9fd.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Anthropic_claude-3-5-sonnet-20240620/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8417
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9637
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7401
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8162
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.8469
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Anthropic/claude-3-7-sonnet-20250219/904c6359-bd7b-4448-9f16-bc115d0629c4.json b/data/reward-bench/Anthropic/claude-3-7-sonnet-20250219/904c6359-bd7b-4448-9f16-bc115d0629c4.json
index 74591cc2b..47b1297ca 100644
--- a/data/reward-bench/Anthropic/claude-3-7-sonnet-20250219/904c6359-bd7b-4448-9f16-bc115d0629c4.json
+++ b/data/reward-bench/Anthropic/claude-3-7-sonnet-20250219/904c6359-bd7b-4448-9f16-bc115d0629c4.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/anthropic_claude-3-7-sonnet-20250219/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7539
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7326
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5437
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.75
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9033
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9212
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6723
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Anthropic/claude-3-haiku-20240307/49511052-6881-4151-9b46-686c75f73c22.json b/data/reward-bench/Anthropic/claude-3-haiku-20240307/49511052-6881-4151-9b46-686c75f73c22.json
index 1e5b98c04..6e0f3e1b3 100644
--- a/data/reward-bench/Anthropic/claude-3-haiku-20240307/49511052-6881-4151-9b46-686c75f73c22.json
+++ b/data/reward-bench/Anthropic/claude-3-haiku-20240307/49511052-6881-4151-9b46-686c75f73c22.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/anthropic_claude-3-haiku-20240307/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.3711
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.4042
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.2812
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.3552
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.595
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.501
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.0899
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Anthropic/claude-3-haiku-20240307/b289e2e6-d57b-4a2b-aa61-e2974d193909.json b/data/reward-bench/Anthropic/claude-3-haiku-20240307/b289e2e6-d57b-4a2b-aa61-e2974d193909.json
index 03e1c4f0a..16656cf8a 100644
--- a/data/reward-bench/Anthropic/claude-3-haiku-20240307/b289e2e6-d57b-4a2b-aa61-e2974d193909.json
+++ b/data/reward-bench/Anthropic/claude-3-haiku-20240307/b289e2e6-d57b-4a2b-aa61-e2974d193909.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Anthropic_claude-3-haiku-20240307/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7289
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9274
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5197
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7953
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.706
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6635
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Anthropic/claude-3-opus-20240229/aeeca919-71a1-42a0-a6d0-6779d77750e6.json b/data/reward-bench/Anthropic/claude-3-opus-20240229/aeeca919-71a1-42a0-a6d0-6779d77750e6.json
index 551660420..dd51285f1 100644
--- a/data/reward-bench/Anthropic/claude-3-opus-20240229/aeeca919-71a1-42a0-a6d0-6779d77750e6.json
+++ b/data/reward-bench/Anthropic/claude-3-opus-20240229/aeeca919-71a1-42a0-a6d0-6779d77750e6.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Anthropic_claude-3-opus-20240229/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8008
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9469
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6031
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8662
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.7868
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Anthropic/claude-3-opus-20240229/db29538d-f40e-42d0-b3c0-e622f92112d2.json b/data/reward-bench/Anthropic/claude-3-opus-20240229/db29538d-f40e-42d0-b3c0-e622f92112d2.json
index 6a4ce0e30..1c912c7c4 100644
--- a/data/reward-bench/Anthropic/claude-3-opus-20240229/db29538d-f40e-42d0-b3c0-e622f92112d2.json
+++ b/data/reward-bench/Anthropic/claude-3-opus-20240229/db29538d-f40e-42d0-b3c0-e622f92112d2.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/anthropic_claude-3-opus-20240229/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5744
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5389
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3312
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5137
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8378
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6646
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5601
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Anthropic/claude-3-sonnet-20240229/ab0cdc4f-47dd-4dcc-b506-982ce3924105.json b/data/reward-bench/Anthropic/claude-3-sonnet-20240229/ab0cdc4f-47dd-4dcc-b506-982ce3924105.json
index b3e532d32..3721b0f48 100644
--- a/data/reward-bench/Anthropic/claude-3-sonnet-20240229/ab0cdc4f-47dd-4dcc-b506-982ce3924105.json
+++ b/data/reward-bench/Anthropic/claude-3-sonnet-20240229/ab0cdc4f-47dd-4dcc-b506-982ce3924105.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Anthropic_claude-3-sonnet-20240229/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7458
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9344
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5658
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8169
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6907
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6963
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Anthropic/claude-opus-4-20250514/44da63b6-d934-4330-bc20-33464bae61dd.json b/data/reward-bench/Anthropic/claude-opus-4-20250514/44da63b6-d934-4330-bc20-33464bae61dd.json
index cc0ce43c9..8dffb9139 100644
--- a/data/reward-bench/Anthropic/claude-opus-4-20250514/44da63b6-d934-4330-bc20-33464bae61dd.json
+++ b/data/reward-bench/Anthropic/claude-opus-4-20250514/44da63b6-d934-4330-bc20-33464bae61dd.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/anthropic_claude-opus-4-20250514/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7648
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8267
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4188
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7491
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8954
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8616
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.8375
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Anthropic/claude-sonnet-4-20250514/c930cbe0-f429-4b61-9abe-86dcb7266cf7.json b/data/reward-bench/Anthropic/claude-sonnet-4-20250514/c930cbe0-f429-4b61-9abe-86dcb7266cf7.json
index 7029d7203..45d756c32 100644
--- a/data/reward-bench/Anthropic/claude-sonnet-4-20250514/c930cbe0-f429-4b61-9abe-86dcb7266cf7.json
+++ b/data/reward-bench/Anthropic/claude-sonnet-4-20250514/c930cbe0-f429-4b61-9abe-86dcb7266cf7.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/anthropic_claude-sonnet-4-20250514/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7117
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7612
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3594
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7049
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8909
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7596
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.7939
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/AtlaAI/Selene-1-Mini-Llama-3.1-8B/c84b27b2-2dd9-48ee-9a53-ec27ae62ae7a.json b/data/reward-bench/AtlaAI/Selene-1-Mini-Llama-3.1-8B/c84b27b2-2dd9-48ee-9a53-ec27ae62ae7a.json
index 3b18998ef..e1c13041b 100644
--- a/data/reward-bench/AtlaAI/Selene-1-Mini-Llama-3.1-8B/c84b27b2-2dd9-48ee-9a53-ec27ae62ae7a.json
+++ b/data/reward-bench/AtlaAI/Selene-1-Mini-Llama-3.1-8B/c84b27b2-2dd9-48ee-9a53-ec27ae62ae7a.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/AtlaAI_Selene-1-Mini-Llama-3.1-8B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8913
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9358
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7939
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8926
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9429
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/AtlaAI/Selene-1/73ee9408-e669-4b8a-9419-76bd6051ce8d.json b/data/reward-bench/AtlaAI/Selene-1/73ee9408-e669-4b8a-9419-76bd6051ce8d.json
index 0b508fc12..e90407d26 100644
--- a/data/reward-bench/AtlaAI/Selene-1/73ee9408-e669-4b8a-9419-76bd6051ce8d.json
+++ b/data/reward-bench/AtlaAI/Selene-1/73ee9408-e669-4b8a-9419-76bd6051ce8d.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/AtlaAI_Selene-1/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9241
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9777
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8399
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9216
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9572
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/CIR-AMS/BTRM_Qwen2_7b_0613/0deed2f4-770e-4033-a65d-e1da19e00611.json b/data/reward-bench/CIR-AMS/BTRM_Qwen2_7b_0613/0deed2f4-770e-4033-a65d-e1da19e00611.json
index 606de4ddf..dd6dc0bf7 100644
--- a/data/reward-bench/CIR-AMS/BTRM_Qwen2_7b_0613/0deed2f4-770e-4033-a65d-e1da19e00611.json
+++ b/data/reward-bench/CIR-AMS/BTRM_Qwen2_7b_0613/0deed2f4-770e-4033-a65d-e1da19e00611.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/CIR-AMS_BTRM_Qwen2_7b_0613/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5736
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5347
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3563
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6066
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7178
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5737
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6527
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/CIR-AMS/BTRM_Qwen2_7b_0613/e727cb77-f229-4aaa-909f-99c7aa06676b.json b/data/reward-bench/CIR-AMS/BTRM_Qwen2_7b_0613/e727cb77-f229-4aaa-909f-99c7aa06676b.json
index c8ff53cce..7179fab0e 100644
--- a/data/reward-bench/CIR-AMS/BTRM_Qwen2_7b_0613/e727cb77-f229-4aaa-909f-99c7aa06676b.json
+++ b/data/reward-bench/CIR-AMS/BTRM_Qwen2_7b_0613/e727cb77-f229-4aaa-909f-99c7aa06676b.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/CIR-AMS_BTRM_Qwen2_7b_0613/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8172
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9749
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5724
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9014
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8775
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.7029
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/CohereForAI/c4ai-command-r-plus/da9264cd-2fa3-4121-81de-eef994e15993.json b/data/reward-bench/CohereForAI/c4ai-command-r-plus/da9264cd-2fa3-4121-81de-eef994e15993.json
index 4b71e3b45..10fb8ed6c 100644
--- a/data/reward-bench/CohereForAI/c4ai-command-r-plus/da9264cd-2fa3-4121-81de-eef994e15993.json
+++ b/data/reward-bench/CohereForAI/c4ai-command-r-plus/da9264cd-2fa3-4121-81de-eef994e15993.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/CohereForAI_c4ai-command-r-plus/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7057
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9511
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5757
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5986
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.704
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6924
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ContextualAI/LMUnit-llama3.1-70b/79cc5cd4-bfed-466d-9fbe-2f27e8aab175.json b/data/reward-bench/ContextualAI/LMUnit-llama3.1-70b/79cc5cd4-bfed-466d-9fbe-2f27e8aab175.json
index 40b37fe16..ff7ea07a0 100644
--- a/data/reward-bench/ContextualAI/LMUnit-llama3.1-70b/79cc5cd4-bfed-466d-9fbe-2f27e8aab175.json
+++ b/data/reward-bench/ContextualAI/LMUnit-llama3.1-70b/79cc5cd4-bfed-466d-9fbe-2f27e8aab175.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/ContextualAI_LMUnit-llama3.1-70b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8054
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8463
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4875
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7158
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9067
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9697
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.9063
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ContextualAI/LMUnit-qwen2.5-72b/28c35831-679d-489a-b2c4-fd2c7f333fbc.json b/data/reward-bench/ContextualAI/LMUnit-qwen2.5-72b/28c35831-679d-489a-b2c4-fd2c7f333fbc.json
index 64bdcfef0..8597afb51 100644
--- a/data/reward-bench/ContextualAI/LMUnit-qwen2.5-72b/28c35831-679d-489a-b2c4-fd2c7f333fbc.json
+++ b/data/reward-bench/ContextualAI/LMUnit-qwen2.5-72b/28c35831-679d-489a-b2c4-fd2c7f333fbc.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/ContextualAI_LMUnit-qwen2.5-72b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8208
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8716
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5437
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7268
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9133
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9677
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.9014
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ContextualAI/archangel_sft-dpo_llama13b/9db7907d-7b22-480c-86a5-f88ec2b302e7.json b/data/reward-bench/ContextualAI/archangel_sft-dpo_llama13b/9db7907d-7b22-480c-86a5-f88ec2b302e7.json
index ab96244b5..4aa411ea6 100644
--- a/data/reward-bench/ContextualAI/archangel_sft-dpo_llama13b/9db7907d-7b22-480c-86a5-f88ec2b302e7.json
+++ b/data/reward-bench/ContextualAI/archangel_sft-dpo_llama13b/9db7907d-7b22-480c-86a5-f88ec2b302e7.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ContextualAI_archangel_sft-dpo_llama13b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.54
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7123
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4298
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5649
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.4401
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5656
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ContextualAI/archangel_sft-dpo_llama30b/2faddf79-41e6-47e9-9c26-17bc987bc870.json b/data/reward-bench/ContextualAI/archangel_sft-dpo_llama30b/2faddf79-41e6-47e9-9c26-17bc987bc870.json
index 215ac5202..fefd98c33 100644
--- a/data/reward-bench/ContextualAI/archangel_sft-dpo_llama30b/2faddf79-41e6-47e9-9c26-17bc987bc870.json
+++ b/data/reward-bench/ContextualAI/archangel_sft-dpo_llama30b/2faddf79-41e6-47e9-9c26-17bc987bc870.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ContextualAI_archangel_sft-dpo_llama30b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5618
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6927
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4474
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.4745
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5705
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ContextualAI/archangel_sft-dpo_llama7b/20989a47-6556-4e3b-8909-d0a419cb159b.json b/data/reward-bench/ContextualAI/archangel_sft-dpo_llama7b/20989a47-6556-4e3b-8909-d0a419cb159b.json
index f40114fab..69dc72884 100644
--- a/data/reward-bench/ContextualAI/archangel_sft-dpo_llama7b/20989a47-6556-4e3b-8909-d0a419cb159b.json
+++ b/data/reward-bench/ContextualAI/archangel_sft-dpo_llama7b/20989a47-6556-4e3b-8909-d0a419cb159b.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ContextualAI_archangel_sft-dpo_llama7b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5304
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5782
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4452
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5203
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.5658
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5544
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ContextualAI/archangel_sft-dpo_pythia1-4b/f3d0010f-efed-4f87-9582-b9c87b4de99a.json b/data/reward-bench/ContextualAI/archangel_sft-dpo_pythia1-4b/f3d0010f-efed-4f87-9582-b9c87b4de99a.json
index ca3483447..c640a7456 100644
--- a/data/reward-bench/ContextualAI/archangel_sft-dpo_pythia1-4b/f3d0010f-efed-4f87-9582-b9c87b4de99a.json
+++ b/data/reward-bench/ContextualAI/archangel_sft-dpo_pythia1-4b/f3d0010f-efed-4f87-9582-b9c87b4de99a.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ContextualAI_archangel_sft-dpo_pythia1-4b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5233
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6397
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3728
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5041
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.5672
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5427
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ContextualAI/archangel_sft-dpo_pythia12-0b/a0ce3ed6-2a2c-46ad-be86-6f6701533e36.json b/data/reward-bench/ContextualAI/archangel_sft-dpo_pythia12-0b/a0ce3ed6-2a2c-46ad-be86-6f6701533e36.json
index 24d3c5885..ed72e23b9 100644
--- a/data/reward-bench/ContextualAI/archangel_sft-dpo_pythia12-0b/a0ce3ed6-2a2c-46ad-be86-6f6701533e36.json
+++ b/data/reward-bench/ContextualAI/archangel_sft-dpo_pythia12-0b/a0ce3ed6-2a2c-46ad-be86-6f6701533e36.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ContextualAI_archangel_sft-dpo_pythia12-0b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5009
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6676
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.364
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5432
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.4139
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5303
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ContextualAI/archangel_sft-dpo_pythia2-8b/d54c4830-23c8-4c12-aea1-4f5b5245464f.json b/data/reward-bench/ContextualAI/archangel_sft-dpo_pythia2-8b/d54c4830-23c8-4c12-aea1-4f5b5245464f.json
index d90b44daa..10908a053 100644
--- a/data/reward-bench/ContextualAI/archangel_sft-dpo_pythia2-8b/d54c4830-23c8-4c12-aea1-4f5b5245464f.json
+++ b/data/reward-bench/ContextualAI/archangel_sft-dpo_pythia2-8b/d54c4830-23c8-4c12-aea1-4f5b5245464f.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ContextualAI_archangel_sft-dpo_pythia2-8b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5286
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8073
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3355
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.4473
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.5135
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5501
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ContextualAI/archangel_sft-dpo_pythia6-9b/b5853278-edd9-4bc8-bbeb-d6dab515b562.json b/data/reward-bench/ContextualAI/archangel_sft-dpo_pythia6-9b/b5853278-edd9-4bc8-bbeb-d6dab515b562.json
index 998861312..40f3a091a 100644
--- a/data/reward-bench/ContextualAI/archangel_sft-dpo_pythia6-9b/b5853278-edd9-4bc8-bbeb-d6dab515b562.json
+++ b/data/reward-bench/ContextualAI/archangel_sft-dpo_pythia6-9b/b5853278-edd9-4bc8-bbeb-d6dab515b562.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ContextualAI_archangel_sft-dpo_pythia6-9b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5263
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7486
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3421
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5176
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.4847
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.551
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ContextualAI/archangel_sft-kto_llama13b/74188e30-1e49-47d8-af01-b80e430dafa0.json b/data/reward-bench/ContextualAI/archangel_sft-kto_llama13b/74188e30-1e49-47d8-af01-b80e430dafa0.json
index 3ce4e1d0e..22b4b63bd 100644
--- a/data/reward-bench/ContextualAI/archangel_sft-kto_llama13b/74188e30-1e49-47d8-af01-b80e430dafa0.json
+++ b/data/reward-bench/ContextualAI/archangel_sft-kto_llama13b/74188e30-1e49-47d8-af01-b80e430dafa0.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ContextualAI_archangel_sft-kto_llama13b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5952
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8408
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3772
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.4649
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7077
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.576
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ContextualAI/archangel_sft-kto_llama30b/93974286-0497-46a2-a2e8-404c1e89dba0.json b/data/reward-bench/ContextualAI/archangel_sft-kto_llama30b/93974286-0497-46a2-a2e8-404c1e89dba0.json
index 03921df15..ca6ff0f55 100644
--- a/data/reward-bench/ContextualAI/archangel_sft-kto_llama30b/93974286-0497-46a2-a2e8-404c1e89dba0.json
+++ b/data/reward-bench/ContextualAI/archangel_sft-kto_llama30b/93974286-0497-46a2-a2e8-404c1e89dba0.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ContextualAI_archangel_sft-kto_llama30b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5901
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8436
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4057
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6054
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.5075
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5862
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ContextualAI/archangel_sft-kto_llama7b/02c0020c-7d69-4701-a606-4bc79ad87afd.json b/data/reward-bench/ContextualAI/archangel_sft-kto_llama7b/02c0020c-7d69-4701-a606-4bc79ad87afd.json
index 556053c1d..ac5acffb2 100644
--- a/data/reward-bench/ContextualAI/archangel_sft-kto_llama7b/02c0020c-7d69-4701-a606-4bc79ad87afd.json
+++ b/data/reward-bench/ContextualAI/archangel_sft-kto_llama7b/02c0020c-7d69-4701-a606-4bc79ad87afd.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ContextualAI_archangel_sft-kto_llama7b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5388
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5587
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4364
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.4568
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6941
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5575
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ContextualAI/archangel_sft-kto_pythia1-4b/5dcb7c54-64e7-4f76-8903-8f57b35cdb0c.json b/data/reward-bench/ContextualAI/archangel_sft-kto_pythia1-4b/5dcb7c54-64e7-4f76-8903-8f57b35cdb0c.json
index 04509bcea..36044c710 100644
--- a/data/reward-bench/ContextualAI/archangel_sft-kto_pythia1-4b/5dcb7c54-64e7-4f76-8903-8f57b35cdb0c.json
+++ b/data/reward-bench/ContextualAI/archangel_sft-kto_pythia1-4b/5dcb7c54-64e7-4f76-8903-8f57b35cdb0c.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ContextualAI_archangel_sft-kto_pythia1-4b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5581
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6844
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3794
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5257
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6447
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5546
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ContextualAI/archangel_sft-kto_pythia12-0b/4887256e-0545-40dd-9756-ff850e003a29.json b/data/reward-bench/ContextualAI/archangel_sft-kto_pythia12-0b/4887256e-0545-40dd-9756-ff850e003a29.json
index 07e49a4d2..16ed21233 100644
--- a/data/reward-bench/ContextualAI/archangel_sft-kto_pythia12-0b/4887256e-0545-40dd-9756-ff850e003a29.json
+++ b/data/reward-bench/ContextualAI/archangel_sft-kto_pythia12-0b/4887256e-0545-40dd-9756-ff850e003a29.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ContextualAI_archangel_sft-kto_pythia12-0b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5053
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7486
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3618
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.4757
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.4127
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.55
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ContextualAI/archangel_sft-kto_pythia2-8b/d2b70870-9cbc-4666-bbd4-097fcebe716e.json b/data/reward-bench/ContextualAI/archangel_sft-kto_pythia2-8b/d2b70870-9cbc-4666-bbd4-097fcebe716e.json
index fc9b9fbf2..4c1047aa1 100644
--- a/data/reward-bench/ContextualAI/archangel_sft-kto_pythia2-8b/d2b70870-9cbc-4666-bbd4-097fcebe716e.json
+++ b/data/reward-bench/ContextualAI/archangel_sft-kto_pythia2-8b/d2b70870-9cbc-4666-bbd4-097fcebe716e.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ContextualAI_archangel_sft-kto_pythia2-8b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5497
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.757
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3421
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.4743
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6216
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.557
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ContextualAI/archangel_sft-kto_pythia6-9b/f420f432-2291-40a9-8ebd-b91241970113.json b/data/reward-bench/ContextualAI/archangel_sft-kto_pythia6-9b/f420f432-2291-40a9-8ebd-b91241970113.json
index 132d06441..521c30c11 100644
--- a/data/reward-bench/ContextualAI/archangel_sft-kto_pythia6-9b/f420f432-2291-40a9-8ebd-b91241970113.json
+++ b/data/reward-bench/ContextualAI/archangel_sft-kto_pythia6-9b/f420f432-2291-40a9-8ebd-b91241970113.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ContextualAI_archangel_sft-kto_pythia6-9b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5561
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7765
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3618
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5365
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.5415
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5723
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Databricks-Mosaic-Research/PGRM/02e68d1b-86f3-4344-ad8d-45df878b744c.json b/data/reward-bench/Databricks-Mosaic-Research/PGRM/02e68d1b-86f3-4344-ad8d-45df878b744c.json
index 4e96fe9f0..5d22f5c2e 100644
--- a/data/reward-bench/Databricks-Mosaic-Research/PGRM/02e68d1b-86f3-4344-ad8d-45df878b744c.json
+++ b/data/reward-bench/Databricks-Mosaic-Research/PGRM/02e68d1b-86f3-4344-ad8d-45df878b744c.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/Databricks-Mosaic-Research_PGRM/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8002
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7937
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5062
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7404
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9289
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9424
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.8893
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/HFXM/RAMO-Llama3.1-8B/f712ab4a-1127-44ba-b6b9-7a40290f3322.json b/data/reward-bench/HFXM/RAMO-Llama3.1-8B/f712ab4a-1127-44ba-b6b9-7a40290f3322.json
index 15402671e..7ccfc23f1 100644
--- a/data/reward-bench/HFXM/RAMO-Llama3.1-8B/f712ab4a-1127-44ba-b6b9-7a40290f3322.json
+++ b/data/reward-bench/HFXM/RAMO-Llama3.1-8B/f712ab4a-1127-44ba-b6b9-7a40290f3322.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/HFXM_RAMO-Llama3.1-8B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6917
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6547
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.375
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5628
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9756
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9071
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6752
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/HuggingFaceH4/starchat2-15b-v0.1/b4175f0f-f9f4-4418-b4aa-a31e7f1f93f4.json b/data/reward-bench/HuggingFaceH4/starchat2-15b-v0.1/b4175f0f-f9f4-4418-b4aa-a31e7f1f93f4.json
index 4d710efce..a6b1abca8 100644
--- a/data/reward-bench/HuggingFaceH4/starchat2-15b-v0.1/b4175f0f-f9f4-4418-b4aa-a31e7f1f93f4.json
+++ b/data/reward-bench/HuggingFaceH4/starchat2-15b-v0.1/b4175f0f-f9f4-4418-b4aa-a31e7f1f93f4.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/HuggingFaceH4_starchat2-15b-v0.1/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7322
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9385
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5548
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7095
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8159
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5525
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/HuggingFaceH4/zephyr-7b-alpha/9879e9a7-ddbc-4338-abc7-e3bc394869e9.json b/data/reward-bench/HuggingFaceH4/zephyr-7b-alpha/9879e9a7-ddbc-4338-abc7-e3bc394869e9.json
index 86a8b8344..b313fb87e 100644
--- a/data/reward-bench/HuggingFaceH4/zephyr-7b-alpha/9879e9a7-ddbc-4338-abc7-e3bc394869e9.json
+++ b/data/reward-bench/HuggingFaceH4/zephyr-7b-alpha/9879e9a7-ddbc-4338-abc7-e3bc394869e9.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/HuggingFaceH4_zephyr-7b-alpha/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7392
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9162
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.625
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7662
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7514
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5353
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/HuggingFaceH4/zephyr-7b-beta/d7d8a5cb-e295-4ced-b528-d99d814ff008.json b/data/reward-bench/HuggingFaceH4/zephyr-7b-beta/d7d8a5cb-e295-4ced-b528-d99d814ff008.json
index 36c56448c..7d0709109 100644
--- a/data/reward-bench/HuggingFaceH4/zephyr-7b-beta/d7d8a5cb-e295-4ced-b528-d99d814ff008.json
+++ b/data/reward-bench/HuggingFaceH4/zephyr-7b-beta/d7d8a5cb-e295-4ced-b528-d99d814ff008.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/HuggingFaceH4_zephyr-7b-beta/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7281
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9525
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6272
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6568
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7789
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5216
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/HuggingFaceH4/zephyr-7b-gemma-v0.1/bff86a1f-71c3-4f27-aeae-bba6d03635ef.json b/data/reward-bench/HuggingFaceH4/zephyr-7b-gemma-v0.1/bff86a1f-71c3-4f27-aeae-bba6d03635ef.json
index ea611719b..89a96432c 100644
--- a/data/reward-bench/HuggingFaceH4/zephyr-7b-gemma-v0.1/bff86a1f-71c3-4f27-aeae-bba6d03635ef.json
+++ b/data/reward-bench/HuggingFaceH4/zephyr-7b-gemma-v0.1/bff86a1f-71c3-4f27-aeae-bba6d03635ef.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/HuggingFaceH4_zephyr-7b-gemma-v0.1/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6758
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9581
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4956
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5824
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7463
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5171
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/IDEA-CCNL/Ziya-LLaMA-7B-Reward/723281f8-54b7-4db6-8253-5a6dcf4f3d4a.json b/data/reward-bench/IDEA-CCNL/Ziya-LLaMA-7B-Reward/723281f8-54b7-4db6-8253-5a6dcf4f3d4a.json
index e8bc23b6a..73199f618 100644
--- a/data/reward-bench/IDEA-CCNL/Ziya-LLaMA-7B-Reward/723281f8-54b7-4db6-8253-5a6dcf4f3d4a.json
+++ b/data/reward-bench/IDEA-CCNL/Ziya-LLaMA-7B-Reward/723281f8-54b7-4db6-8253-5a6dcf4f3d4a.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/IDEA-CCNL_Ziya-LLaMA-7B-Reward/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6378
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8687
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4605
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6405
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.5775
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6461
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/LxzGordon/URM-LLaMa-3-8B/0ce7dc54-f608-4985-9904-75cee09b6288.json b/data/reward-bench/LxzGordon/URM-LLaMa-3-8B/0ce7dc54-f608-4985-9904-75cee09b6288.json
index 9f7301f3d..2f1093e30 100644
--- a/data/reward-bench/LxzGordon/URM-LLaMa-3-8B/0ce7dc54-f608-4985-9904-75cee09b6288.json
+++ b/data/reward-bench/LxzGordon/URM-LLaMa-3-8B/0ce7dc54-f608-4985-9904-75cee09b6288.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/LxzGordon_URM-LLaMa-3-8B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8991
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9693
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7873
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8824
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9574
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/LxzGordon/URM-LLaMa-3.1-8B/5bb0aaa4-2cc5-4622-8235-993bc4178f12.json b/data/reward-bench/LxzGordon/URM-LLaMa-3.1-8B/5bb0aaa4-2cc5-4622-8235-993bc4178f12.json
index b34ec8f07..d56005468 100644
--- a/data/reward-bench/LxzGordon/URM-LLaMa-3.1-8B/5bb0aaa4-2cc5-4622-8235-993bc4178f12.json
+++ b/data/reward-bench/LxzGordon/URM-LLaMa-3.1-8B/5bb0aaa4-2cc5-4622-8235-993bc4178f12.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/LxzGordon_URM-LLaMa-3.1-8B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9294
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9553
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8816
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9108
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9698
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/LxzGordon/URM-LLaMa-3.1-8B/85ab22b8-0587-4e2b-857f-3d6d84d571a4.json b/data/reward-bench/LxzGordon/URM-LLaMa-3.1-8B/85ab22b8-0587-4e2b-857f-3d6d84d571a4.json
index 7ce19f3b5..a57e5caa3 100644
--- a/data/reward-bench/LxzGordon/URM-LLaMa-3.1-8B/85ab22b8-0587-4e2b-857f-3d6d84d571a4.json
+++ b/data/reward-bench/LxzGordon/URM-LLaMa-3.1-8B/85ab22b8-0587-4e2b-857f-3d6d84d571a4.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/LxzGordon_URM-LLaMa-3.1-8B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7394
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6884
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.45
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6393
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9178
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9758
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.7653
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/NCSOFT/Llama-3-OffsetBias-8B/37aa6702-b2fa-43bf-b5a9-36740f627217.json b/data/reward-bench/NCSOFT/Llama-3-OffsetBias-8B/37aa6702-b2fa-43bf-b5a9-36740f627217.json
index d03295a6a..a9c1eb53c 100644
--- a/data/reward-bench/NCSOFT/Llama-3-OffsetBias-8B/37aa6702-b2fa-43bf-b5a9-36740f627217.json
+++ b/data/reward-bench/NCSOFT/Llama-3-OffsetBias-8B/37aa6702-b2fa-43bf-b5a9-36740f627217.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/NCSOFT_Llama-3-OffsetBias-8B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8397
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9246
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8026
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8676
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.7639
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/NCSOFT/Llama-3-OffsetBias-RM-8B/57f48d0c-e424-410d-b9ee-4707e2add036.json b/data/reward-bench/NCSOFT/Llama-3-OffsetBias-RM-8B/57f48d0c-e424-410d-b9ee-4707e2add036.json
index ab1c474bd..f38bf29f7 100644
--- a/data/reward-bench/NCSOFT/Llama-3-OffsetBias-RM-8B/57f48d0c-e424-410d-b9ee-4707e2add036.json
+++ b/data/reward-bench/NCSOFT/Llama-3-OffsetBias-RM-8B/57f48d0c-e424-410d-b9ee-4707e2add036.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/NCSOFT_Llama-3-OffsetBias-RM-8B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8942
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9721
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.818
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8676
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9192
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/NCSOFT/Llama-3-OffsetBias-RM-8B/8643b4dd-e18c-442c-adb5-84ef756534f8.json b/data/reward-bench/NCSOFT/Llama-3-OffsetBias-RM-8B/8643b4dd-e18c-442c-adb5-84ef756534f8.json
index fd43b8778..ec0f3756c 100644
--- a/data/reward-bench/NCSOFT/Llama-3-OffsetBias-RM-8B/8643b4dd-e18c-442c-adb5-84ef756534f8.json
+++ b/data/reward-bench/NCSOFT/Llama-3-OffsetBias-RM-8B/8643b4dd-e18c-442c-adb5-84ef756534f8.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/NCSOFT_Llama-3-OffsetBias-RM-8B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.648
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6084
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5191
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7222
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9596
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6786
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Nexusflow/Starling-RM-34B/2f3d2e46-1f9e-4b1c-9729-ab0a93cc245c.json b/data/reward-bench/Nexusflow/Starling-RM-34B/2f3d2e46-1f9e-4b1c-9729-ab0a93cc245c.json
index 8e269f55a..3b7921590 100644
--- a/data/reward-bench/Nexusflow/Starling-RM-34B/2f3d2e46-1f9e-4b1c-9729-ab0a93cc245c.json
+++ b/data/reward-bench/Nexusflow/Starling-RM-34B/2f3d2e46-1f9e-4b1c-9729-ab0a93cc245c.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Nexusflow_Starling-RM-34B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8133
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9693
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5724
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.877
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8845
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.7137
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Nexusflow/Starling-RM-34B/4aec78d3-a38c-48e0-b9e2-b6dc063bd37e.json b/data/reward-bench/Nexusflow/Starling-RM-34B/4aec78d3-a38c-48e0-b9e2-b6dc063bd37e.json
index 6a782cd05..a2c665080 100644
--- a/data/reward-bench/Nexusflow/Starling-RM-34B/4aec78d3-a38c-48e0-b9e2-b6dc063bd37e.json
+++ b/data/reward-bench/Nexusflow/Starling-RM-34B/4aec78d3-a38c-48e0-b9e2-b6dc063bd37e.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/Nexusflow_Starling-RM-34B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.4553
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.4589
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3187
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6175
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7556
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.4808
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.1004
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/NousResearch/Hermes-3-Llama-3.1-70B/f9b60945-8b14-4564-9d44-3eb6db675ab9.json b/data/reward-bench/NousResearch/Hermes-3-Llama-3.1-70B/f9b60945-8b14-4564-9d44-3eb6db675ab9.json
index 1bd4f9222..734675894 100644
--- a/data/reward-bench/NousResearch/Hermes-3-Llama-3.1-70B/f9b60945-8b14-4564-9d44-3eb6db675ab9.json
+++ b/data/reward-bench/NousResearch/Hermes-3-Llama-3.1-70B/f9b60945-8b14-4564-9d44-3eb6db675ab9.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/NousResearch_Hermes-3-Llama-3.1-70B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7847
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9623
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5669
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.823
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.7867
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/NousResearch/Nous-Hermes-2-Mistral-7B-DPO/56703c11-eccb-4f66-af13-60f972a5068f.json b/data/reward-bench/NousResearch/Nous-Hermes-2-Mistral-7B-DPO/56703c11-eccb-4f66-af13-60f972a5068f.json
index 28eb5c34d..0e770043c 100644
--- a/data/reward-bench/NousResearch/Nous-Hermes-2-Mistral-7B-DPO/56703c11-eccb-4f66-af13-60f972a5068f.json
+++ b/data/reward-bench/NousResearch/Nous-Hermes-2-Mistral-7B-DPO/56703c11-eccb-4f66-af13-60f972a5068f.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/NousResearch_Nous-Hermes-2-Mistral-7B-DPO/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7481
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9218
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6053
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8243
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7375
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.555
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO/fbd8be7e-5670-4729-a77d-83472510b734.json b/data/reward-bench/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO/fbd8be7e-5670-4729-a77d-83472510b734.json
index f190b81a1..99623d8ff 100644
--- a/data/reward-bench/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO/fbd8be7e-5670-4729-a77d-83472510b734.json
+++ b/data/reward-bench/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO/fbd8be7e-5670-4729-a77d-83472510b734.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/NousResearch_Nous-Hermes-2-Mixtral-8x7B-DPO/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7138
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9162
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6053
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8149
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6126
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5266
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/OpenAssistant/oasst-rm-2-pythia-6.9b-epoch-1/2e18ee77-9c46-4cf9-9521-303ad15e5be4.json b/data/reward-bench/OpenAssistant/oasst-rm-2-pythia-6.9b-epoch-1/2e18ee77-9c46-4cf9-9521-303ad15e5be4.json
index 4c1ad8e64..31e05eb58 100644
--- a/data/reward-bench/OpenAssistant/oasst-rm-2-pythia-6.9b-epoch-1/2e18ee77-9c46-4cf9-9521-303ad15e5be4.json
+++ b/data/reward-bench/OpenAssistant/oasst-rm-2-pythia-6.9b-epoch-1/2e18ee77-9c46-4cf9-9521-303ad15e5be4.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/OpenAssistant_oasst-rm-2-pythia-6.9b-epoch-1/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.615
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9246
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3728
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5446
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.5855
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6801
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/OpenAssistant/oasst-rm-2-pythia-6.9b-epoch-1/ec5b296e-03e8-4371-a8c1-eca0b0b9759d.json b/data/reward-bench/OpenAssistant/oasst-rm-2-pythia-6.9b-epoch-1/ec5b296e-03e8-4371-a8c1-eca0b0b9759d.json
index 4d37887c0..dfed08cd8 100644
--- a/data/reward-bench/OpenAssistant/oasst-rm-2-pythia-6.9b-epoch-1/ec5b296e-03e8-4371-a8c1-eca0b0b9759d.json
+++ b/data/reward-bench/OpenAssistant/oasst-rm-2-pythia-6.9b-epoch-1/ec5b296e-03e8-4371-a8c1-eca0b0b9759d.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/OpenAssistant_oasst-rm-2-pythia-6.9b-epoch-1/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.2653
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.3979
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.2875
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.377
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.3289
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.1535
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.047
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/OpenAssistant/oasst-rm-2.1-pythia-1.4b-epoch-2.5/07b61a55-a8e3-4a6f-9806-a4100f8d5297.json b/data/reward-bench/OpenAssistant/oasst-rm-2.1-pythia-1.4b-epoch-2.5/07b61a55-a8e3-4a6f-9806-a4100f8d5297.json
index 23d7514d9..85e007109 100644
--- a/data/reward-bench/OpenAssistant/oasst-rm-2.1-pythia-1.4b-epoch-2.5/07b61a55-a8e3-4a6f-9806-a4100f8d5297.json
+++ b/data/reward-bench/OpenAssistant/oasst-rm-2.1-pythia-1.4b-epoch-2.5/07b61a55-a8e3-4a6f-9806-a4100f8d5297.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/OpenAssistant_oasst-rm-2.1-pythia-1.4b-epoch-2.5/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6901
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8855
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4868
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6311
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7752
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6533
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/OpenAssistant/oasst-rm-2.1-pythia-1.4b-epoch-2.5/3d534c25-5016-44de-9c47-24b7d7399b0f.json b/data/reward-bench/OpenAssistant/oasst-rm-2.1-pythia-1.4b-epoch-2.5/3d534c25-5016-44de-9c47-24b7d7399b0f.json
index bad24200c..38eca68e4 100644
--- a/data/reward-bench/OpenAssistant/oasst-rm-2.1-pythia-1.4b-epoch-2.5/3d534c25-5016-44de-9c47-24b7d7399b0f.json
+++ b/data/reward-bench/OpenAssistant/oasst-rm-2.1-pythia-1.4b-epoch-2.5/3d534c25-5016-44de-9c47-24b7d7399b0f.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/OpenAssistant_oasst-rm-2.1-pythia-1.4b-epoch-2.5/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.2648
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.3179
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.2625
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.3934
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.3244
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.2707
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.0198
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/OpenAssistant/reward-model-deberta-v3-large-v2/4de91433-05b3-4f88-9d0f-66691c671f62.json b/data/reward-bench/OpenAssistant/reward-model-deberta-v3-large-v2/4de91433-05b3-4f88-9d0f-66691c671f62.json
index 88c6cf6ea..365667594 100644
--- a/data/reward-bench/OpenAssistant/reward-model-deberta-v3-large-v2/4de91433-05b3-4f88-9d0f-66691c671f62.json
+++ b/data/reward-bench/OpenAssistant/reward-model-deberta-v3-large-v2/4de91433-05b3-4f88-9d0f-66691c671f62.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/OpenAssistant_reward-model-deberta-v3-large-v2/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.32
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.3853
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.2687
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5027
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.3667
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.2768
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.12
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/OpenAssistant/reward-model-deberta-v3-large-v2/dc71f1ba-f4b8-4231-ac72-0acf9a22d73e.json b/data/reward-bench/OpenAssistant/reward-model-deberta-v3-large-v2/dc71f1ba-f4b8-4231-ac72-0acf9a22d73e.json
index a8597cef2..4712b7f92 100644
--- a/data/reward-bench/OpenAssistant/reward-model-deberta-v3-large-v2/dc71f1ba-f4b8-4231-ac72-0acf9a22d73e.json
+++ b/data/reward-bench/OpenAssistant/reward-model-deberta-v3-large-v2/dc71f1ba-f4b8-4231-ac72-0acf9a22d73e.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/OpenAssistant_reward-model-deberta-v3-large-v2/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6126
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8939
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4518
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7338
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.3855
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5836
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/PKU-Alignment/beaver-7b-v1.0-cost/36c4adc9-c2fb-4bc3-81ba-88478d30332e.json b/data/reward-bench/PKU-Alignment/beaver-7b-v1.0-cost/36c4adc9-c2fb-4bc3-81ba-88478d30332e.json
index 77c839a13..ae927c59e 100644
--- a/data/reward-bench/PKU-Alignment/beaver-7b-v1.0-cost/36c4adc9-c2fb-4bc3-81ba-88478d30332e.json
+++ b/data/reward-bench/PKU-Alignment/beaver-7b-v1.0-cost/36c4adc9-c2fb-4bc3-81ba-88478d30332e.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/PKU-Alignment_beaver-7b-v1.0-cost/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5798
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6173
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4232
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7351
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.5482
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.57
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/PKU-Alignment/beaver-7b-v1.0-cost/f0827b15-20d0-4986-b5a0-bb4bc9be768e.json b/data/reward-bench/PKU-Alignment/beaver-7b-v1.0-cost/f0827b15-20d0-4986-b5a0-bb4bc9be768e.json
index 1d30468c7..9e4c95ee2 100644
--- a/data/reward-bench/PKU-Alignment/beaver-7b-v1.0-cost/f0827b15-20d0-4986-b5a0-bb4bc9be768e.json
+++ b/data/reward-bench/PKU-Alignment/beaver-7b-v1.0-cost/f0827b15-20d0-4986-b5a0-bb4bc9be768e.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/PKU-Alignment_beaver-7b-v1.0-cost/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.3332
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.3263
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.2313
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.3989
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7589
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.2939
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": -0.01
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/PKU-Alignment/beaver-7b-v1.0-reward/aeaa8b33-e327-4c65-9641-5dfc63feee3b.json b/data/reward-bench/PKU-Alignment/beaver-7b-v1.0-reward/aeaa8b33-e327-4c65-9641-5dfc63feee3b.json
index 36bcdfdc9..fc41926be 100644
--- a/data/reward-bench/PKU-Alignment/beaver-7b-v1.0-reward/aeaa8b33-e327-4c65-9641-5dfc63feee3b.json
+++ b/data/reward-bench/PKU-Alignment/beaver-7b-v1.0-reward/aeaa8b33-e327-4c65-9641-5dfc63feee3b.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/PKU-Alignment_beaver-7b-v1.0-reward/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.1606
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.2105
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.2938
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.2623
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.1422
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.0646
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": -0.01
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/PKU-Alignment/beaver-7b-v1.0-reward/c97c79f3-fd92-49db-9131-5e45834a7eaf.json b/data/reward-bench/PKU-Alignment/beaver-7b-v1.0-reward/c97c79f3-fd92-49db-9131-5e45834a7eaf.json
index 2100e18c1..d06d08a3c 100644
--- a/data/reward-bench/PKU-Alignment/beaver-7b-v1.0-reward/c97c79f3-fd92-49db-9131-5e45834a7eaf.json
+++ b/data/reward-bench/PKU-Alignment/beaver-7b-v1.0-reward/c97c79f3-fd92-49db-9131-5e45834a7eaf.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/PKU-Alignment_beaver-7b-v1.0-reward/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.4727
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8184
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.2873
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.3757
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.346
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5993
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/PKU-Alignment/beaver-7b-v2.0-cost/687099cb-c1bf-49ec-a902-329c2b818369.json b/data/reward-bench/PKU-Alignment/beaver-7b-v2.0-cost/687099cb-c1bf-49ec-a902-329c2b818369.json
index e0c222d4d..3868ab64e 100644
--- a/data/reward-bench/PKU-Alignment/beaver-7b-v2.0-cost/687099cb-c1bf-49ec-a902-329c2b818369.json
+++ b/data/reward-bench/PKU-Alignment/beaver-7b-v2.0-cost/687099cb-c1bf-49ec-a902-329c2b818369.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/PKU-Alignment_beaver-7b-v2.0-cost/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.3326
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.3789
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.275
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.3333
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7356
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.2828
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": -0.01
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/PKU-Alignment/beaver-7b-v2.0-cost/8da4f5eb-6264-4503-b9bc-fcf843b638be.json b/data/reward-bench/PKU-Alignment/beaver-7b-v2.0-cost/8da4f5eb-6264-4503-b9bc-fcf843b638be.json
index 5908eca1e..4af7bc7a5 100644
--- a/data/reward-bench/PKU-Alignment/beaver-7b-v2.0-cost/8da4f5eb-6264-4503-b9bc-fcf843b638be.json
+++ b/data/reward-bench/PKU-Alignment/beaver-7b-v2.0-cost/8da4f5eb-6264-4503-b9bc-fcf843b638be.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/PKU-Alignment_beaver-7b-v2.0-cost/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5957
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5726
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4561
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7608
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6211
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5397
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/PKU-Alignment/beaver-7b-v2.0-reward/28a68b87-5412-4374-9e61-896b0fff7669.json b/data/reward-bench/PKU-Alignment/beaver-7b-v2.0-reward/28a68b87-5412-4374-9e61-896b0fff7669.json
index 45166e401..376b686c0 100644
--- a/data/reward-bench/PKU-Alignment/beaver-7b-v2.0-reward/28a68b87-5412-4374-9e61-896b0fff7669.json
+++ b/data/reward-bench/PKU-Alignment/beaver-7b-v2.0-reward/28a68b87-5412-4374-9e61-896b0fff7669.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/PKU-Alignment_beaver-7b-v2.0-reward/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.2544
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.2168
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.2562
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.3825
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.3156
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.2606
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.0944
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/PKU-Alignment/beaver-7b-v2.0-reward/3209c869-03c5-4801-8e4b-4c8bcde3d58f.json b/data/reward-bench/PKU-Alignment/beaver-7b-v2.0-reward/3209c869-03c5-4801-8e4b-4c8bcde3d58f.json
index 39d9d8ddf..49fb24c89 100644
--- a/data/reward-bench/PKU-Alignment/beaver-7b-v2.0-reward/3209c869-03c5-4801-8e4b-4c8bcde3d58f.json
+++ b/data/reward-bench/PKU-Alignment/beaver-7b-v2.0-reward/3209c869-03c5-4801-8e4b-4c8bcde3d58f.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/PKU-Alignment_beaver-7b-v2.0-reward/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6366
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8994
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.364
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6041
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6887
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6171
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/PoLL/gpt-3.5-turbo-0125_claude-3-sonnet-2024022.../9d1e124c-e133-41d3-8ac7-5c8c5027aa02.json b/data/reward-bench/PoLL/gpt-3.5-turbo-0125_claude-3-sonnet-2024022.../9d1e124c-e133-41d3-8ac7-5c8c5027aa02.json
index 88bc18eb8..f9da09026 100644
--- a/data/reward-bench/PoLL/gpt-3.5-turbo-0125_claude-3-sonnet-2024022.../9d1e124c-e133-41d3-8ac7-5c8c5027aa02.json
+++ b/data/reward-bench/PoLL/gpt-3.5-turbo-0125_claude-3-sonnet-2024022.../9d1e124c-e133-41d3-8ac7-5c8c5027aa02.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/PoLL_gpt-3.5-turbo-0125_claude-3-sonnet-2024022.../1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7578
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9525
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5406
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8034
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.7346
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Qwen/Qwen1.5-0.5B-Chat/633d499b-58bd-4fca-9b56-0f005a5a21b8.json b/data/reward-bench/Qwen/Qwen1.5-0.5B-Chat/633d499b-58bd-4fca-9b56-0f005a5a21b8.json
index 41b56ed43..8753b5ea8 100644
--- a/data/reward-bench/Qwen/Qwen1.5-0.5B-Chat/633d499b-58bd-4fca-9b56-0f005a5a21b8.json
+++ b/data/reward-bench/Qwen/Qwen1.5-0.5B-Chat/633d499b-58bd-4fca-9b56-0f005a5a21b8.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Qwen_Qwen1.5-0.5B-Chat/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5298
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.3547
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6294
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5703
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.5984
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.4629
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Qwen/Qwen1.5-1.8B-Chat/5c4f3caf-6af3-48c6-83e2-4710d31e6acf.json b/data/reward-bench/Qwen/Qwen1.5-1.8B-Chat/5c4f3caf-6af3-48c6-83e2-4710d31e6acf.json
index ef965fde9..48dfa65fd 100644
--- a/data/reward-bench/Qwen/Qwen1.5-1.8B-Chat/5c4f3caf-6af3-48c6-83e2-4710d31e6acf.json
+++ b/data/reward-bench/Qwen/Qwen1.5-1.8B-Chat/5c4f3caf-6af3-48c6-83e2-4710d31e6acf.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Qwen_Qwen1.5-1.8B-Chat/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.589
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5615
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6031
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.4838
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7793
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.4453
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Qwen/Qwen1.5-14B-Chat/77d1edc1-fb54-4371-bf7c-baebbb351163.json b/data/reward-bench/Qwen/Qwen1.5-14B-Chat/77d1edc1-fb54-4371-bf7c-baebbb351163.json
index d5fc3341b..f34eee3d4 100644
--- a/data/reward-bench/Qwen/Qwen1.5-14B-Chat/77d1edc1-fb54-4371-bf7c-baebbb351163.json
+++ b/data/reward-bench/Qwen/Qwen1.5-14B-Chat/77d1edc1-fb54-4371-bf7c-baebbb351163.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Qwen_Qwen1.5-14B-Chat/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6864
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5726
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7018
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7122
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8961
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.4123
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Qwen/Qwen1.5-4B-Chat/e7eecdb0-bc17-4d9f-b3e8-9ee777d2f595.json b/data/reward-bench/Qwen/Qwen1.5-4B-Chat/e7eecdb0-bc17-4d9f-b3e8-9ee777d2f595.json
index ce4ff66dd..85d507824 100644
--- a/data/reward-bench/Qwen/Qwen1.5-4B-Chat/e7eecdb0-bc17-4d9f-b3e8-9ee777d2f595.json
+++ b/data/reward-bench/Qwen/Qwen1.5-4B-Chat/e7eecdb0-bc17-4d9f-b3e8-9ee777d2f595.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Qwen_Qwen1.5-4B-Chat/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5477
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.3883
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6272
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5568
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6689
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.447
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Qwen/Qwen1.5-72B-Chat/3f3915b3-0d6e-451c-9185-fa4372b93f2b.json b/data/reward-bench/Qwen/Qwen1.5-72B-Chat/3f3915b3-0d6e-451c-9185-fa4372b93f2b.json
index c36fc9a9f..f3cc894c3 100644
--- a/data/reward-bench/Qwen/Qwen1.5-72B-Chat/3f3915b3-0d6e-451c-9185-fa4372b93f2b.json
+++ b/data/reward-bench/Qwen/Qwen1.5-72B-Chat/3f3915b3-0d6e-451c-9185-fa4372b93f2b.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Qwen_Qwen1.5-72B-Chat/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6723
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6229
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6601
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6757
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8554
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.4226
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Qwen/Qwen1.5-7B-Chat/e534d37b-3009-4a7d-82d8-d7c85b95649e.json b/data/reward-bench/Qwen/Qwen1.5-7B-Chat/e534d37b-3009-4a7d-82d8-d7c85b95649e.json
index 62722eeef..2373972cd 100644
--- a/data/reward-bench/Qwen/Qwen1.5-7B-Chat/e534d37b-3009-4a7d-82d8-d7c85b95649e.json
+++ b/data/reward-bench/Qwen/Qwen1.5-7B-Chat/e534d37b-3009-4a7d-82d8-d7c85b95649e.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Qwen_Qwen1.5-7B-Chat/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.675
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5363
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6908
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6919
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9041
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.4288
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Qwen/Qwen1.5-MoE-A2.7B-Chat/bd8f0ed1-75fc-48c1-996e-655d205c027c.json b/data/reward-bench/Qwen/Qwen1.5-MoE-A2.7B-Chat/bd8f0ed1-75fc-48c1-996e-655d205c027c.json
index b694ee08b..7daa3735e 100644
--- a/data/reward-bench/Qwen/Qwen1.5-MoE-A2.7B-Chat/bd8f0ed1-75fc-48c1-996e-655d205c027c.json
+++ b/data/reward-bench/Qwen/Qwen1.5-MoE-A2.7B-Chat/bd8f0ed1-75fc-48c1-996e-655d205c027c.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Qwen_Qwen1.5-MoE-A2.7B-Chat/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6644
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7291
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6316
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.774
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.4536
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Qwen/WorldPM-72B/e9effaf6-e48b-4b35-b035-430be81b316b.json b/data/reward-bench/Qwen/WorldPM-72B/e9effaf6-e48b-4b35-b035-430be81b316b.json
index 55bff16c3..6ee54b6e7 100644
--- a/data/reward-bench/Qwen/WorldPM-72B/e9effaf6-e48b-4b35-b035-430be81b316b.json
+++ b/data/reward-bench/Qwen/WorldPM-72B/e9effaf6-e48b-4b35-b035-430be81b316b.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/Qwen_WorldPM-72B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6333
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7074
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3125
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6557
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8533
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9172
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.3535
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/R-I-S-E/RISE-Judge-Qwen2.5-32B/d2132eea-eb88-41e5-b8e6-2e8e8a623ed1.json b/data/reward-bench/R-I-S-E/RISE-Judge-Qwen2.5-32B/d2132eea-eb88-41e5-b8e6-2e8e8a623ed1.json
index 5cad58eb3..d48e6bfec 100644
--- a/data/reward-bench/R-I-S-E/RISE-Judge-Qwen2.5-32B/d2132eea-eb88-41e5-b8e6-2e8e8a623ed1.json
+++ b/data/reward-bench/R-I-S-E/RISE-Judge-Qwen2.5-32B/d2132eea-eb88-41e5-b8e6-2e8e8a623ed1.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/R-I-S-E_RISE-Judge-Qwen2.5-32B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9266
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9665
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8333
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9189
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9877
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/R-I-S-E/RISE-Judge-Qwen2.5-7B/ffd05bc7-3724-40ba-85b9-c25ebe71fba2.json b/data/reward-bench/R-I-S-E/RISE-Judge-Qwen2.5-7B/ffd05bc7-3724-40ba-85b9-c25ebe71fba2.json
index ac71f5f5f..2418db79b 100644
--- a/data/reward-bench/R-I-S-E/RISE-Judge-Qwen2.5-7B/ffd05bc7-3724-40ba-85b9-c25ebe71fba2.json
+++ b/data/reward-bench/R-I-S-E/RISE-Judge-Qwen2.5-7B/ffd05bc7-3724-40ba-85b9-c25ebe71fba2.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/R-I-S-E_RISE-Judge-Qwen2.5-7B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8819
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9218
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7654
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8797
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9608
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/RLHFlow/ArmoRM-Llama3-8B-v0.1/43f0e93d-f0b8-46af-a549-e1ac315d96ea.json b/data/reward-bench/RLHFlow/ArmoRM-Llama3-8B-v0.1/43f0e93d-f0b8-46af-a549-e1ac315d96ea.json
index 4788e3bbf..7370b5a14 100644
--- a/data/reward-bench/RLHFlow/ArmoRM-Llama3-8B-v0.1/43f0e93d-f0b8-46af-a549-e1ac315d96ea.json
+++ b/data/reward-bench/RLHFlow/ArmoRM-Llama3-8B-v0.1/43f0e93d-f0b8-46af-a549-e1ac315d96ea.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/RLHFlow_ArmoRM-Llama3-8B-v0.1/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6646
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6568
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4188
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6612
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8222
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7657
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6629
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/RLHFlow/ArmoRM-Llama3-8B-v0.1/9ccab7bd-d2ed-4ab3-ad81-656650c29a3b.json b/data/reward-bench/RLHFlow/ArmoRM-Llama3-8B-v0.1/9ccab7bd-d2ed-4ab3-ad81-656650c29a3b.json
index e46af9896..41532e2cf 100644
--- a/data/reward-bench/RLHFlow/ArmoRM-Llama3-8B-v0.1/9ccab7bd-d2ed-4ab3-ad81-656650c29a3b.json
+++ b/data/reward-bench/RLHFlow/ArmoRM-Llama3-8B-v0.1/9ccab7bd-d2ed-4ab3-ad81-656650c29a3b.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/RLHFlow_ArmoRM-Llama3-8B-v0.1/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.886
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9693
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7675
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9054
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9735
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.7429
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/RLHFlow/LLaMA3-iterative-DPO-final/c10d4213-f1fa-41e6-92d9-0d5337c1362b.json b/data/reward-bench/RLHFlow/LLaMA3-iterative-DPO-final/c10d4213-f1fa-41e6-92d9-0d5337c1362b.json
index 4f2ac0d9d..e8c6cfc5b 100644
--- a/data/reward-bench/RLHFlow/LLaMA3-iterative-DPO-final/c10d4213-f1fa-41e6-92d9-0d5337c1362b.json
+++ b/data/reward-bench/RLHFlow/LLaMA3-iterative-DPO-final/c10d4213-f1fa-41e6-92d9-0d5337c1362b.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/RLHFlow_LLaMA3-iterative-DPO-final/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6783
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.838
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5921
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7865
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6161
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.4392
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/RLHFlow/RewardModel-Mistral-7B-for-DPA-v1/63b08ba0-eeb9-48ae-a5d1-d7d3792aa1c0.json b/data/reward-bench/RLHFlow/RewardModel-Mistral-7B-for-DPA-v1/63b08ba0-eeb9-48ae-a5d1-d7d3792aa1c0.json
index 271dde1c8..35d7a9ebf 100644
--- a/data/reward-bench/RLHFlow/RewardModel-Mistral-7B-for-DPA-v1/63b08ba0-eeb9-48ae-a5d1-d7d3792aa1c0.json
+++ b/data/reward-bench/RLHFlow/RewardModel-Mistral-7B-for-DPA-v1/63b08ba0-eeb9-48ae-a5d1-d7d3792aa1c0.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/RLHFlow_RewardModel-Mistral-7B-for-DPA-v1/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6633
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8799
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4978
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7068
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.5971
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6068
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/RLHFlow/pair-preference-model-LLaMA3-8B/d724076d-509f-4ad4-894c-976b0472de85.json b/data/reward-bench/RLHFlow/pair-preference-model-LLaMA3-8B/d724076d-509f-4ad4-894c-976b0472de85.json
index db8b6e695..ee0769a51 100644
--- a/data/reward-bench/RLHFlow/pair-preference-model-LLaMA3-8B/d724076d-509f-4ad4-894c-976b0472de85.json
+++ b/data/reward-bench/RLHFlow/pair-preference-model-LLaMA3-8B/d724076d-509f-4ad4-894c-976b0472de85.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/RLHFlow_pair-preference-model-LLaMA3-8B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8575
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9832
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6579
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8973
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9473
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.7458
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Ray2333/GRM-Gemma-2B-rewardmodel-ft/54d34f25-1cd9-4995-8e56-c36981842fc8.json b/data/reward-bench/Ray2333/GRM-Gemma-2B-rewardmodel-ft/54d34f25-1cd9-4995-8e56-c36981842fc8.json
index ea2e28411..05c7b0ff2 100644
--- a/data/reward-bench/Ray2333/GRM-Gemma-2B-rewardmodel-ft/54d34f25-1cd9-4995-8e56-c36981842fc8.json
+++ b/data/reward-bench/Ray2333/GRM-Gemma-2B-rewardmodel-ft/54d34f25-1cd9-4995-8e56-c36981842fc8.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Ray2333_GRM-Gemma-2B-rewardmodel-ft/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8447
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8939
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7522
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8446
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.8881
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Ray2333/GRM-Gemma-2B-sftreg/63ae1c75-fd4d-4f40-afd0-b9f91d700014.json b/data/reward-bench/Ray2333/GRM-Gemma-2B-sftreg/63ae1c75-fd4d-4f40-afd0-b9f91d700014.json
index dedd0ad29..8a5814b51 100644
--- a/data/reward-bench/Ray2333/GRM-Gemma-2B-sftreg/63ae1c75-fd4d-4f40-afd0-b9f91d700014.json
+++ b/data/reward-bench/Ray2333/GRM-Gemma-2B-sftreg/63ae1c75-fd4d-4f40-afd0-b9f91d700014.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Ray2333_GRM-Gemma-2B-sftreg/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7451
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9553
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4868
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7932
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7684
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6983
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Ray2333/GRM-Llama3-8B-rewardmodel-ft/1d5ebbce-8cfe-446b-82c0-a227d4e9247f.json b/data/reward-bench/Ray2333/GRM-Llama3-8B-rewardmodel-ft/1d5ebbce-8cfe-446b-82c0-a227d4e9247f.json
index 61a889811..ae24803ba 100644
--- a/data/reward-bench/Ray2333/GRM-Llama3-8B-rewardmodel-ft/1d5ebbce-8cfe-446b-82c0-a227d4e9247f.json
+++ b/data/reward-bench/Ray2333/GRM-Llama3-8B-rewardmodel-ft/1d5ebbce-8cfe-446b-82c0-a227d4e9247f.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Ray2333_GRM-Llama3-8B-rewardmodel-ft/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9154
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9553
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8618
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9081
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9362
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Ray2333/GRM-Llama3-8B-rewardmodel-ft/3f9c81ac-5c76-43b4-a27d-7eaa055139c4.json b/data/reward-bench/Ray2333/GRM-Llama3-8B-rewardmodel-ft/3f9c81ac-5c76-43b4-a27d-7eaa055139c4.json
index 1e19c6890..2f035232b 100644
--- a/data/reward-bench/Ray2333/GRM-Llama3-8B-rewardmodel-ft/3f9c81ac-5c76-43b4-a27d-7eaa055139c4.json
+++ b/data/reward-bench/Ray2333/GRM-Llama3-8B-rewardmodel-ft/3f9c81ac-5c76-43b4-a27d-7eaa055139c4.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/Ray2333_GRM-Llama3-8B-rewardmodel-ft/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6766
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6274
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.35
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5847
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9222
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8929
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6824
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Ray2333/GRM-gemma2-2B-rewardmodel-ft/680098fb-76cf-47b6-a0ea-a1a06ca46dca.json b/data/reward-bench/Ray2333/GRM-gemma2-2B-rewardmodel-ft/680098fb-76cf-47b6-a0ea-a1a06ca46dca.json
index 1f04a08e6..fa7e8dccb 100644
--- a/data/reward-bench/Ray2333/GRM-gemma2-2B-rewardmodel-ft/680098fb-76cf-47b6-a0ea-a1a06ca46dca.json
+++ b/data/reward-bench/Ray2333/GRM-gemma2-2B-rewardmodel-ft/680098fb-76cf-47b6-a0ea-a1a06ca46dca.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/Ray2333_GRM-gemma2-2B-rewardmodel-ft/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5966
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5305
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3125
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5902
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9222
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7455
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4788
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Ray2333/GRM-gemma2-2B-rewardmodel-ft/6ec21338-9908-4ce4-a1f2-dac14c5e27ab.json b/data/reward-bench/Ray2333/GRM-gemma2-2B-rewardmodel-ft/6ec21338-9908-4ce4-a1f2-dac14c5e27ab.json
index 03ffaccd8..79c0a560c 100644
--- a/data/reward-bench/Ray2333/GRM-gemma2-2B-rewardmodel-ft/6ec21338-9908-4ce4-a1f2-dac14c5e27ab.json
+++ b/data/reward-bench/Ray2333/GRM-gemma2-2B-rewardmodel-ft/6ec21338-9908-4ce4-a1f2-dac14c5e27ab.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Ray2333_GRM-gemma2-2B-rewardmodel-ft/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8839
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9302
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7719
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9216
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.912
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Ray2333/GRM-llama3-8B-distill/592ad1e3-8a48-4c39-8013-81d7c731780f.json b/data/reward-bench/Ray2333/GRM-llama3-8B-distill/592ad1e3-8a48-4c39-8013-81d7c731780f.json
index 499d8ac36..3c94abda8 100644
--- a/data/reward-bench/Ray2333/GRM-llama3-8B-distill/592ad1e3-8a48-4c39-8013-81d7c731780f.json
+++ b/data/reward-bench/Ray2333/GRM-llama3-8B-distill/592ad1e3-8a48-4c39-8013-81d7c731780f.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Ray2333_GRM-llama3-8B-distill/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8464
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9832
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6842
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8676
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9133
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.7209
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Ray2333/GRM-llama3-8B-distill/5b36f0af-7ff6-4564-9714-08fbf41d261f.json b/data/reward-bench/Ray2333/GRM-llama3-8B-distill/5b36f0af-7ff6-4564-9714-08fbf41d261f.json
index 79518e254..7a518a591 100644
--- a/data/reward-bench/Ray2333/GRM-llama3-8B-distill/5b36f0af-7ff6-4564-9714-08fbf41d261f.json
+++ b/data/reward-bench/Ray2333/GRM-llama3-8B-distill/5b36f0af-7ff6-4564-9714-08fbf41d261f.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/Ray2333_GRM-llama3-8B-distill/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.589
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5874
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3875
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5902
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7222
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6727
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5743
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Ray2333/GRM-llama3-8B-sftreg/04f120c6-b648-4c83-81d8-05118efb0904.json b/data/reward-bench/Ray2333/GRM-llama3-8B-sftreg/04f120c6-b648-4c83-81d8-05118efb0904.json
index 65a99ac02..fd63fed4b 100644
--- a/data/reward-bench/Ray2333/GRM-llama3-8B-sftreg/04f120c6-b648-4c83-81d8-05118efb0904.json
+++ b/data/reward-bench/Ray2333/GRM-llama3-8B-sftreg/04f120c6-b648-4c83-81d8-05118efb0904.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Ray2333_GRM-llama3-8B-sftreg/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8542
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.986
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6776
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8919
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9229
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.7309
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Ray2333/GRM-llama3-8B-sftreg/c907e494-ab2e-4a28-a28d-aeb68eb818ed.json b/data/reward-bench/Ray2333/GRM-llama3-8B-sftreg/c907e494-ab2e-4a28-a28d-aeb68eb818ed.json
index 4e9d051e4..c42486675 100644
--- a/data/reward-bench/Ray2333/GRM-llama3-8B-sftreg/c907e494-ab2e-4a28-a28d-aeb68eb818ed.json
+++ b/data/reward-bench/Ray2333/GRM-llama3-8B-sftreg/c907e494-ab2e-4a28-a28d-aeb68eb818ed.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/Ray2333_GRM-llama3-8B-sftreg/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6089
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6189
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3875
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5792
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7867
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6828
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5981
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Ray2333/GRM-llama3.2-3B-rewardmodel-ft/d9eed240-ebbe-482f-8dae-c5251ed6d067.json b/data/reward-bench/Ray2333/GRM-llama3.2-3B-rewardmodel-ft/d9eed240-ebbe-482f-8dae-c5251ed6d067.json
index 394d5ae65..ef4f104a0 100644
--- a/data/reward-bench/Ray2333/GRM-llama3.2-3B-rewardmodel-ft/d9eed240-ebbe-482f-8dae-c5251ed6d067.json
+++ b/data/reward-bench/Ray2333/GRM-llama3.2-3B-rewardmodel-ft/d9eed240-ebbe-482f-8dae-c5251ed6d067.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Ray2333_GRM-llama3.2-3B-rewardmodel-ft/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9092
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9162
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8487
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.927
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.945
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Ray2333/Gemma-2B-rewardmodel-baseline/670865e1-f219-465b-9fbe-6da6f73ac9e6.json b/data/reward-bench/Ray2333/Gemma-2B-rewardmodel-baseline/670865e1-f219-465b-9fbe-6da6f73ac9e6.json
index 94d947a18..429660d5b 100644
--- a/data/reward-bench/Ray2333/Gemma-2B-rewardmodel-baseline/670865e1-f219-465b-9fbe-6da6f73ac9e6.json
+++ b/data/reward-bench/Ray2333/Gemma-2B-rewardmodel-baseline/670865e1-f219-465b-9fbe-6da6f73ac9e6.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Ray2333_Gemma-2B-rewardmodel-baseline/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.729
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9413
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4693
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7865
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7384
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6897
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Ray2333/Gemma-2B-rewardmodel-ft/88953298-b63e-499f-a31e-f0f586c4772d.json b/data/reward-bench/Ray2333/Gemma-2B-rewardmodel-ft/88953298-b63e-499f-a31e-f0f586c4772d.json
index ca7b25606..f7eece540 100644
--- a/data/reward-bench/Ray2333/Gemma-2B-rewardmodel-ft/88953298-b63e-499f-a31e-f0f586c4772d.json
+++ b/data/reward-bench/Ray2333/Gemma-2B-rewardmodel-ft/88953298-b63e-499f-a31e-f0f586c4772d.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Ray2333_Gemma-2B-rewardmodel-ft/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8048
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7793
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7478
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8527
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.8393
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Ray2333/reward-model-Mistral-7B-instruct-Unifie.../3acb690c-ffc0-4e67-8ae1-e79bcee4f824.json b/data/reward-bench/Ray2333/reward-model-Mistral-7B-instruct-Unifie.../3acb690c-ffc0-4e67-8ae1-e79bcee4f824.json
index 17c691fe8..9a4e578d4 100644
--- a/data/reward-bench/Ray2333/reward-model-Mistral-7B-instruct-Unifie.../3acb690c-ffc0-4e67-8ae1-e79bcee4f824.json
+++ b/data/reward-bench/Ray2333/reward-model-Mistral-7B-instruct-Unifie.../3acb690c-ffc0-4e67-8ae1-e79bcee4f824.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Ray2333_reward-model-Mistral-7B-instruct-Unifie.../1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7661
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9777
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5066
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8527
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7389
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.7434
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/SF-Foundation/TextEval-Llama3.1-70B/6ad2cb6a-f9a3-424e-aed2-9493899872e3.json b/data/reward-bench/SF-Foundation/TextEval-Llama3.1-70B/6ad2cb6a-f9a3-424e-aed2-9493899872e3.json
index cac72f2a0..c50e15fdc 100644
--- a/data/reward-bench/SF-Foundation/TextEval-Llama3.1-70B/6ad2cb6a-f9a3-424e-aed2-9493899872e3.json
+++ b/data/reward-bench/SF-Foundation/TextEval-Llama3.1-70B/6ad2cb6a-f9a3-424e-aed2-9493899872e3.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/SF-Foundation_TextEval-Llama3.1-70B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9348
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9413
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.9013
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9324
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9641
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/SF-Foundation/TextEval-OffsetBias-12B/1892bf75-916b-4d4f-96ab-fda36872ae5d.json b/data/reward-bench/SF-Foundation/TextEval-OffsetBias-12B/1892bf75-916b-4d4f-96ab-fda36872ae5d.json
index 5fca94bb9..b71080064 100644
--- a/data/reward-bench/SF-Foundation/TextEval-OffsetBias-12B/1892bf75-916b-4d4f-96ab-fda36872ae5d.json
+++ b/data/reward-bench/SF-Foundation/TextEval-OffsetBias-12B/1892bf75-916b-4d4f-96ab-fda36872ae5d.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/SF-Foundation_TextEval-OffsetBias-12B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9105
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.919
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8662
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9203
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9365
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Salesforce/SFR-LLaMa-3.1-70B-Judge-r/e06e1863-c28f-4c96-a672-b1073c80aa71.json b/data/reward-bench/Salesforce/SFR-LLaMa-3.1-70B-Judge-r/e06e1863-c28f-4c96-a672-b1073c80aa71.json
index 02ed42a46..49c043587 100644
--- a/data/reward-bench/Salesforce/SFR-LLaMa-3.1-70B-Judge-r/e06e1863-c28f-4c96-a672-b1073c80aa71.json
+++ b/data/reward-bench/Salesforce/SFR-LLaMa-3.1-70B-Judge-r/e06e1863-c28f-4c96-a672-b1073c80aa71.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Salesforce_SFR-LLaMa-3.1-70B-Judge-r/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9272
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9693
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8476
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9162
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9757
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Salesforce/SFR-LLaMa-3.1-8B-Judge-r/d923f7aa-a9d4-406a-b5d7-bdab508f04f7.json b/data/reward-bench/Salesforce/SFR-LLaMa-3.1-8B-Judge-r/d923f7aa-a9d4-406a-b5d7-bdab508f04f7.json
index cbebf4cf5..deced96e1 100644
--- a/data/reward-bench/Salesforce/SFR-LLaMa-3.1-8B-Judge-r/d923f7aa-a9d4-406a-b5d7-bdab508f04f7.json
+++ b/data/reward-bench/Salesforce/SFR-LLaMa-3.1-8B-Judge-r/d923f7aa-a9d4-406a-b5d7-bdab508f04f7.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Salesforce_SFR-LLaMa-3.1-8B-Judge-r/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8865
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9553
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7774
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8622
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9513
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Salesforce/SFR-nemo-12B-Judge-r/5c5e40b1-e86a-4d30-b93c-f8f9e73cdca8.json b/data/reward-bench/Salesforce/SFR-nemo-12B-Judge-r/5c5e40b1-e86a-4d30-b93c-f8f9e73cdca8.json
index 4b8e440cd..616e9bc30 100644
--- a/data/reward-bench/Salesforce/SFR-nemo-12B-Judge-r/5c5e40b1-e86a-4d30-b93c-f8f9e73cdca8.json
+++ b/data/reward-bench/Salesforce/SFR-nemo-12B-Judge-r/5c5e40b1-e86a-4d30-b93c-f8f9e73cdca8.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Salesforce_SFR-nemo-12B-Judge-r/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9027
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9721
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8224
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8649
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9513
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Schrieffer/Llama-SARM-4B/59299d8c-e468-490f-8a52-eef49b0aaeea.json b/data/reward-bench/Schrieffer/Llama-SARM-4B/59299d8c-e468-490f-8a52-eef49b0aaeea.json
index f8eea126b..4492a4262 100644
--- a/data/reward-bench/Schrieffer/Llama-SARM-4B/59299d8c-e468-490f-8a52-eef49b0aaeea.json
+++ b/data/reward-bench/Schrieffer/Llama-SARM-4B/59299d8c-e468-490f-8a52-eef49b0aaeea.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/Schrieffer_Llama-SARM-4B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7379
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6874
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4281
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6448
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9178
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9556
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.7939
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ShikaiChen/LDL-Reward-Gemma-2-27B-v0.1/3ce9612f-9b57-476e-9fa4-6e63f14568a7.json b/data/reward-bench/ShikaiChen/LDL-Reward-Gemma-2-27B-v0.1/3ce9612f-9b57-476e-9fa4-6e63f14568a7.json
index 4322979ce..6723992e6 100644
--- a/data/reward-bench/ShikaiChen/LDL-Reward-Gemma-2-27B-v0.1/3ce9612f-9b57-476e-9fa4-6e63f14568a7.json
+++ b/data/reward-bench/ShikaiChen/LDL-Reward-Gemma-2-27B-v0.1/3ce9612f-9b57-476e-9fa4-6e63f14568a7.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ShikaiChen_LDL-Reward-Gemma-2-27B-v0.1/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9499
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9637
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.9079
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9378
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9903
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ShikaiChen/LDL-Reward-Gemma-2-27B-v0.1/9c605bf1-2533-43db-a610-e71c0aaecdb5.json b/data/reward-bench/ShikaiChen/LDL-Reward-Gemma-2-27B-v0.1/9c605bf1-2533-43db-a610-e71c0aaecdb5.json
index 66d1a28bd..e51beb588 100644
--- a/data/reward-bench/ShikaiChen/LDL-Reward-Gemma-2-27B-v0.1/9c605bf1-2533-43db-a610-e71c0aaecdb5.json
+++ b/data/reward-bench/ShikaiChen/LDL-Reward-Gemma-2-27B-v0.1/9c605bf1-2533-43db-a610-e71c0aaecdb5.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/ShikaiChen_LDL-Reward-Gemma-2-27B-v0.1/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7249
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7558
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.35
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6448
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9222
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9131
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.7633
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Skywork/Skywork-Critic-Llama-3.1-70B/c289f778-92b8-44df-a079-3bced33c8ab5.json b/data/reward-bench/Skywork/Skywork-Critic-Llama-3.1-70B/c289f778-92b8-44df-a079-3bced33c8ab5.json
index 399d00b39..7f469a316 100644
--- a/data/reward-bench/Skywork/Skywork-Critic-Llama-3.1-70B/c289f778-92b8-44df-a079-3bced33c8ab5.json
+++ b/data/reward-bench/Skywork/Skywork-Critic-Llama-3.1-70B/c289f778-92b8-44df-a079-3bced33c8ab5.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Skywork_Skywork-Critic-Llama-3.1-70B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9331
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9665
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8794
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9311
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9554
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Skywork/Skywork-Critic-Llama-3.1-8B/329d4101-e740-490c-9fbc-1708f76a2f61.json b/data/reward-bench/Skywork/Skywork-Critic-Llama-3.1-8B/329d4101-e740-490c-9fbc-1708f76a2f61.json
index f6484f7e1..cf3327493 100644
--- a/data/reward-bench/Skywork/Skywork-Critic-Llama-3.1-8B/329d4101-e740-490c-9fbc-1708f76a2f61.json
+++ b/data/reward-bench/Skywork/Skywork-Critic-Llama-3.1-8B/329d4101-e740-490c-9fbc-1708f76a2f61.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Skywork_Skywork-Critic-Llama-3.1-8B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8896
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9358
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8136
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9108
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.898
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Skywork/Skywork-Reward-Gemma-2-27B-v0.2/3e87f52e-b136-4cb3-8cbb-d8d8a8571051.json b/data/reward-bench/Skywork/Skywork-Reward-Gemma-2-27B-v0.2/3e87f52e-b136-4cb3-8cbb-d8d8a8571051.json
index 4fcc4b504..4ac0f4414 100644
--- a/data/reward-bench/Skywork/Skywork-Reward-Gemma-2-27B-v0.2/3e87f52e-b136-4cb3-8cbb-d8d8a8571051.json
+++ b/data/reward-bench/Skywork/Skywork-Reward-Gemma-2-27B-v0.2/3e87f52e-b136-4cb3-8cbb-d8d8a8571051.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/Skywork_Skywork-Reward-Gemma-2-27B-v0.2/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7531
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7674
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.375
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6721
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9689
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9172
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.8182
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Skywork/Skywork-Reward-Gemma-2-27B-v0.2/62b9adca-db38-46c0-a68a-ed7a8e735035.json b/data/reward-bench/Skywork/Skywork-Reward-Gemma-2-27B-v0.2/62b9adca-db38-46c0-a68a-ed7a8e735035.json
index 890821552..5c04a1152 100644
--- a/data/reward-bench/Skywork/Skywork-Reward-Gemma-2-27B-v0.2/62b9adca-db38-46c0-a68a-ed7a8e735035.json
+++ b/data/reward-bench/Skywork/Skywork-Reward-Gemma-2-27B-v0.2/62b9adca-db38-46c0-a68a-ed7a8e735035.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Skywork_Skywork-Reward-Gemma-2-27B-v0.2/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9426
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9609
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8991
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9297
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9807
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Skywork/Skywork-Reward-Gemma-2-27B/4d2f43eb-e6f3-4686-a9d9-6b6c6b68b86c.json b/data/reward-bench/Skywork/Skywork-Reward-Gemma-2-27B/4d2f43eb-e6f3-4686-a9d9-6b6c6b68b86c.json
index 5809afc66..08b4c8323 100644
--- a/data/reward-bench/Skywork/Skywork-Reward-Gemma-2-27B/4d2f43eb-e6f3-4686-a9d9-6b6c6b68b86c.json
+++ b/data/reward-bench/Skywork/Skywork-Reward-Gemma-2-27B/4d2f43eb-e6f3-4686-a9d9-6b6c6b68b86c.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/Skywork_Skywork-Reward-Gemma-2-27B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7576
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7368
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4031
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7049
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9422
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9323
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.8261
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Skywork/Skywork-Reward-Gemma-2-27B/830df3fd-d479-4af8-a92b-93d82e804fec.json b/data/reward-bench/Skywork/Skywork-Reward-Gemma-2-27B/830df3fd-d479-4af8-a92b-93d82e804fec.json
index 021c98b9c..22de7e431 100644
--- a/data/reward-bench/Skywork/Skywork-Reward-Gemma-2-27B/830df3fd-d479-4af8-a92b-93d82e804fec.json
+++ b/data/reward-bench/Skywork/Skywork-Reward-Gemma-2-27B/830df3fd-d479-4af8-a92b-93d82e804fec.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Skywork_Skywork-Reward-Gemma-2-27B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.938
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9581
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.9145
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9189
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9606
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Skywork/Skywork-Reward-Llama-3.1-8B-v0.2/0e6d85b8-aa37-448c-adb2-0da2bd13e322.json b/data/reward-bench/Skywork/Skywork-Reward-Llama-3.1-8B-v0.2/0e6d85b8-aa37-448c-adb2-0da2bd13e322.json
index a309aa94b..e5a811527 100644
--- a/data/reward-bench/Skywork/Skywork-Reward-Llama-3.1-8B-v0.2/0e6d85b8-aa37-448c-adb2-0da2bd13e322.json
+++ b/data/reward-bench/Skywork/Skywork-Reward-Llama-3.1-8B-v0.2/0e6d85b8-aa37-448c-adb2-0da2bd13e322.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Skywork_Skywork-Reward-Llama-3.1-8B-v0.2/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9313
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9469
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8838
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.927
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9675
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Skywork/Skywork-Reward-Llama-3.1-8B-v0.2/45f0bd9c-e939-4b83-a623-1db61f431500.json b/data/reward-bench/Skywork/Skywork-Reward-Llama-3.1-8B-v0.2/45f0bd9c-e939-4b83-a623-1db61f431500.json
index 2de246c7d..1941ebc04 100644
--- a/data/reward-bench/Skywork/Skywork-Reward-Llama-3.1-8B-v0.2/45f0bd9c-e939-4b83-a623-1db61f431500.json
+++ b/data/reward-bench/Skywork/Skywork-Reward-Llama-3.1-8B-v0.2/45f0bd9c-e939-4b83-a623-1db61f431500.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/Skywork_Skywork-Reward-Llama-3.1-8B-v0.2/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7175
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6968
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4062
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6011
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9422
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9414
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.7169
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Skywork/Skywork-Reward-Llama-3.1-8B/0f710903-7dd8-44ea-914d-d43bbfe894f1.json b/data/reward-bench/Skywork/Skywork-Reward-Llama-3.1-8B/0f710903-7dd8-44ea-914d-d43bbfe894f1.json
index 0b2359ed4..ba30f4f9f 100644
--- a/data/reward-bench/Skywork/Skywork-Reward-Llama-3.1-8B/0f710903-7dd8-44ea-914d-d43bbfe894f1.json
+++ b/data/reward-bench/Skywork/Skywork-Reward-Llama-3.1-8B/0f710903-7dd8-44ea-914d-d43bbfe894f1.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/Skywork_Skywork-Reward-Llama-3.1-8B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7314
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6989
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.425
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9333
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9616
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.741
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Skywork/Skywork-Reward-Llama-3.1-8B/b9ddd960-f6f7-4962-8297-88ec7fbbbd1f.json b/data/reward-bench/Skywork/Skywork-Reward-Llama-3.1-8B/b9ddd960-f6f7-4962-8297-88ec7fbbbd1f.json
index 6bf4c02d1..03903b4ec 100644
--- a/data/reward-bench/Skywork/Skywork-Reward-Llama-3.1-8B/b9ddd960-f6f7-4962-8297-88ec7fbbbd1f.json
+++ b/data/reward-bench/Skywork/Skywork-Reward-Llama-3.1-8B/b9ddd960-f6f7-4962-8297-88ec7fbbbd1f.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Skywork_Skywork-Reward-Llama-3.1-8B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9252
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9581
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8728
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9081
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.962
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Skywork/Skywork-Reward-V2-Llama-3.1-8B/25a4520b-c780-45fc-a00f-36db1776c6a8.json b/data/reward-bench/Skywork/Skywork-Reward-V2-Llama-3.1-8B/25a4520b-c780-45fc-a00f-36db1776c6a8.json
index 7c195cad3..b19a61534 100644
--- a/data/reward-bench/Skywork/Skywork-Reward-V2-Llama-3.1-8B/25a4520b-c780-45fc-a00f-36db1776c6a8.json
+++ b/data/reward-bench/Skywork/Skywork-Reward-V2-Llama-3.1-8B/25a4520b-c780-45fc-a00f-36db1776c6a8.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/Skywork_Skywork-Reward-V2-Llama-3.1-8B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8413
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8463
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6625
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.776
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9667
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9838
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.8124
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Skywork/Skywork-Reward-V2-Llama-3.2-1B/96d7e5c1-2f43-4f09-9702-0af090afa141.json b/data/reward-bench/Skywork/Skywork-Reward-V2-Llama-3.2-1B/96d7e5c1-2f43-4f09-9702-0af090afa141.json
index d9d0560be..2ff90cff2 100644
--- a/data/reward-bench/Skywork/Skywork-Reward-V2-Llama-3.2-1B/96d7e5c1-2f43-4f09-9702-0af090afa141.json
+++ b/data/reward-bench/Skywork/Skywork-Reward-V2-Llama-3.2-1B/96d7e5c1-2f43-4f09-9702-0af090afa141.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/Skywork_Skywork-Reward-V2-Llama-3.2-1B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6438
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6084
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4562
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6011
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8733
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8929
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4306
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Skywork/Skywork-Reward-V2-Llama-3.2-3B/5a47f8bd-401a-4b6b-91b0-9593b36e5996.json b/data/reward-bench/Skywork/Skywork-Reward-V2-Llama-3.2-3B/5a47f8bd-401a-4b6b-91b0-9593b36e5996.json
index 3d9cbc212..9f8069f50 100644
--- a/data/reward-bench/Skywork/Skywork-Reward-V2-Llama-3.2-3B/5a47f8bd-401a-4b6b-91b0-9593b36e5996.json
+++ b/data/reward-bench/Skywork/Skywork-Reward-V2-Llama-3.2-3B/5a47f8bd-401a-4b6b-91b0-9593b36e5996.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/Skywork_Skywork-Reward-V2-Llama-3.2-3B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7466
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7621
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4562
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.694
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9311
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9596
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6768
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Skywork/Skywork-Reward-V2-Qwen3-0.6B/c27e98d4-f5ea-48f9-babc-3ccda2d21d2a.json b/data/reward-bench/Skywork/Skywork-Reward-V2-Qwen3-0.6B/c27e98d4-f5ea-48f9-babc-3ccda2d21d2a.json
index 3d71cef8d..44ea9887d 100644
--- a/data/reward-bench/Skywork/Skywork-Reward-V2-Qwen3-0.6B/c27e98d4-f5ea-48f9-babc-3ccda2d21d2a.json
+++ b/data/reward-bench/Skywork/Skywork-Reward-V2-Qwen3-0.6B/c27e98d4-f5ea-48f9-babc-3ccda2d21d2a.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/Skywork_Skywork-Reward-V2-Qwen3-0.6B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6125
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.58
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7158
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8444
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7949
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.3397
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Skywork/Skywork-Reward-V2-Qwen3-1.7B/060bf847-e7b5-4e30-934f-5306d01c499a.json b/data/reward-bench/Skywork/Skywork-Reward-V2-Qwen3-1.7B/060bf847-e7b5-4e30-934f-5306d01c499a.json
index 708a6390b..f670ad051 100644
--- a/data/reward-bench/Skywork/Skywork-Reward-V2-Qwen3-1.7B/060bf847-e7b5-4e30-934f-5306d01c499a.json
+++ b/data/reward-bench/Skywork/Skywork-Reward-V2-Qwen3-1.7B/060bf847-e7b5-4e30-934f-5306d01c499a.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/Skywork_Skywork-Reward-V2-Qwen3-1.7B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6818
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6568
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4437
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7268
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8911
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8848
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4872
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Skywork/Skywork-Reward-V2-Qwen3-4B/e648e6c2-18bb-49d7-b08f-47ce41a67d4f.json b/data/reward-bench/Skywork/Skywork-Reward-V2-Qwen3-4B/e648e6c2-18bb-49d7-b08f-47ce41a67d4f.json
index 47d640d45..6f6900c68 100644
--- a/data/reward-bench/Skywork/Skywork-Reward-V2-Qwen3-4B/e648e6c2-18bb-49d7-b08f-47ce41a67d4f.json
+++ b/data/reward-bench/Skywork/Skywork-Reward-V2-Qwen3-4B/e648e6c2-18bb-49d7-b08f-47ce41a67d4f.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/Skywork_Skywork-Reward-V2-Qwen3-4B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7551
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7737
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4625
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7322
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9222
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9657
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6743
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Skywork/Skywork-Reward-V2-Qwen3-8B/537e92cb-25db-47f5-916a-6f666e14639a.json b/data/reward-bench/Skywork/Skywork-Reward-V2-Qwen3-8B/537e92cb-25db-47f5-916a-6f666e14639a.json
index 769d2cb8b..1c01babb8 100644
--- a/data/reward-bench/Skywork/Skywork-Reward-V2-Qwen3-8B/537e92cb-25db-47f5-916a-6f666e14639a.json
+++ b/data/reward-bench/Skywork/Skywork-Reward-V2-Qwen3-8B/537e92cb-25db-47f5-916a-6f666e14639a.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/Skywork_Skywork-Reward-V2-Qwen3-8B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7837
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7989
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7705
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.94
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9636
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.7294
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Skywork/Skywork-VL-Reward-7B/e59ca33f-c6ce-44d4-9cb4-2fd65608313b.json b/data/reward-bench/Skywork/Skywork-VL-Reward-7B/e59ca33f-c6ce-44d4-9cb4-2fd65608313b.json
index cce15d82f..47757e3b6 100644
--- a/data/reward-bench/Skywork/Skywork-VL-Reward-7B/e59ca33f-c6ce-44d4-9cb4-2fd65608313b.json
+++ b/data/reward-bench/Skywork/Skywork-VL-Reward-7B/e59ca33f-c6ce-44d4-9cb4-2fd65608313b.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Skywork_Skywork-VL-Reward-7B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9007
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8994
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.875
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9108
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9176
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/Skywork/Skywork-VL-Reward-7B/fc99848b-82c7-459e-8327-1867a332ff28.json b/data/reward-bench/Skywork/Skywork-VL-Reward-7B/fc99848b-82c7-459e-8327-1867a332ff28.json
index acad04a74..adb50e622 100644
--- a/data/reward-bench/Skywork/Skywork-VL-Reward-7B/fc99848b-82c7-459e-8327-1867a332ff28.json
+++ b/data/reward-bench/Skywork/Skywork-VL-Reward-7B/fc99848b-82c7-459e-8327-1867a332ff28.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/Skywork_Skywork-VL-Reward-7B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6885
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6063
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.35
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6339
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8911
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8909
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.7586
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/SultanR/SmolTulu-1.7b-RM/357f4f03-9542-495f-b575-4274111bbe1f.json b/data/reward-bench/SultanR/SmolTulu-1.7b-RM/357f4f03-9542-495f-b575-4274111bbe1f.json
index 8e503b342..16bfc7b82 100644
--- a/data/reward-bench/SultanR/SmolTulu-1.7b-RM/357f4f03-9542-495f-b575-4274111bbe1f.json
+++ b/data/reward-bench/SultanR/SmolTulu-1.7b-RM/357f4f03-9542-495f-b575-4274111bbe1f.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/SultanR_SmolTulu-1.7b-RM/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5094
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.743
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4408
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5716
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.2821
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ZiyiYe/Con-J-Qwen2-7B/d78c42d6-fc0d-4719-bbb6-7a53dbb0d017.json b/data/reward-bench/ZiyiYe/Con-J-Qwen2-7B/d78c42d6-fc0d-4719-bbb6-7a53dbb0d017.json
index f06598ac7..5ae0638d6 100644
--- a/data/reward-bench/ZiyiYe/Con-J-Qwen2-7B/d78c42d6-fc0d-4719-bbb6-7a53dbb0d017.json
+++ b/data/reward-bench/ZiyiYe/Con-J-Qwen2-7B/d78c42d6-fc0d-4719-bbb6-7a53dbb0d017.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ZiyiYe_Con-J-Qwen2-7B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8712
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.919
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8026
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8824
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.8808
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ai2/llama-2-chat-7b-nectar-3.8m.json/c94ddbe5-2bc0-4a33-b06b-10671fb22b70.json b/data/reward-bench/ai2/llama-2-chat-7b-nectar-3.8m.json/c94ddbe5-2bc0-4a33-b06b-10671fb22b70.json
index 71e6f10bb..400642b9b 100644
--- a/data/reward-bench/ai2/llama-2-chat-7b-nectar-3.8m.json/c94ddbe5-2bc0-4a33-b06b-10671fb22b70.json
+++ b/data/reward-bench/ai2/llama-2-chat-7b-nectar-3.8m.json/c94ddbe5-2bc0-4a33-b06b-10671fb22b70.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ai2_llama-2-chat-7b-nectar-3.8m.json/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5843
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8631
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.2654
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,7 +83,12 @@
       },
       "score_details": {
         "score": 0.6243
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ai2/llama-2-chat-nectar-180k.json/cc2ac405-1710-46fa-aeba-dd86797c666c.json b/data/reward-bench/ai2/llama-2-chat-nectar-180k.json/cc2ac405-1710-46fa-aeba-dd86797c666c.json
index 02fb796d2..26ba58fae 100644
--- a/data/reward-bench/ai2/llama-2-chat-nectar-180k.json/cc2ac405-1710-46fa-aeba-dd86797c666c.json
+++ b/data/reward-bench/ai2/llama-2-chat-nectar-180k.json/cc2ac405-1710-46fa-aeba-dd86797c666c.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ai2_llama-2-chat-nectar-180k.json/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5235
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8827
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.2851
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,7 +83,12 @@
       },
       "score_details": {
         "score": 0.4027
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ai2/llama-2-chat-ultrafeedback-60k.jsonl/49fcb3e2-2883-4c3d-b519-d511c6b10162.json b/data/reward-bench/ai2/llama-2-chat-ultrafeedback-60k.jsonl/49fcb3e2-2883-4c3d-b519-d511c6b10162.json
index 73085ecb0..4b539edf5 100644
--- a/data/reward-bench/ai2/llama-2-chat-ultrafeedback-60k.jsonl/49fcb3e2-2883-4c3d-b519-d511c6b10162.json
+++ b/data/reward-bench/ai2/llama-2-chat-ultrafeedback-60k.jsonl/49fcb3e2-2883-4c3d-b519-d511c6b10162.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ai2_llama-2-chat-ultrafeedback-60k.jsonl/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.644
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9441
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4539
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,7 +83,12 @@
       },
       "score_details": {
         "score": 0.5338
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../0ba5ce6c-f311-4b02-a67a-d49539119a8e.json b/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../0ba5ce6c-f311-4b02-a67a-d49539119a8e.json
index 60e788067..277116c3d 100644
--- a/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../0ba5ce6c-f311-4b02-a67a-d49539119a8e.json
+++ b/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../0ba5ce6c-f311-4b02-a67a-d49539119a8e.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ai2_tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7058
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9525
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3947
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,7 +83,12 @@
       },
       "score_details": {
         "score": 0.7703
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../49029c9e-a831-4219-8e26-df20862ad3e1.json b/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../49029c9e-a831-4219-8e26-df20862ad3e1.json
index 966dbbe7a..dfc9008b5 100644
--- a/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../49029c9e-a831-4219-8e26-df20862ad3e1.json
+++ b/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../49029c9e-a831-4219-8e26-df20862ad3e1.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ai2_tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7004
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9413
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3882
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,7 +83,12 @@
       },
       "score_details": {
         "score": 0.7716
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../6dedd117-eab0-4c31-b50b-4890099d9904.json b/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../6dedd117-eab0-4c31-b50b-4890099d9904.json
index 20188aabb..974cd9980 100644
--- a/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../6dedd117-eab0-4c31-b50b-4890099d9904.json
+++ b/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../6dedd117-eab0-4c31-b50b-4890099d9904.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ai2_tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6905
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9441
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3596
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,7 +83,12 @@
       },
       "score_details": {
         "score": 0.7676
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../71c20c06-efb8-428e-9e9d-e4fedf11041a.json b/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../71c20c06-efb8-428e-9e9d-e4fedf11041a.json
index f233bfae7..fb2652a50 100644
--- a/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../71c20c06-efb8-428e-9e9d-e4fedf11041a.json
+++ b/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../71c20c06-efb8-428e-9e9d-e4fedf11041a.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ai2_tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6945
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9385
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3706
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,7 +83,12 @@
       },
       "score_details": {
         "score": 0.7743
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../862f3d57-8f5f-4372-b6fb-876fb35efba4.json b/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../862f3d57-8f5f-4372-b6fb-876fb35efba4.json
index 8a33df5ad..a8d6993af 100644
--- a/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../862f3d57-8f5f-4372-b6fb-876fb35efba4.json
+++ b/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../862f3d57-8f5f-4372-b6fb-876fb35efba4.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ai2_tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6808
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9302
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3596
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,7 +83,12 @@
       },
       "score_details": {
         "score": 0.7527
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../93ea2bfa-e058-42d5-afac-0d3fc50fce91.json b/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../93ea2bfa-e058-42d5-afac-0d3fc50fce91.json
index 0717d8e99..4d645ea3b 100644
--- a/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../93ea2bfa-e058-42d5-afac-0d3fc50fce91.json
+++ b/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../93ea2bfa-e058-42d5-afac-0d3fc50fce91.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ai2_tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6895
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9385
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3706
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,7 +83,12 @@
       },
       "score_details": {
         "score": 0.7595
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../c1331fa1-7793-4526-b24b-02261bb4437f.json b/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../c1331fa1-7793-4526-b24b-02261bb4437f.json
index fb237ec91..f0096c309 100644
--- a/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../c1331fa1-7793-4526-b24b-02261bb4437f.json
+++ b/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../c1331fa1-7793-4526-b24b-02261bb4437f.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ai2_tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7019
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9497
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.375
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,7 +83,12 @@
       },
       "score_details": {
         "score": 0.7811
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../c3cab72a-47b3-47ec-bb2d-986903ab8c26.json b/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../c3cab72a-47b3-47ec-bb2d-986903ab8c26.json
index 6d1bc4865..7ccfca2e6 100644
--- a/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../c3cab72a-47b3-47ec-bb2d-986903ab8c26.json
+++ b/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../c3cab72a-47b3-47ec-bb2d-986903ab8c26.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ai2_tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7008
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9385
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3882
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,7 +83,12 @@
       },
       "score_details": {
         "score": 0.7757
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../cd0452a7-0370-4024-a51f-b3deff290db9.json b/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../cd0452a7-0370-4024-a51f-b3deff290db9.json
index f3d24d1cb..dddd173cb 100644
--- a/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../cd0452a7-0370-4024-a51f-b3deff290db9.json
+++ b/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../cd0452a7-0370-4024-a51f-b3deff290db9.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ai2_tulu-2-7b-rm-v0-nectar-binarized-3.8m-check.../1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6924
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9441
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3575
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,7 +83,12 @@
       },
       "score_details": {
         "score": 0.7757
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-700k.json/6fd85045-d600-451f-8d27-da637add4081.json b/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-700k.json/6fd85045-d600-451f-8d27-da637add4081.json
index c9f57ea2b..fbf11359b 100644
--- a/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-700k.json/6fd85045-d600-451f-8d27-da637add4081.json
+++ b/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized-700k.json/6fd85045-d600-451f-8d27-da637add4081.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ai2_tulu-2-7b-rm-v0-nectar-binarized-700k.json/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7127
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9358
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4079
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,7 +83,12 @@
       },
       "score_details": {
         "score": 0.7946
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized.json/a15ca8c3-fd90-4ef9-80c5-40eeac60d785.json b/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized.json/a15ca8c3-fd90-4ef9-80c5-40eeac60d785.json
index 7af294ed7..3770ce48e 100644
--- a/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized.json/a15ca8c3-fd90-4ef9-80c5-40eeac60d785.json
+++ b/data/reward-bench/ai2/tulu-2-7b-rm-v0-nectar-binarized.json/a15ca8c3-fd90-4ef9-80c5-40eeac60d785.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ai2_tulu-2-7b-rm-v0-nectar-binarized.json/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6756
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9134
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3904
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,7 +83,12 @@
       },
       "score_details": {
         "score": 0.723
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/ai2/tulu-2-7b-rm-v0.json/5f43832f-14fa-49e1-a851-949163aec826.json b/data/reward-bench/ai2/tulu-2-7b-rm-v0.json/5f43832f-14fa-49e1-a851-949163aec826.json
index d81909091..ffe63e3e4 100644
--- a/data/reward-bench/ai2/tulu-2-7b-rm-v0.json/5f43832f-14fa-49e1-a851-949163aec826.json
+++ b/data/reward-bench/ai2/tulu-2-7b-rm-v0.json/5f43832f-14fa-49e1-a851-949163aec826.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/ai2_tulu-2-7b-rm-v0.json/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6655
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.933
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4539
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,7 +83,12 @@
       },
       "score_details": {
         "score": 0.6095
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/Llama-3.1-70B-Instruct-RM-RB2/1f8869e7-e434-469e-906d-d34621582cba.json b/data/reward-bench/allenai/Llama-3.1-70B-Instruct-RM-RB2/1f8869e7-e434-469e-906d-d34621582cba.json
index 83967095d..fef53f2e4 100644
--- a/data/reward-bench/allenai/Llama-3.1-70B-Instruct-RM-RB2/1f8869e7-e434-469e-906d-d34621582cba.json
+++ b/data/reward-bench/allenai/Llama-3.1-70B-Instruct-RM-RB2/1f8869e7-e434-469e-906d-d34621582cba.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_Llama-3.1-70B-Instruct-RM-RB2/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7606
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8126
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4188
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6995
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8844
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8646
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.8835
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/Llama-3.1-70B-Instruct-RM-RB2/8f9d05db-9bb0-4998-bc75-96dbfa695548.json b/data/reward-bench/allenai/Llama-3.1-70B-Instruct-RM-RB2/8f9d05db-9bb0-4998-bc75-96dbfa695548.json
index ba3b8f2bf..419aa0a24 100644
--- a/data/reward-bench/allenai/Llama-3.1-70B-Instruct-RM-RB2/8f9d05db-9bb0-4998-bc75-96dbfa695548.json
+++ b/data/reward-bench/allenai/Llama-3.1-70B-Instruct-RM-RB2/8f9d05db-9bb0-4998-bc75-96dbfa695548.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/allenai_Llama-3.1-70B-Instruct-RM-RB2/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9021
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9665
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8355
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9095
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8969
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.0
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/Llama-3.1-8B-Base-RM-RB2/2681e475-da0a-48a9-ab68-e0bf59240f90.json b/data/reward-bench/allenai/Llama-3.1-8B-Base-RM-RB2/2681e475-da0a-48a9-ab68-e0bf59240f90.json
index d5327ebdc..77a854ced 100644
--- a/data/reward-bench/allenai/Llama-3.1-8B-Base-RM-RB2/2681e475-da0a-48a9-ab68-e0bf59240f90.json
+++ b/data/reward-bench/allenai/Llama-3.1-8B-Base-RM-RB2/2681e475-da0a-48a9-ab68-e0bf59240f90.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_Llama-3.1-8B-Base-RM-RB2/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.649
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.72
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3625
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.612
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8267
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8323
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5406
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/Llama-3.1-8B-Base-RM-RB2/e2986d78-100d-417a-9f38-9a570a335d95.json b/data/reward-bench/allenai/Llama-3.1-8B-Base-RM-RB2/e2986d78-100d-417a-9f38-9a570a335d95.json
index b7c605956..a01839a2f 100644
--- a/data/reward-bench/allenai/Llama-3.1-8B-Base-RM-RB2/e2986d78-100d-417a-9f38-9a570a335d95.json
+++ b/data/reward-bench/allenai/Llama-3.1-8B-Base-RM-RB2/e2986d78-100d-417a-9f38-9a570a335d95.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/allenai_Llama-3.1-8B-Base-RM-RB2/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8463
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.933
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7785
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8851
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7886
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.0
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/Llama-3.1-8B-Instruct-RM-RB2/1bc5cd51-5a3a-46ea-bc78-56f9b3081f69.json b/data/reward-bench/allenai/Llama-3.1-8B-Instruct-RM-RB2/1bc5cd51-5a3a-46ea-bc78-56f9b3081f69.json
index 50aa7aae8..7175068fd 100644
--- a/data/reward-bench/allenai/Llama-3.1-8B-Instruct-RM-RB2/1bc5cd51-5a3a-46ea-bc78-56f9b3081f69.json
+++ b/data/reward-bench/allenai/Llama-3.1-8B-Instruct-RM-RB2/1bc5cd51-5a3a-46ea-bc78-56f9b3081f69.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/allenai_Llama-3.1-8B-Instruct-RM-RB2/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8885
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9581
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8158
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8932
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.887
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.0
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/Llama-3.1-8B-Instruct-RM-RB2/1d1127ee-7a0e-4915-b8bf-0b22f8ba338b.json b/data/reward-bench/allenai/Llama-3.1-8B-Instruct-RM-RB2/1d1127ee-7a0e-4915-b8bf-0b22f8ba338b.json
index f7e4dfc34..095adf95a 100644
--- a/data/reward-bench/allenai/Llama-3.1-8B-Instruct-RM-RB2/1d1127ee-7a0e-4915-b8bf-0b22f8ba338b.json
+++ b/data/reward-bench/allenai/Llama-3.1-8B-Instruct-RM-RB2/1d1127ee-7a0e-4915-b8bf-0b22f8ba338b.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_Llama-3.1-8B-Instruct-RM-RB2/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7285
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7432
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4437
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6175
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8956
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9071
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.7638
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/Llama-3.1-Tulu-3-70B-SFT-RM-RB2/4bb55ff5-5adf-407f-a9d6-910c6c9d2770.json b/data/reward-bench/allenai/Llama-3.1-Tulu-3-70B-SFT-RM-RB2/4bb55ff5-5adf-407f-a9d6-910c6c9d2770.json
index de7dc82bc..f3bf51149 100644
--- a/data/reward-bench/allenai/Llama-3.1-Tulu-3-70B-SFT-RM-RB2/4bb55ff5-5adf-407f-a9d6-910c6c9d2770.json
+++ b/data/reward-bench/allenai/Llama-3.1-Tulu-3-70B-SFT-RM-RB2/4bb55ff5-5adf-407f-a9d6-910c6c9d2770.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_Llama-3.1-Tulu-3-70B-SFT-RM-RB2/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.722
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8084
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3688
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6776
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8689
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7778
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.8308
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/Llama-3.1-Tulu-3-70B-SFT-RM-RB2/daebee0b-3856-4270-94c6-c14bd84f5cf5.json b/data/reward-bench/allenai/Llama-3.1-Tulu-3-70B-SFT-RM-RB2/daebee0b-3856-4270-94c6-c14bd84f5cf5.json
index 451b6f9b6..d0492cb5e 100644
--- a/data/reward-bench/allenai/Llama-3.1-Tulu-3-70B-SFT-RM-RB2/daebee0b-3856-4270-94c6-c14bd84f5cf5.json
+++ b/data/reward-bench/allenai/Llama-3.1-Tulu-3-70B-SFT-RM-RB2/daebee0b-3856-4270-94c6-c14bd84f5cf5.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/allenai_Llama-3.1-Tulu-3-70B-SFT-RM-RB2/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8892
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9693
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8268
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9027
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8583
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.0
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-DPO-RM-RB2/1be99417-352e-4a94-8108-b43123553667.json b/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-DPO-RM-RB2/1be99417-352e-4a94-8108-b43123553667.json
index 5788822b2..042aac2cb 100644
--- a/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-DPO-RM-RB2/1be99417-352e-4a94-8108-b43123553667.json
+++ b/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-DPO-RM-RB2/1be99417-352e-4a94-8108-b43123553667.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_Llama-3.1-Tulu-3-8B-DPO-RM-RB2/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.687
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7516
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3875
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.86
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8545
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6397
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-DPO-RM-RB2/8d3fbc68-2ee7-4989-a40c-f4a45e579b5c.json b/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-DPO-RM-RB2/8d3fbc68-2ee7-4989-a40c-f4a45e579b5c.json
index 748ceff12..8adafbc18 100644
--- a/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-DPO-RM-RB2/8d3fbc68-2ee7-4989-a40c-f4a45e579b5c.json
+++ b/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-DPO-RM-RB2/8d3fbc68-2ee7-4989-a40c-f4a45e579b5c.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/allenai_Llama-3.1-Tulu-3-8B-DPO-RM-RB2/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8431
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9553
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.761
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8662
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7898
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.0
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-RL-RM-RB2/9533891f-c2f7-4e82-9f39-131768dbc28a.json b/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-RL-RM-RB2/9533891f-c2f7-4e82-9f39-131768dbc28a.json
index 7db85157a..98a6ce817 100644
--- a/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-RL-RM-RB2/9533891f-c2f7-4e82-9f39-131768dbc28a.json
+++ b/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-RL-RM-RB2/9533891f-c2f7-4e82-9f39-131768dbc28a.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/allenai_Llama-3.1-Tulu-3-8B-RL-RM-RB2/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8369
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9469
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7588
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8703
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7715
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.0
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-RL-RM-RB2/b8a47660-f0a5-4136-a743-979863c53e3a.json b/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-RL-RM-RB2/b8a47660-f0a5-4136-a743-979863c53e3a.json
index 7d48f70bb..d3b513f5d 100644
--- a/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-RL-RM-RB2/b8a47660-f0a5-4136-a743-979863c53e3a.json
+++ b/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-RL-RM-RB2/b8a47660-f0a5-4136-a743-979863c53e3a.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_Llama-3.1-Tulu-3-8B-RL-RM-RB2/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6871
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7642
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6175
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8644
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8485
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6281
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-RM/2673bea2-42eb-42a5-9dc2-13d43341c9b2.json b/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-RM/2673bea2-42eb-42a5-9dc2-13d43341c9b2.json
index 14e9efed4..e3e043728 100644
--- a/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-RM/2673bea2-42eb-42a5-9dc2-13d43341c9b2.json
+++ b/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-RM/2673bea2-42eb-42a5-9dc2-13d43341c9b2.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_Llama-3.1-Tulu-3-8B-RM/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.59
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7453
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3469
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6448
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7422
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5364
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5243
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-SFT-RM-RB2/6f5555c2-588a-48d1-811c-be53634bbdef.json b/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-SFT-RM-RB2/6f5555c2-588a-48d1-811c-be53634bbdef.json
index 6f121b539..44e1a6e59 100644
--- a/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-SFT-RM-RB2/6f5555c2-588a-48d1-811c-be53634bbdef.json
+++ b/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-SFT-RM-RB2/6f5555c2-588a-48d1-811c-be53634bbdef.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/allenai_Llama-3.1-Tulu-3-8B-SFT-RM-RB2/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8551
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9497
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7917
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8784
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8005
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.0
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-SFT-RM-RB2/9c96fa7b-52e8-4aed-9fdd-f389091d5e6f.json b/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-SFT-RM-RB2/9c96fa7b-52e8-4aed-9fdd-f389091d5e6f.json
index d0adf9b8d..674d59e88 100644
--- a/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-SFT-RM-RB2/9c96fa7b-52e8-4aed-9fdd-f389091d5e6f.json
+++ b/data/reward-bench/allenai/Llama-3.1-Tulu-3-8B-SFT-RM-RB2/9c96fa7b-52e8-4aed-9fdd-f389091d5e6f.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_Llama-3.1-Tulu-3-8B-SFT-RM-RB2/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6821
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7326
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3875
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5792
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8978
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8889
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6063
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/OLMo-7B-Instruct/0519d9fb-f220-40ab-8257-f20ed98a8b47.json b/data/reward-bench/allenai/OLMo-7B-Instruct/0519d9fb-f220-40ab-8257-f20ed98a8b47.json
index f511228aa..f8ff8a104 100644
--- a/data/reward-bench/allenai/OLMo-7B-Instruct/0519d9fb-f220-40ab-8257-f20ed98a8b47.json
+++ b/data/reward-bench/allenai/OLMo-7B-Instruct/0519d9fb-f220-40ab-8257-f20ed98a8b47.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/allenai_OLMo-7B-Instruct/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6727
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8966
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5066
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6486
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7168
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5173
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/llama-3-tulu-2-70b-uf-mean-rm/ece70375-447f-41e8-aa03-8f4b26abea73.json b/data/reward-bench/allenai/llama-3-tulu-2-70b-uf-mean-rm/ece70375-447f-41e8-aa03-8f4b26abea73.json
index 2571fe4e1..5110dfc2e 100644
--- a/data/reward-bench/allenai/llama-3-tulu-2-70b-uf-mean-rm/ece70375-447f-41e8-aa03-8f4b26abea73.json
+++ b/data/reward-bench/allenai/llama-3-tulu-2-70b-uf-mean-rm/ece70375-447f-41e8-aa03-8f4b26abea73.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/allenai_llama-3-tulu-2-70b-uf-mean-rm/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7019
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8631
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5614
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6095
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8268
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5957
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/llama-3-tulu-2-8b-uf-mean-rm/7bbaffdd-f822-48cf-a0f2-e66b16db678d.json b/data/reward-bench/allenai/llama-3-tulu-2-8b-uf-mean-rm/7bbaffdd-f822-48cf-a0f2-e66b16db678d.json
index 607b1292d..e1917bdfd 100644
--- a/data/reward-bench/allenai/llama-3-tulu-2-8b-uf-mean-rm/7bbaffdd-f822-48cf-a0f2-e66b16db678d.json
+++ b/data/reward-bench/allenai/llama-3-tulu-2-8b-uf-mean-rm/7bbaffdd-f822-48cf-a0f2-e66b16db678d.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/allenai_llama-3-tulu-2-8b-uf-mean-rm/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7342
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9525
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5921
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6162
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8212
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6434
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/llama-3-tulu-2-dpo-70b/27c5c441-64ce-41dd-8384-f84c8f6ccc14.json b/data/reward-bench/allenai/llama-3-tulu-2-dpo-70b/27c5c441-64ce-41dd-8384-f84c8f6ccc14.json
index 38ddc2375..bef93ec9e 100644
--- a/data/reward-bench/allenai/llama-3-tulu-2-dpo-70b/27c5c441-64ce-41dd-8384-f84c8f6ccc14.json
+++ b/data/reward-bench/allenai/llama-3-tulu-2-dpo-70b/27c5c441-64ce-41dd-8384-f84c8f6ccc14.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/allenai_llama-3-tulu-2-dpo-70b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7496
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9637
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5746
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7486
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.802
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5687
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/llama-3-tulu-2-dpo-8b/38a14e6a-2094-4e0b-be22-45181ede2a63.json b/data/reward-bench/allenai/llama-3-tulu-2-dpo-8b/38a14e6a-2094-4e0b-be22-45181ede2a63.json
index b4a96b007..a54ed9cc6 100644
--- a/data/reward-bench/allenai/llama-3-tulu-2-dpo-8b/38a14e6a-2094-4e0b-be22-45181ede2a63.json
+++ b/data/reward-bench/allenai/llama-3-tulu-2-dpo-8b/38a14e6a-2094-4e0b-be22-45181ede2a63.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/allenai_llama-3-tulu-2-dpo-8b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7275
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9525
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5351
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6649
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8663
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5097
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739590997/cee37c2c-2766-47b7-9192-a141e5d22f2d.json b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739590997/cee37c2c-2766-47b7-9192-a141e5d22f2d.json
index 5511a688f..264f422e1 100644
--- a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739590997/cee37c2c-2766-47b7-9192-a141e5d22f2d.json
+++ b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739590997/cee37c2c-2766-47b7-9192-a141e5d22f2d.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-reward_modeling__1__1739590997/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6004
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7032
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.375
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.623
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7867
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.598
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5165
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739871066/d1d69392-8717-462d-9ce0-c7ddf5faf97d.json b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739871066/d1d69392-8717-462d-9ce0-c7ddf5faf97d.json
index 4d1d727af..1d7e43d9e 100644
--- a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739871066/d1d69392-8717-462d-9ce0-c7ddf5faf97d.json
+++ b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739871066/d1d69392-8717-462d-9ce0-c7ddf5faf97d.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-reward_modeling__1__1739871066/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6012
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6989
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.425
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7978
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.604
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4527
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739925892/72071bb1-57c0-4727-8100-ba24d8da10f5.json b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739925892/72071bb1-57c0-4727-8100-ba24d8da10f5.json
index f0d0e8725..ccb6f9252 100644
--- a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739925892/72071bb1-57c0-4727-8100-ba24d8da10f5.json
+++ b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739925892/72071bb1-57c0-4727-8100-ba24d8da10f5.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-reward_modeling__1__1739925892/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6345
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7432
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3563
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.623
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8111
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7131
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5606
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739943850/7626c158-edaf-48f3-9ac3-1188be0c6032.json b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739943850/7626c158-edaf-48f3-9ac3-1188be0c6032.json
index e113a319b..8e0cbdf9e 100644
--- a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739943850/7626c158-edaf-48f3-9ac3-1188be0c6032.json
+++ b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739943850/7626c158-edaf-48f3-9ac3-1188be0c6032.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-reward_modeling__1__1739943850/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.4978
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5726
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3125
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5191
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6489
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6222
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.3114
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739943881/c37be7a8-dc10-4fea-962b-202986a4581e.json b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739943881/c37be7a8-dc10-4fea-962b-202986a4581e.json
index d1d507707..b0fd4a9be 100644
--- a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739943881/c37be7a8-dc10-4fea-962b-202986a4581e.json
+++ b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739943881/c37be7a8-dc10-4fea-962b-202986a4581e.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-reward_modeling__1__1739943881/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5998
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7032
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3187
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5792
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8222
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6727
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5025
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739943972/223dc616-b20f-4065-91a7-3c35bfd11c94.json b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739943972/223dc616-b20f-4065-91a7-3c35bfd11c94.json
index 6efc37a05..c0ad13c6c 100644
--- a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739943972/223dc616-b20f-4065-91a7-3c35bfd11c94.json
+++ b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739943972/223dc616-b20f-4065-91a7-3c35bfd11c94.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-reward_modeling__1__1739943972/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5289
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6168
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.375
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5738
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6844
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5657
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.3577
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739957701/4236b0a9-9d1e-41f6-8364-a7e8ebf51635.json b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739957701/4236b0a9-9d1e-41f6-8364-a7e8ebf51635.json
index 15342b481..6eb775d20 100644
--- a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739957701/4236b0a9-9d1e-41f6-8364-a7e8ebf51635.json
+++ b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739957701/4236b0a9-9d1e-41f6-8364-a7e8ebf51635.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-reward_modeling__1__1739957701/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6194
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6779
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3563
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6011
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8022
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.697
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5822
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739971507/c8030a87-0cdf-4918-b0d5-d1fb0e284656.json b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739971507/c8030a87-0cdf-4918-b0d5-d1fb0e284656.json
index db24dc879..c409d89eb 100644
--- a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739971507/c8030a87-0cdf-4918-b0d5-d1fb0e284656.json
+++ b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739971507/c8030a87-0cdf-4918-b0d5-d1fb0e284656.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-reward_modeling__1__1739971507/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5717
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.68
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.375
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6066
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7667
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5475
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4545
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739971529/e6ecc1eb-7ff1-46aa-bf03-37bad1b391b7.json b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739971529/e6ecc1eb-7ff1-46aa-bf03-37bad1b391b7.json
index 76286022b..c8518a2e2 100644
--- a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739971529/e6ecc1eb-7ff1-46aa-bf03-37bad1b391b7.json
+++ b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739971529/e6ecc1eb-7ff1-46aa-bf03-37bad1b391b7.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-reward_modeling__1__1739971529/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5564
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6568
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3563
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5956
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7533
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5737
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4027
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739998765/64872b1a-1eae-4171-95ec-a80c782b69f0.json b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739998765/64872b1a-1eae-4171-95ec-a80c782b69f0.json
index 77dd9be0e..b41f9844e 100644
--- a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739998765/64872b1a-1eae-4171-95ec-a80c782b69f0.json
+++ b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1739998765/64872b1a-1eae-4171-95ec-a80c782b69f0.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-reward_modeling__1__1739998765/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6008
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7095
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4125
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6066
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8022
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5859
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4883
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1740005072/37484401-c7fe-469d-889a-e70f7cadbf82.json b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1740005072/37484401-c7fe-469d-889a-e70f7cadbf82.json
index c78258032..04e0eceb6 100644
--- a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1740005072/37484401-c7fe-469d-889a-e70f7cadbf82.json
+++ b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1740005072/37484401-c7fe-469d-889a-e70f7cadbf82.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-reward_modeling__1__1740005072/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6097
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7137
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3937
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6339
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7778
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6343
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5047
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1740129284/8cf36288-3add-4fcd-a012-0df9eae2a059.json b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1740129284/8cf36288-3add-4fcd-a012-0df9eae2a059.json
index 660d601e2..a39194f60 100644
--- a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1740129284/8cf36288-3add-4fcd-a012-0df9eae2a059.json
+++ b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1740129284/8cf36288-3add-4fcd-a012-0df9eae2a059.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-reward_modeling__1__1740129284/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6129
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7116
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4437
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6448
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8022
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6101
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4652
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1741286813/f2c8f979-c331-4b9b-b0a7-5efa82c17d3b.json b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1741286813/f2c8f979-c331-4b9b-b0a7-5efa82c17d3b.json
index f109fdac1..6657f9ea6 100644
--- a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1741286813/f2c8f979-c331-4b9b-b0a7-5efa82c17d3b.json
+++ b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1741286813/f2c8f979-c331-4b9b-b0a7-5efa82c17d3b.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-reward_modeling__1__1741286813/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6557
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6295
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4188
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.612
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9111
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8263
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5365
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1741287363/de409ce8-fb68-4113-8879-23712769cbde.json b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1741287363/de409ce8-fb68-4113-8879-23712769cbde.json
index 2320f7feb..56ed0daae 100644
--- a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1741287363/de409ce8-fb68-4113-8879-23712769cbde.json
+++ b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1741287363/de409ce8-fb68-4113-8879-23712769cbde.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-reward_modeling__1__1741287363/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6672
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6295
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.375
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6066
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.88
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9374
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5748
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1741292911/264f20d7-1574-448c-8917-eb3f20810819.json b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1741292911/264f20d7-1574-448c-8917-eb3f20810819.json
index 68df2fbb6..d217f0d3d 100644
--- a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1741292911/264f20d7-1574-448c-8917-eb3f20810819.json
+++ b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1741292911/264f20d7-1574-448c-8917-eb3f20810819.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-reward_modeling__1__1741292911/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6607
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6589
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6066
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9089
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8869
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5028
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1742338142/0ebaec42-9190-4326-95dd-5ecb48bf1a72.json b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1742338142/0ebaec42-9190-4326-95dd-5ecb48bf1a72.json
index a29c40de9..4897a8825 100644
--- a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1742338142/0ebaec42-9190-4326-95dd-5ecb48bf1a72.json
+++ b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1742338142/0ebaec42-9190-4326-95dd-5ecb48bf1a72.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-reward_modeling__1__1742338142/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6344
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7326
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3812
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7049
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.88
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6323
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.475
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1742519610/29515933-c60b-4686-b475-70ef53d75457.json b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1742519610/29515933-c60b-4686-b475-70ef53d75457.json
index 7b2861f0f..e2f564fd7 100644
--- a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1742519610/29515933-c60b-4686-b475-70ef53d75457.json
+++ b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1742519610/29515933-c60b-4686-b475-70ef53d75457.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-reward_modeling__1__1742519610/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6361
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7074
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3812
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6721
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.82
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6444
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5915
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1742519628/414174a9-7e44-4f7b-94ce-0757639f5af7.json b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1742519628/414174a9-7e44-4f7b-94ce-0757639f5af7.json
index ad3f3b414..e92fdfc16 100644
--- a/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1742519628/414174a9-7e44-4f7b-94ce-0757639f5af7.json
+++ b/data/reward-bench/allenai/open_instruct_dev-reward_modeling__1__1742519628/414174a9-7e44-4f7b-94ce-0757639f5af7.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-reward_modeling__1__1742519628/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5609
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5179
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3563
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.623
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8356
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5071
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5254
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_100pctflipped__1__1744241455/48513083-f854-455e-8455-ddbd2698ec03.json b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_100pctflipped__1__1744241455/48513083-f854-455e-8455-ddbd2698ec03.json
index 8cc753229..c75b5a4dd 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_100pctflipped__1__1744241455/48513083-f854-455e-8455-ddbd2698ec03.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_100pctflipped__1__1744241455/48513083-f854-455e-8455-ddbd2698ec03.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_1e-6_1_100pctflipped__1__1744241455/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.0576
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.04
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.1313
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.0546
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.0489
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.0808
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": -0.01
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_10pctflipped__1__1743295511/0b373560-854f-4482-81d0-6c984e130144.json b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_10pctflipped__1__1743295511/0b373560-854f-4482-81d0-6c984e130144.json
index 25e15cee3..d30d94d18 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_10pctflipped__1__1743295511/0b373560-854f-4482-81d0-6c984e130144.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_10pctflipped__1__1743295511/0b373560-854f-4482-81d0-6c984e130144.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_1e-6_1_10pctflipped__1__1743295511/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5499
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6821
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3937
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5956
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7356
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5212
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.3711
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_20pctflipped__1__1743295406/1a021cab-d569-4077-af5e-1643f45de03d.json b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_20pctflipped__1__1743295406/1a021cab-d569-4077-af5e-1643f45de03d.json
index b9b8966dc..d5744d0a2 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_20pctflipped__1__1743295406/1a021cab-d569-4077-af5e-1643f45de03d.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_20pctflipped__1__1743295406/1a021cab-d569-4077-af5e-1643f45de03d.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_1e-6_1_20pctflipped__1__1743295406/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5054
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6358
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3688
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6066
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6867
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.4424
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.2922
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_30pctflipped__1__1743325136/e26e230d-59b3-4243-a6c4-3845ab74b89b.json b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_30pctflipped__1__1743325136/e26e230d-59b3-4243-a6c4-3845ab74b89b.json
index 7ae1c6a61..1263be4bc 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_30pctflipped__1__1743325136/e26e230d-59b3-4243-a6c4-3845ab74b89b.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_30pctflipped__1__1743325136/e26e230d-59b3-4243-a6c4-3845ab74b89b.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_1e-6_1_30pctflipped__1__1743325136/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.478
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6442
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3563
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.612
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6356
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.2707
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.3496
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_50pctflipped__1__1744241398/aa0991d0-9c5e-4f94-bc12-3342ca389e99.json b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_50pctflipped__1__1744241398/aa0991d0-9c5e-4f94-bc12-3342ca389e99.json
index ea8c8eb0d..8bd48e77c 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_50pctflipped__1__1744241398/aa0991d0-9c5e-4f94-bc12-3342ca389e99.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_50pctflipped__1__1744241398/aa0991d0-9c5e-4f94-bc12-3342ca389e99.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_1e-6_1_50pctflipped__1__1744241398/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.219
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.2484
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.2812
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.2623
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.3422
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.1717
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.008
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_5pctflipped__1__1743444535/397abe47-d5e9-487d-b883-ec49db16c584.json b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_5pctflipped__1__1743444535/397abe47-d5e9-487d-b883-ec49db16c584.json
index ce94d3dd6..a81128f70 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_5pctflipped__1__1743444535/397abe47-d5e9-487d-b883-ec49db16c584.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_5pctflipped__1__1743444535/397abe47-d5e9-487d-b883-ec49db16c584.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_1e-6_1_5pctflipped__1__1743444535/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5625
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6821
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4062
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6011
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7511
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5313
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.403
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_dpo__1__1743550054/82f52a35-41b5-4b9c-bb3e-4bf18eed0b92.json b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_dpo__1__1743550054/82f52a35-41b5-4b9c-bb3e-4bf18eed0b92.json
index 8f5f2f727..53333e181 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_dpo__1__1743550054/82f52a35-41b5-4b9c-bb3e-4bf18eed0b92.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_dpo__1__1743550054/82f52a35-41b5-4b9c-bb3e-4bf18eed0b92.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_1e-6_1_dpo__1__1743550054/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5759
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7074
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.375
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.623
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7578
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5333
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.459
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_dpo_skyworks__1__1744530271/670382ab-a8a1-43f3-a572-b9a5aeae23ef.json b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_dpo_skyworks__1__1744530271/670382ab-a8a1-43f3-a572-b9a5aeae23ef.json
index 3560ba862..ba5b508f6 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_dpo_skyworks__1__1744530271/670382ab-a8a1-43f3-a572-b9a5aeae23ef.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_dpo_skyworks__1__1744530271/670382ab-a8a1-43f3-a572-b9a5aeae23ef.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_1e-6_1_dpo_skyworks__1__1744530271/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6057
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5053
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.375
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5902
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8422
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7798
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5419
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_dpo_skyworkstulufull__1__1743550181/a4b3c031-7c01-4f7a-8cfe-52b3260d6ecc.json b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_dpo_skyworkstulufull__1__1743550181/a4b3c031-7c01-4f7a-8cfe-52b3260d6ecc.json
index f5393bdb8..55a7568d2 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_dpo_skyworkstulufull__1__1743550181/a4b3c031-7c01-4f7a-8cfe-52b3260d6ecc.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_dpo_skyworkstulufull__1__1743550181/a4b3c031-7c01-4f7a-8cfe-52b3260d6ecc.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_1e-6_1_dpo_skyworkstulufull__1__1743550181/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6535
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7137
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3812
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6175
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8244
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7737
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6101
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_rl__1__1743551221/7fcd3fce-2296-4b5c-8362-24b1c70ccb8f.json b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_rl__1__1743551221/7fcd3fce-2296-4b5c-8362-24b1c70ccb8f.json
index 03b3b1315..b781deca8 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_rl__1__1743551221/7fcd3fce-2296-4b5c-8362-24b1c70ccb8f.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_rl__1__1743551221/7fcd3fce-2296-4b5c-8362-24b1c70ccb8f.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_1e-6_1_rl__1__1743551221/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5799
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7116
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3812
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.76
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5374
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.461
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_rl_skyworks__1__1744530262/4f164e8b-55a1-498f-b586-cf78da7d0b57.json b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_rl_skyworks__1__1744530262/4f164e8b-55a1-498f-b586-cf78da7d0b57.json
index ed8838f86..9f032475e 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_rl_skyworks__1__1744530262/4f164e8b-55a1-498f-b586-cf78da7d0b57.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_rl_skyworks__1__1744530262/4f164e8b-55a1-498f-b586-cf78da7d0b57.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_1e-6_1_rl_skyworks__1__1744530262/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5903
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.4863
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3625
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5738
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8489
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7778
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4926
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_rl_skyworkstulufull__1__1743551523/a84d3d61-6e05-4d4d-bc89-7f663e9667fb.json b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_rl_skyworkstulufull__1__1743551523/a84d3d61-6e05-4d4d-bc89-7f663e9667fb.json
index ae1b169a8..9d860b297 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_rl_skyworkstulufull__1__1743551523/a84d3d61-6e05-4d4d-bc89-7f663e9667fb.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_rl_skyworkstulufull__1__1743551523/a84d3d61-6e05-4d4d-bc89-7f663e9667fb.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_1e-6_1_rl_skyworkstulufull__1__1743551523/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6483
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7074
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3625
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6175
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8222
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7758
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6044
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_skyworkstulumix__1__1743205750/7aa98f71-8262-4c1f-a71c-1ef36f2ef04c.json b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_skyworkstulumix__1__1743205750/7aa98f71-8262-4c1f-a71c-1ef36f2ef04c.json
index 7679c69db..7961d2bec 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_skyworkstulumix__1__1743205750/7aa98f71-8262-4c1f-a71c-1ef36f2ef04c.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_1_skyworkstulumix__1__1743205750/7aa98f71-8262-4c1f-a71c-1ef36f2ef04c.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_1e-6_1_skyworkstulumix__1__1743205750/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5157
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6084
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3688
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6066
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7089
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.4222
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.3791
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_10pctflipped__1__1743295427/93398c1f-3129-4be4-83b5-62a4a45c6b84.json b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_10pctflipped__1__1743295427/93398c1f-3129-4be4-83b5-62a4a45c6b84.json
index 95de0b2a6..9a7aa8751 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_10pctflipped__1__1743295427/93398c1f-3129-4be4-83b5-62a4a45c6b84.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_10pctflipped__1__1743295427/93398c1f-3129-4be4-83b5-62a4a45c6b84.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_1e-6_2_10pctflipped__1__1743295427/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6009
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7263
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.375
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5902
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7933
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7273
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.3931
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_20pctflipped__1__1743295446/62493784-f899-4736-bdce-2107ec99a752.json b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_20pctflipped__1__1743295446/62493784-f899-4736-bdce-2107ec99a752.json
index dd6172be6..0629539f9 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_20pctflipped__1__1743295446/62493784-f899-4736-bdce-2107ec99a752.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_20pctflipped__1__1743295446/62493784-f899-4736-bdce-2107ec99a752.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_1e-6_2_20pctflipped__1__1743295446/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5716
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6779
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3937
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5464
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7533
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7051
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.3534
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_30pctflipped__1__1743325094/9b68ecaa-cf9d-414e-9cf1-c662c765bb5c.json b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_30pctflipped__1__1743325094/9b68ecaa-cf9d-414e-9cf1-c662c765bb5c.json
index 13df8e692..bca56ed2b 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_30pctflipped__1__1743325094/9b68ecaa-cf9d-414e-9cf1-c662c765bb5c.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_30pctflipped__1__1743325094/9b68ecaa-cf9d-414e-9cf1-c662c765bb5c.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_1e-6_2_30pctflipped__1__1743325094/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5151
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6484
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3312
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5574
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7289
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.4889
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.3357
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_5pctflipped__1__1743444636/76f3d0bd-2b71-4406-a0d4-b01b6c91c4ff.json b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_5pctflipped__1__1743444636/76f3d0bd-2b71-4406-a0d4-b01b6c91c4ff.json
index 8cfb3dab5..54fc2bfbe 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_5pctflipped__1__1743444636/76f3d0bd-2b71-4406-a0d4-b01b6c91c4ff.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_5pctflipped__1__1743444636/76f3d0bd-2b71-4406-a0d4-b01b6c91c4ff.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_1e-6_2_5pctflipped__1__1743444636/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6119
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.72
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4062
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8067
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6889
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.421
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_dpo__1__1743549325/2dc5ab6f-2427-42ae-9582-a0e6139f451a.json b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_dpo__1__1743549325/2dc5ab6f-2427-42ae-9582-a0e6139f451a.json
index 91011ae74..55ddbdfe8 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_dpo__1__1743549325/2dc5ab6f-2427-42ae-9582-a0e6139f451a.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_dpo__1__1743549325/2dc5ab6f-2427-42ae-9582-a0e6139f451a.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_1e-6_2_dpo__1__1743549325/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6008
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7179
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.35
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5956
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6707
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4707
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_rl__1__1743551238/0db97be6-6562-47d8-bd1a-5b469250e54b.json b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_rl__1__1743551238/0db97be6-6562-47d8-bd1a-5b469250e54b.json
index 3b7dac4aa..4b4ef4368 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_rl__1__1743551238/0db97be6-6562-47d8-bd1a-5b469250e54b.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_rl__1__1743551238/0db97be6-6562-47d8-bd1a-5b469250e54b.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_1e-6_2_rl__1__1743551238/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5965
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7095
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3438
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.612
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8044
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6566
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.453
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_skyworkstulumix__1__1743205906/228e4dc4-e517-4023-b690-7f0c321286b2.json b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_skyworkstulumix__1__1743205906/228e4dc4-e517-4023-b690-7f0c321286b2.json
index 9f627ce74..2cf126b25 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_skyworkstulumix__1__1743205906/228e4dc4-e517-4023-b690-7f0c321286b2.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_1e-6_2_skyworkstulumix__1__1743205906/228e4dc4-e517-4023-b690-7f0c321286b2.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_1e-6_2_skyworkstulumix__1__1743205906/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5574
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6526
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3937
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6011
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7711
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5051
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4208
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_100pctflipped__1__1744241529/9442b27c-c94d-41c0-a752-3bd82385272d.json b/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_100pctflipped__1__1744241529/9442b27c-c94d-41c0-a752-3bd82385272d.json
index 776e5e4aa..8dc1a9073 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_100pctflipped__1__1744241529/9442b27c-c94d-41c0-a752-3bd82385272d.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_100pctflipped__1__1744241529/9442b27c-c94d-41c0-a752-3bd82385272d.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_2e-5_1_100pctflipped__1__1744241529/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.0719
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.0421
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.2062
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.0601
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.0378
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.0949
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": -0.01
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_10pctflipped__1__1743295305/561039ac-b156-40eb-bf53-21a275b858ca.json b/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_10pctflipped__1__1743295305/561039ac-b156-40eb-bf53-21a275b858ca.json
index bce0553bd..5f62f67ab 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_10pctflipped__1__1743295305/561039ac-b156-40eb-bf53-21a275b858ca.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_10pctflipped__1__1743295305/561039ac-b156-40eb-bf53-21a275b858ca.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_2e-5_1_10pctflipped__1__1743295305/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.553
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6674
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3563
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6733
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5697
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4227
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_20pctflipped__1__1743324778/d801d700-7b4d-4a62-883b-3d85b05385ea.json b/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_20pctflipped__1__1743324778/d801d700-7b4d-4a62-883b-3d85b05385ea.json
index e616ad328..431df7a47 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_20pctflipped__1__1743324778/d801d700-7b4d-4a62-883b-3d85b05385ea.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_20pctflipped__1__1743324778/d801d700-7b4d-4a62-883b-3d85b05385ea.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_2e-5_1_20pctflipped__1__1743324778/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.4955
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6189
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.325
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5792
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6378
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5657
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.2466
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_30pctflipped__1__1743326459/b8f24058-4441-4d19-898e-80470cc7b685.json b/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_30pctflipped__1__1743326459/b8f24058-4441-4d19-898e-80470cc7b685.json
index 258844fef..6552eeea3 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_30pctflipped__1__1743326459/b8f24058-4441-4d19-898e-80470cc7b685.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_30pctflipped__1__1743326459/b8f24058-4441-4d19-898e-80470cc7b685.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_2e-5_1_30pctflipped__1__1743326459/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.4198
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5747
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3375
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5464
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.4933
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.3596
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.2073
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_5pctflipped__1__1743443747/1f372e00-e7a8-43ef-8e14-ef1b08e5e957.json b/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_5pctflipped__1__1743443747/1f372e00-e7a8-43ef-8e14-ef1b08e5e957.json
index 6f242885e..6c4f2b7cc 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_5pctflipped__1__1743443747/1f372e00-e7a8-43ef-8e14-ef1b08e5e957.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_5pctflipped__1__1743443747/1f372e00-e7a8-43ef-8e14-ef1b08e5e957.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_2e-5_1_5pctflipped__1__1743443747/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5465
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6821
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.375
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.612
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7333
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5051
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.3713
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_skyworkstulumix__1__1743205935/0200a1b3-71f1-4633-96a5-4ca9883a67a7.json b/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_skyworkstulumix__1__1743205935/0200a1b3-71f1-4633-96a5-4ca9883a67a7.json
index 6377b0646..aabf71c3b 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_skyworkstulumix__1__1743205935/0200a1b3-71f1-4633-96a5-4ca9883a67a7.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_1_skyworkstulumix__1__1743205935/0200a1b3-71f1-4633-96a5-4ca9883a67a7.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_2e-5_1_skyworkstulumix__1__1743205935/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5197
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6126
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3375
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5847
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7333
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.4646
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.3855
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_2_10pctflipped__1__1743295360/55479901-aec7-4875-b792-ba73b54aa37a.json b/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_2_10pctflipped__1__1743295360/55479901-aec7-4875-b792-ba73b54aa37a.json
index fa1623133..a1a7dd25e 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_2_10pctflipped__1__1743295360/55479901-aec7-4875-b792-ba73b54aa37a.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_2_10pctflipped__1__1743295360/55479901-aec7-4875-b792-ba73b54aa37a.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_2e-5_2_10pctflipped__1__1743295360/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.4555
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5495
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3063
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.4262
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.5711
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6101
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.2696
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_2_20pctflipped__1__1743295366/872597b2-4392-4f23-b5b2-41d418b6cf89.json b/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_2_20pctflipped__1__1743295366/872597b2-4392-4f23-b5b2-41d418b6cf89.json
index 9b0a80d97..f5aa5f436 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_2_20pctflipped__1__1743295366/872597b2-4392-4f23-b5b2-41d418b6cf89.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_2_20pctflipped__1__1743295366/872597b2-4392-4f23-b5b2-41d418b6cf89.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_2e-5_2_20pctflipped__1__1743295366/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.4422
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5053
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3375
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.4044
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.5422
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6646
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.1991
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_2_30pctflipped__1__1743326352/5cb437b5-5993-418d-bd9f-81dea71d9edf.json b/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_2_30pctflipped__1__1743326352/5cb437b5-5993-418d-bd9f-81dea71d9edf.json
index 81139c06d..a0af647f5 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_2_30pctflipped__1__1743326352/5cb437b5-5993-418d-bd9f-81dea71d9edf.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_2_30pctflipped__1__1743326352/5cb437b5-5993-418d-bd9f-81dea71d9edf.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_2e-5_2_30pctflipped__1__1743326352/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.341
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.4674
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.2875
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.3333
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.3711
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.3919
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.195
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_2_5pctflipped__1__1743444634/c471cdf7-73f9-48c9-a970-baa66b609093.json b/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_2_5pctflipped__1__1743444634/c471cdf7-73f9-48c9-a970-baa66b609093.json
index cf6f1e202..c1a864b6a 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_2_5pctflipped__1__1743444634/c471cdf7-73f9-48c9-a970-baa66b609093.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_2_5pctflipped__1__1743444634/c471cdf7-73f9-48c9-a970-baa66b609093.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_2e-5_2_5pctflipped__1__1743444634/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.4698
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5853
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.2562
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5027
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6489
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5697
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.2562
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_2_skyworkstulumix__1__1743205988/794a71b4-8a43-4c69-a663-369eea6a84a3.json b/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_2_skyworkstulumix__1__1743205988/794a71b4-8a43-4c69-a663-369eea6a84a3.json
index 2f9ef1c59..4f624253c 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_2_skyworkstulumix__1__1743205988/794a71b4-8a43-4c69-a663-369eea6a84a3.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_2e-5_2_skyworkstulumix__1__1743205988/794a71b4-8a43-4c69-a663-369eea6a84a3.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_2e-5_2_skyworkstulumix__1__1743205988/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.4791
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6421
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3125
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.541
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6911
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.4182
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.27
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_100pctflipped__1__1744242103/2ad22375-4ed8-4be6-a012-a6f6799581e2.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_100pctflipped__1__1744242103/2ad22375-4ed8-4be6-a012-a6f6799581e2.json
index 656ff3ace..da7381bc1 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_100pctflipped__1__1744242103/2ad22375-4ed8-4be6-a012-a6f6799581e2.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_100pctflipped__1__1744242103/2ad22375-4ed8-4be6-a012-a6f6799581e2.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_1_100pctflipped__1__1744242103/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.0607
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.0274
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.1625
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.0656
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.04
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.0788
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": -0.01
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_10pctflipped__1__1743324835/a8df0dc2-d16c-4e1a-b0b5-abe2a4a1d803.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_10pctflipped__1__1743324835/a8df0dc2-d16c-4e1a-b0b5-abe2a4a1d803.json
index 15ddbb19b..a04867707 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_10pctflipped__1__1743324835/a8df0dc2-d16c-4e1a-b0b5-abe2a4a1d803.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_10pctflipped__1__1743324835/a8df0dc2-d16c-4e1a-b0b5-abe2a4a1d803.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_1_10pctflipped__1__1743324835/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6089
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4375
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.612
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7622
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6444
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4686
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_1pctflipped__1__1743445221/ca0a010a-fe3a-4b87-8c80-4a8d3e2597fb.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_1pctflipped__1__1743445221/ca0a010a-fe3a-4b87-8c80-4a8d3e2597fb.json
index fd550ff4e..de5939755 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_1pctflipped__1__1743445221/ca0a010a-fe3a-4b87-8c80-4a8d3e2597fb.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_1pctflipped__1__1743445221/ca0a010a-fe3a-4b87-8c80-4a8d3e2597fb.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_1_1pctflipped__1__1743445221/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6032
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7158
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4062
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7778
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5859
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5051
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_20pctflipped__1__1743324826/5d1c166c-6a22-4afb-b1b1-f7db9ec38bd8.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_20pctflipped__1__1743324826/5d1c166c-6a22-4afb-b1b1-f7db9ec38bd8.json
index cb78f43a1..7f0d231a3 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_20pctflipped__1__1743324826/5d1c166c-6a22-4afb-b1b1-f7db9ec38bd8.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_20pctflipped__1__1743324826/5d1c166c-6a22-4afb-b1b1-f7db9ec38bd8.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_1_20pctflipped__1__1743324826/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5831
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6947
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4188
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.623
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.74
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5758
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4465
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_30pctflipped__1__1743326363/10a432fa-dfef-4c9c-bdf7-ce0f81fd1895.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_30pctflipped__1__1743326363/10a432fa-dfef-4c9c-bdf7-ce0f81fd1895.json
index b0a09b23e..25ae9470b 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_30pctflipped__1__1743326363/10a432fa-dfef-4c9c-bdf7-ce0f81fd1895.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_30pctflipped__1__1743326363/10a432fa-dfef-4c9c-bdf7-ce0f81fd1895.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_1_30pctflipped__1__1743326363/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5268
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.68
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3688
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5792
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7178
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.4343
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.3809
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_5pctflipped__1__1743444498/a550663c-2a04-4dfb-8663-b177a7181f3d.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_5pctflipped__1__1743444498/a550663c-2a04-4dfb-8663-b177a7181f3d.json
index e0aa38363..0676aafc3 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_5pctflipped__1__1743444498/a550663c-2a04-4dfb-8663-b177a7181f3d.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_5pctflipped__1__1743444498/a550663c-2a04-4dfb-8663-b177a7181f3d.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_1_5pctflipped__1__1743444498/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6093
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7326
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4313
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6339
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7578
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5859
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5143
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1__2__1743897475/72b6196e-0a2b-4ec9-80a3-a7eb14f7be09.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1__2__1743897475/72b6196e-0a2b-4ec9-80a3-a7eb14f7be09.json
index 5f55252f9..42e9ce0e8 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1__2__1743897475/72b6196e-0a2b-4ec9-80a3-a7eb14f7be09.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1__2__1743897475/72b6196e-0a2b-4ec9-80a3-a7eb14f7be09.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_1__2__1743897475/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6122
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7368
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.623
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8044
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.602
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5071
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1__3__1744311421/5e41f068-f009-4e32-bac1-9de5220a2ce2.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1__3__1744311421/5e41f068-f009-4e32-bac1-9de5220a2ce2.json
index 7a3fade87..c9eb27faa 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1__3__1744311421/5e41f068-f009-4e32-bac1-9de5220a2ce2.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1__3__1744311421/5e41f068-f009-4e32-bac1-9de5220a2ce2.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_1__3__1744311421/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5995
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7179
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3375
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6066
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6323
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.503
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_dpo__1__1743549903/eca1331f-6503-481a-b77b-3d96791f54e8.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_dpo__1__1743549903/eca1331f-6503-481a-b77b-3d96791f54e8.json
index 44c242478..86624d603 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_dpo__1__1743549903/eca1331f-6503-481a-b77b-3d96791f54e8.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_dpo__1__1743549903/eca1331f-6503-481a-b77b-3d96791f54e8.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_1_dpo__1__1743549903/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6154
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7326
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4375
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6339
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7778
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6061
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5043
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_dpo_skyworks__1__1744530368/69def7de-a916-4d23-984b-e676e91e1d8c.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_dpo_skyworks__1__1744530368/69def7de-a916-4d23-984b-e676e91e1d8c.json
index 04069c084..ade9d6695 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_dpo_skyworks__1__1744530368/69def7de-a916-4d23-984b-e676e91e1d8c.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_dpo_skyworks__1__1744530368/69def7de-a916-4d23-984b-e676e91e1d8c.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_1_dpo_skyworks__1__1744530368/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6604
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6316
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3937
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5792
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9044
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8929
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5604
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_dpo_skyworkstulufull__1__1743550182/679c6e0b-9e0b-4224-b1e3-59df149739a0.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_dpo_skyworkstulufull__1__1743550182/679c6e0b-9e0b-4224-b1e3-59df149739a0.json
index 60fb1cc4c..c5d2892d2 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_dpo_skyworkstulufull__1__1743550182/679c6e0b-9e0b-4224-b1e3-59df149739a0.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_dpo_skyworkstulufull__1__1743550182/679c6e0b-9e0b-4224-b1e3-59df149739a0.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_1_dpo_skyworkstulufull__1__1743550182/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6783
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7705
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6066
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.84
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8101
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6427
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_no_if__2__1744316012/2335433d-37c6-47f0-ad3b-5e0a42e9488f.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_no_if__2__1744316012/2335433d-37c6-47f0-ad3b-5e0a42e9488f.json
index c7922a644..e2e75967a 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_no_if__2__1744316012/2335433d-37c6-47f0-ad3b-5e0a42e9488f.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_no_if__2__1744316012/2335433d-37c6-47f0-ad3b-5e0a42e9488f.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_1_no_if__2__1744316012/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5911
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7347
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.74
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.604
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4392
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_no_if__3__1744315765/fe84f8a3-5fe9-4385-b6d4-0436fb7e5197.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_no_if__3__1744315765/fe84f8a3-5fe9-4385-b6d4-0436fb7e5197.json
index a845558dc..2d3cbe13a 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_no_if__3__1744315765/fe84f8a3-5fe9-4385-b6d4-0436fb7e5197.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_no_if__3__1744315765/fe84f8a3-5fe9-4385-b6d4-0436fb7e5197.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_1_no_if__3__1744315765/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5926
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7263
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3563
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.623
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7889
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5879
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4733
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_rl__1__1743551527/70d2697e-0df5-40ae-9268-b906c9cabd9d.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_rl__1__1743551527/70d2697e-0df5-40ae-9268-b906c9cabd9d.json
index 007b55ac9..d305acb78 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_rl__1__1743551527/70d2697e-0df5-40ae-9268-b906c9cabd9d.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_rl__1__1743551527/70d2697e-0df5-40ae-9268-b906c9cabd9d.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_1_rl__1__1743551527/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6126
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7411
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.425
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.623
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7822
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5939
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5104
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_rl_skyworks__1__1744530236/0a30fd70-2381-4a4b-89aa-dbd169c856f0.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_rl_skyworks__1__1744530236/0a30fd70-2381-4a4b-89aa-dbd169c856f0.json
index f2f9d18b0..bf0b750c2 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_rl_skyworks__1__1744530236/0a30fd70-2381-4a4b-89aa-dbd169c856f0.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_rl_skyworks__1__1744530236/0a30fd70-2381-4a4b-89aa-dbd169c856f0.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_1_rl_skyworks__1__1744530236/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6525
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6021
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3875
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5792
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8933
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8626
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.59
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_rl_skyworkstulufull__1__1743551530/b9c787f9-3bcd-4215-a157-7fcfa2df82cc.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_rl_skyworkstulufull__1__1743551530/b9c787f9-3bcd-4215-a157-7fcfa2df82cc.json
index 15a69a666..bf056a3a5 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_rl_skyworkstulufull__1__1743551530/b9c787f9-3bcd-4215-a157-7fcfa2df82cc.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_rl_skyworkstulufull__1__1743551530/b9c787f9-3bcd-4215-a157-7fcfa2df82cc.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_1_rl_skyworkstulufull__1__1743551530/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6849
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7453
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3812
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.612
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8422
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8404
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6885
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_skyworkstulu75__1__1743534417/bdd98f27-fbfd-4de7-bd4e-3b8c3e4e7cc0.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_skyworkstulu75__1__1743534417/bdd98f27-fbfd-4de7-bd4e-3b8c3e4e7cc0.json
index 64c48beaa..b8d8f17e6 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_skyworkstulu75__1__1743534417/bdd98f27-fbfd-4de7-bd4e-3b8c3e4e7cc0.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_skyworkstulu75__1__1743534417/bdd98f27-fbfd-4de7-bd4e-3b8c3e4e7cc0.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_1_skyworkstulu75__1__1743534417/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.586
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6632
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.425
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6557
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7778
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5172
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.477
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_skyworkstulufull__1__1743446486/44b20109-d534-4aa9-867d-fa59935ef6d0.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_skyworkstulufull__1__1743446486/44b20109-d534-4aa9-867d-fa59935ef6d0.json
index 0c4f3ed5a..5bc8800b1 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_skyworkstulufull__1__1743446486/44b20109-d534-4aa9-867d-fa59935ef6d0.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_skyworkstulufull__1__1743446486/44b20109-d534-4aa9-867d-fa59935ef6d0.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_1_skyworkstulufull__1__1743446486/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6773
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7432
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.612
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8422
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.804
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6626
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_skyworkstulufull__2__1744314745/d1196312-4153-4a38-aa46-2940d63d7924.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_skyworkstulufull__2__1744314745/d1196312-4153-4a38-aa46-2940d63d7924.json
index 211703e24..620c1403f 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_skyworkstulufull__2__1744314745/d1196312-4153-4a38-aa46-2940d63d7924.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_skyworkstulufull__2__1744314745/d1196312-4153-4a38-aa46-2940d63d7924.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_1_skyworkstulufull__2__1744314745/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6793
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7558
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4062
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8311
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8061
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6485
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_skyworkstulufull__3__1744311661/4b1e3070-04ef-47e7-b720-739320194e7b.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_skyworkstulufull__3__1744311661/4b1e3070-04ef-47e7-b720-739320194e7b.json
index 2ebaeb360..93ad54ca5 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_skyworkstulufull__3__1744311661/4b1e3070-04ef-47e7-b720-739320194e7b.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_skyworkstulufull__3__1744311661/4b1e3070-04ef-47e7-b720-739320194e7b.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_1_skyworkstulufull__3__1744311661/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6611
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.72
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3563
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6393
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8444
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7636
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6428
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_skyworkstulumix__1__1743204472/247f400e-dca8-4dab-bebf-092f778f02c9.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_skyworkstulumix__1__1743204472/247f400e-dca8-4dab-bebf-092f778f02c9.json
index 42b80157b..12de82f8f 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_skyworkstulumix__1__1743204472/247f400e-dca8-4dab-bebf-092f778f02c9.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_1_skyworkstulumix__1__1743204472/247f400e-dca8-4dab-bebf-092f778f02c9.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_1_skyworkstulumix__1__1743204472/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5778
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6674
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3875
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6011
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7933
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5172
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5003
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_10pctflipped__1__1743295267/d043ad21-102b-49f0-9e8e-6daef7cc3a2e.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_10pctflipped__1__1743295267/d043ad21-102b-49f0-9e8e-6daef7cc3a2e.json
index 85cca367e..7f64660cc 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_10pctflipped__1__1743295267/d043ad21-102b-49f0-9e8e-6daef7cc3a2e.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_10pctflipped__1__1743295267/d043ad21-102b-49f0-9e8e-6daef7cc3a2e.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_2_10pctflipped__1__1743295267/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5746
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6505
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.35
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5082
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7844
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7414
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4128
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_1pctflipped__1__1743445759/d45ec8b8-1ee6-49bb-9237-a7271ba9d13c.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_1pctflipped__1__1743445759/d45ec8b8-1ee6-49bb-9237-a7271ba9d13c.json
index 07424bed4..cd842e3b9 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_1pctflipped__1__1743445759/d45ec8b8-1ee6-49bb-9237-a7271ba9d13c.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_1pctflipped__1__1743445759/d45ec8b8-1ee6-49bb-9237-a7271ba9d13c.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_2_1pctflipped__1__1743445759/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6065
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7116
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.35
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5792
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8178
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7152
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.465
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_20pctflipped__1__1743324905/05a4c6aa-9af2-44f0-8c55-8aeed2e75eaf.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_20pctflipped__1__1743324905/05a4c6aa-9af2-44f0-8c55-8aeed2e75eaf.json
index e27b5cfcd..eb5fdd21c 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_20pctflipped__1__1743324905/05a4c6aa-9af2-44f0-8c55-8aeed2e75eaf.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_20pctflipped__1__1743324905/05a4c6aa-9af2-44f0-8c55-8aeed2e75eaf.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_2_20pctflipped__1__1743324905/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5305
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5832
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3312
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.459
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7178
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7071
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.3849
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_30pctflipped__1__1743326363/a6ef712e-014e-470e-8d5b-f3b51f677aee.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_30pctflipped__1__1743326363/a6ef712e-014e-470e-8d5b-f3b51f677aee.json
index 68eaa49b9..f42f0f831 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_30pctflipped__1__1743326363/a6ef712e-014e-470e-8d5b-f3b51f677aee.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_30pctflipped__1__1743326363/a6ef712e-014e-470e-8d5b-f3b51f677aee.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_2_30pctflipped__1__1743326363/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.4436
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5411
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3312
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.3115
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6267
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5414
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.31
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_5pctflipped__1__1743444505/35a039ba-06be-4ec2-9bde-a6a6db2eefec.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_5pctflipped__1__1743444505/35a039ba-06be-4ec2-9bde-a6a6db2eefec.json
index f0c8fa826..f6b4dff52 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_5pctflipped__1__1743444505/35a039ba-06be-4ec2-9bde-a6a6db2eefec.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_5pctflipped__1__1743444505/35a039ba-06be-4ec2-9bde-a6a6db2eefec.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_2_5pctflipped__1__1743444505/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5925
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.68
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3688
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5519
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.78
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7434
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.431
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_dpo__1__1743550180/97cb96f8-ce4c-403f-bfbc-386d3c611c81.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_dpo__1__1743550180/97cb96f8-ce4c-403f-bfbc-386d3c611c81.json
index 275d60107..d291b202f 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_dpo__1__1743550180/97cb96f8-ce4c-403f-bfbc-386d3c611c81.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_dpo__1__1743550180/97cb96f8-ce4c-403f-bfbc-386d3c611c81.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_2_dpo__1__1743550180/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6198
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7263
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3312
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6339
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8133
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7232
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4908
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_dpo_skyworkstulufull__1__1743550187/3a1621e9-75ee-4b34-9c0d-ae15399b1dab.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_dpo_skyworkstulufull__1__1743550187/3a1621e9-75ee-4b34-9c0d-ae15399b1dab.json
index 1949117b5..0d4d4902f 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_dpo_skyworkstulufull__1__1743550187/3a1621e9-75ee-4b34-9c0d-ae15399b1dab.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_dpo_skyworkstulufull__1__1743550187/3a1621e9-75ee-4b34-9c0d-ae15399b1dab.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_2_dpo_skyworkstulufull__1__1743550187/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6763
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7411
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.375
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.612
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8844
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8545
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5908
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_rl__1__1743551509/237218ac-4c74-4647-82b1-700360ddfdbd.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_rl__1__1743551509/237218ac-4c74-4647-82b1-700360ddfdbd.json
index f848eb22f..6717d04eb 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_rl__1__1743551509/237218ac-4c74-4647-82b1-700360ddfdbd.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_rl__1__1743551509/237218ac-4c74-4647-82b1-700360ddfdbd.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_2_rl__1__1743551509/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6245
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7242
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.35
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6175
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8178
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7253
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5124
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_rl_skyworkstulufull__1__1743551498/2858d126-d2ef-4512-8fc8-c39faf24b908.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_rl_skyworkstulufull__1__1743551498/2858d126-d2ef-4512-8fc8-c39faf24b908.json
index 19a835907..7e1595151 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_rl_skyworkstulufull__1__1743551498/2858d126-d2ef-4512-8fc8-c39faf24b908.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_rl_skyworkstulufull__1__1743551498/2858d126-d2ef-4512-8fc8-c39faf24b908.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_2_rl_skyworkstulufull__1__1743551498/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6673
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7326
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3438
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6175
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8622
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8566
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5911
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_skyworkstulu75__1__1743548926/d118ddb1-aafc-4ddf-b5c7-f3ff921bbe0c.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_skyworkstulu75__1__1743548926/d118ddb1-aafc-4ddf-b5c7-f3ff921bbe0c.json
index 54f6f5b7e..599698f0e 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_skyworkstulu75__1__1743548926/d118ddb1-aafc-4ddf-b5c7-f3ff921bbe0c.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_skyworkstulu75__1__1743548926/d118ddb1-aafc-4ddf-b5c7-f3ff921bbe0c.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_2_skyworkstulu75__1__1743548926/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5863
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6674
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3937
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5515
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4768
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_skyworkstulumix__1__1743205661/379ec82f-a6a7-4976-a4a6-ab80cb9da293.json b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_skyworkstulumix__1__1743205661/379ec82f-a6a7-4976-a4a6-ab80cb9da293.json
index ff4fe8a13..aa704ecb8 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_skyworkstulumix__1__1743205661/379ec82f-a6a7-4976-a4a6-ab80cb9da293.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_3e-6_2_skyworkstulumix__1__1743205661/379ec82f-a6a7-4976-a4a6-ab80cb9da293.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_3e-6_2_skyworkstulumix__1__1743205661/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.589
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6842
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3688
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6393
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7867
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6081
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.447
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llama70b_skyworkstulufull__4__1747266598/c4df42d1-a838-4717-a814-40559fcd7342.json b/data/reward-bench/allenai/open_instruct_dev-rm_llama70b_skyworkstulufull__4__1747266598/c4df42d1-a838-4717-a814-40559fcd7342.json
index 239e14075..1c2c98ef1 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llama70b_skyworkstulufull__4__1747266598/c4df42d1-a838-4717-a814-40559fcd7342.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llama70b_skyworkstulufull__4__1747266598/c4df42d1-a838-4717-a814-40559fcd7342.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llama70b_skyworkstulufull__4__1747266598/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7306
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7474
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.375
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.694
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8622
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8061
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.8992
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llama70b_skyworkstulufull__8__1745387923/f022d826-3252-4def-b37b-3ce44d78f4ce.json b/data/reward-bench/allenai/open_instruct_dev-rm_llama70b_skyworkstulufull__8__1745387923/f022d826-3252-4def-b37b-3ce44d78f4ce.json
index dd8ead8fd..a60528170 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llama70b_skyworkstulufull__8__1745387923/f022d826-3252-4def-b37b-3ce44d78f4ce.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llama70b_skyworkstulufull__8__1745387923/f022d826-3252-4def-b37b-3ce44d78f4ce.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llama70b_skyworkstulufull__8__1745387923/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7573
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8168
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4125
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7049
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8733
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8545
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.8814
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llama_1e-6_1__1__1743896628/cecc321b-efbd-434e-8a31-a97bbb8bbb3b.json b/data/reward-bench/allenai/open_instruct_dev-rm_llama_1e-6_1__1__1743896628/cecc321b-efbd-434e-8a31-a97bbb8bbb3b.json
index 1b6ae8e92..7523cf126 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llama_1e-6_1__1__1743896628/cecc321b-efbd-434e-8a31-a97bbb8bbb3b.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llama_1e-6_1__1__1743896628/cecc321b-efbd-434e-8a31-a97bbb8bbb3b.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llama_1e-6_1__1__1743896628/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6637
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6947
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4062
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8422
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7273
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6834
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llama_1e-6_1_skyworks__1__1744062999/278c2132-3415-48f4-a839-ed09d71e9240.json b/data/reward-bench/allenai/open_instruct_dev-rm_llama_1e-6_1_skyworks__1__1744062999/278c2132-3415-48f4-a839-ed09d71e9240.json
index a91a3b5a1..884f2c1d7 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llama_1e-6_1_skyworks__1__1744062999/278c2132-3415-48f4-a839-ed09d71e9240.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llama_1e-6_1_skyworks__1__1744062999/278c2132-3415-48f4-a839-ed09d71e9240.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llama_1e-6_1_skyworks__1__1744062999/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6665
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5979
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3688
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6339
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8956
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8606
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6422
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llama_1e-6_1_skyworkstulufull__1__1743712777/92bbda1a-ecb1-493d-aa39-a29522c1a11e.json b/data/reward-bench/allenai/open_instruct_dev-rm_llama_1e-6_1_skyworkstulufull__1__1743712777/92bbda1a-ecb1-493d-aa39-a29522c1a11e.json
index 34e3c97b7..58d203adf 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llama_1e-6_1_skyworkstulufull__1__1743712777/92bbda1a-ecb1-493d-aa39-a29522c1a11e.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llama_1e-6_1_skyworkstulufull__1__1743712777/92bbda1a-ecb1-493d-aa39-a29522c1a11e.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llama_1e-6_1_skyworkstulufull__1__1743712777/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7038
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6947
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3937
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6557
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8867
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8586
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.7331
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llama_1e-6_2__1__1743896638/f43b2dff-9e73-4779-86e0-b2cc30ae8b40.json b/data/reward-bench/allenai/open_instruct_dev-rm_llama_1e-6_2__1__1743896638/f43b2dff-9e73-4779-86e0-b2cc30ae8b40.json
index efc7adbb8..eb2f9451c 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llama_1e-6_2__1__1743896638/f43b2dff-9e73-4779-86e0-b2cc30ae8b40.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llama_1e-6_2__1__1743896638/f43b2dff-9e73-4779-86e0-b2cc30ae8b40.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llama_1e-6_2__1__1743896638/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6754
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6716
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6339
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8756
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7737
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6976
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llama_1e-6_2_skyworkstulufull__1__1743800938/59a98f5d-d017-4b1a-a563-5abd113337e9.json b/data/reward-bench/allenai/open_instruct_dev-rm_llama_1e-6_2_skyworkstulufull__1__1743800938/59a98f5d-d017-4b1a-a563-5abd113337e9.json
index 370fb153c..b741da56e 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llama_1e-6_2_skyworkstulufull__1__1743800938/59a98f5d-d017-4b1a-a563-5abd113337e9.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llama_1e-6_2_skyworkstulufull__1__1743800938/59a98f5d-d017-4b1a-a563-5abd113337e9.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llama_1e-6_2_skyworkstulufull__1__1743800938/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7241
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7305
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6667
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9422
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9414
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6635
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llama_2e-5_1_skyworkstulufull__1__1743712885/a41597ed-fbab-41af-9625-c277ca988546.json b/data/reward-bench/allenai/open_instruct_dev-rm_llama_2e-5_1_skyworkstulufull__1__1743712885/a41597ed-fbab-41af-9625-c277ca988546.json
index 389f17a6d..4c6ec4ab3 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llama_2e-5_1_skyworkstulufull__1__1743712885/a41597ed-fbab-41af-9625-c277ca988546.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llama_2e-5_1_skyworkstulufull__1__1743712885/a41597ed-fbab-41af-9625-c277ca988546.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llama_2e-5_1_skyworkstulufull__1__1743712885/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6716
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6632
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3688
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.82
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8303
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.719
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llama_2e-5_2_skyworkstulufull__1__1743800773/e311eb59-f217-4bc2-b69b-dcea434797a8.json b/data/reward-bench/allenai/open_instruct_dev-rm_llama_2e-5_2_skyworkstulufull__1__1743800773/e311eb59-f217-4bc2-b69b-dcea434797a8.json
index 03485eca0..92fb6052e 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llama_2e-5_2_skyworkstulufull__1__1743800773/e311eb59-f217-4bc2-b69b-dcea434797a8.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llama_2e-5_2_skyworkstulufull__1__1743800773/e311eb59-f217-4bc2-b69b-dcea434797a8.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llama_2e-5_2_skyworkstulufull__1__1743800773/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6207
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6358
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.375
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5902
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8267
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.802
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4948
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llama_2e-6_1_skyworkstulufull__1__1743893867/69b037c3-bae2-4889-b10d-e732c45851e9.json b/data/reward-bench/allenai/open_instruct_dev-rm_llama_2e-6_1_skyworkstulufull__1__1743893867/69b037c3-bae2-4889-b10d-e732c45851e9.json
index 6484f285a..5c7a0911d 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llama_2e-6_1_skyworkstulufull__1__1743893867/69b037c3-bae2-4889-b10d-e732c45851e9.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llama_2e-6_1_skyworkstulufull__1__1743893867/69b037c3-bae2-4889-b10d-e732c45851e9.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llama_2e-6_1_skyworkstulufull__1__1743893867/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.719
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7263
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3875
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6393
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8956
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9273
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.738
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1__1__1743929424/adeee000-0b62-4a0c-afaa-5e8c5f29ff6d.json b/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1__1__1743929424/adeee000-0b62-4a0c-afaa-5e8c5f29ff6d.json
index 2e7c644e7..8b895898b 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1__1__1743929424/adeee000-0b62-4a0c-afaa-5e8c5f29ff6d.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1__1__1743929424/adeee000-0b62-4a0c-afaa-5e8c5f29ff6d.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llama_3e-6_1__1__1743929424/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6572
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7305
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3688
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8289
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.703
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6837
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1__2__1744311395/4464d588-62b2-440b-8188-2450bd7a94c5.json b/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1__2__1744311395/4464d588-62b2-440b-8188-2450bd7a94c5.json
index 9bf9f5677..cba9daba8 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1__2__1744311395/4464d588-62b2-440b-8188-2450bd7a94c5.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1__2__1744311395/4464d588-62b2-440b-8188-2450bd7a94c5.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llama_3e-6_1__2__1744311395/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6938
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7537
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.45
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6393
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8667
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7616
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6913
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1__3__1744311491/bf358648-a41d-43ee-8c14-f8b8eef41871.json b/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1__3__1744311491/bf358648-a41d-43ee-8c14-f8b8eef41871.json
index f600554b8..acca1c710 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1__3__1744311491/bf358648-a41d-43ee-8c14-f8b8eef41871.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1__3__1744311491/bf358648-a41d-43ee-8c14-f8b8eef41871.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llama_3e-6_1__3__1744311491/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6754
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7242
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4062
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8422
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7535
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6976
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1_skyworks__1__1744062787/afd99f12-f739-40d3-aa11-ef3a45316931.json b/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1_skyworks__1__1744062787/afd99f12-f739-40d3-aa11-ef3a45316931.json
index ba7ec7691..d8abd1886 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1_skyworks__1__1744062787/afd99f12-f739-40d3-aa11-ef3a45316931.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1_skyworks__1__1744062787/afd99f12-f739-40d3-aa11-ef3a45316931.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llama_3e-6_1_skyworks__1__1744062787/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7045
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6253
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3812
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6667
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.92
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9232
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.7109
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1_skyworkstulufull__2__1744311461/49b4a24b-ddf1-47f0-ba39-9366892a1213.json b/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1_skyworkstulufull__2__1744311461/49b4a24b-ddf1-47f0-ba39-9366892a1213.json
index aed65ca51..68019510c 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1_skyworkstulufull__2__1744311461/49b4a24b-ddf1-47f0-ba39-9366892a1213.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1_skyworkstulufull__2__1744311461/49b4a24b-ddf1-47f0-ba39-9366892a1213.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llama_3e-6_1_skyworkstulufull__2__1744311461/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7189
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7305
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3937
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6066
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8978
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9374
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.7475
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1_skyworkstulufull__3__1744311780/ea14a487-39c3-488b-b52b-998e57135487.json b/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1_skyworkstulufull__3__1744311780/ea14a487-39c3-488b-b52b-998e57135487.json
index 9b879bd49..cb7ea678a 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1_skyworkstulufull__3__1744311780/ea14a487-39c3-488b-b52b-998e57135487.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_1_skyworkstulufull__3__1744311780/ea14a487-39c3-488b-b52b-998e57135487.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llama_3e-6_1_skyworkstulufull__3__1744311780/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7172
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7242
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4313
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6175
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8778
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.897
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.7555
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_2__1__1743896489/02f74b6a-7f63-484e-a7c1-0c53bd801b87.json b/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_2__1__1743896489/02f74b6a-7f63-484e-a7c1-0c53bd801b87.json
index 7b6ba9d0a..462dccb75 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_2__1__1743896489/02f74b6a-7f63-484e-a7c1-0c53bd801b87.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_2__1__1743896489/02f74b6a-7f63-484e-a7c1-0c53bd801b87.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llama_3e-6_2__1__1743896489/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6813
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7137
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4437
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8644
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7596
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6781
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_2_skyworkstulufull__1__1743800713/e492c59d-4b03-4dce-983e-a8724de35a60.json b/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_2_skyworkstulufull__1__1743800713/e492c59d-4b03-4dce-983e-a8724de35a60.json
index 32bb74ed1..1f6674a88 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_2_skyworkstulufull__1__1743800713/e492c59d-4b03-4dce-983e-a8724de35a60.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llama_3e-6_2_skyworkstulufull__1__1743800713/e492c59d-4b03-4dce-983e-a8724de35a60.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llama_3e-6_2_skyworkstulufull__1__1743800713/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7209
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7116
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3875
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6612
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9067
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9172
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.7414
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llama_4e-6_1_skyworkstulufull__1__1743893911/53de0394-8516-4882-b2bc-c7e62e3d8ef0.json b/data/reward-bench/allenai/open_instruct_dev-rm_llama_4e-6_1_skyworkstulufull__1__1743893911/53de0394-8516-4882-b2bc-c7e62e3d8ef0.json
index 7a4cda11c..f774c416d 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llama_4e-6_1_skyworkstulufull__1__1743893911/53de0394-8516-4882-b2bc-c7e62e3d8ef0.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llama_4e-6_1_skyworkstulufull__1__1743893911/53de0394-8516-4882-b2bc-c7e62e3d8ef0.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llama_4e-6_1_skyworkstulufull__1__1743893911/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7266
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7347
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4313
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6339
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8933
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.897
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.7697
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llamabase_1e-6_1_skyworkstulufull__1__1745386412/56d4c1c5-5238-45dc-8331-64a14b830779.json b/data/reward-bench/allenai/open_instruct_dev-rm_llamabase_1e-6_1_skyworkstulufull__1__1745386412/56d4c1c5-5238-45dc-8331-64a14b830779.json
index d5a03d7e7..41b8b3c61 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llamabase_1e-6_1_skyworkstulufull__1__1745386412/56d4c1c5-5238-45dc-8331-64a14b830779.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llamabase_1e-6_1_skyworkstulufull__1__1745386412/56d4c1c5-5238-45dc-8331-64a14b830779.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llamabase_1e-6_1_skyworkstulufull__1__1745386412/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5342
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6042
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.275
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7222
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.5818
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.3935
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llamabase_1e-6_2_skyworkstulufull__1__1745441922/7003c9d4-c758-4373-a7a3-04822978bf35.json b/data/reward-bench/allenai/open_instruct_dev-rm_llamabase_1e-6_2_skyworkstulufull__1__1745441922/7003c9d4-c758-4373-a7a3-04822978bf35.json
index b721ec24f..19e1f2b82 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llamabase_1e-6_2_skyworkstulufull__1__1745441922/7003c9d4-c758-4373-a7a3-04822978bf35.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llamabase_1e-6_2_skyworkstulufull__1__1745441922/7003c9d4-c758-4373-a7a3-04822978bf35.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llamabase_1e-6_2_skyworkstulufull__1__1745441922/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6111
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6884
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3063
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.623
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8289
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7576
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4628
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llamabase_2e-5_1_skyworkstulufull__1__1745386495/75a7dcb6-789c-49de-b209-4cf7d27465e4.json b/data/reward-bench/allenai/open_instruct_dev-rm_llamabase_2e-5_1_skyworkstulufull__1__1745386495/75a7dcb6-789c-49de-b209-4cf7d27465e4.json
index 7349185f8..504f0108c 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llamabase_2e-5_1_skyworkstulufull__1__1745386495/75a7dcb6-789c-49de-b209-4cf7d27465e4.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llamabase_2e-5_1_skyworkstulufull__1__1745386495/75a7dcb6-789c-49de-b209-4cf7d27465e4.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llamabase_2e-5_1_skyworkstulufull__1__1745386495/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5825
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6379
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.325
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5355
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8222
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7051
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4691
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llamabase_2e-5_2_skyworkstulufull__1__1745386507/e91d3910-4f20-4e82-b1fb-8605f5d2b8ac.json b/data/reward-bench/allenai/open_instruct_dev-rm_llamabase_2e-5_2_skyworkstulufull__1__1745386507/e91d3910-4f20-4e82-b1fb-8605f5d2b8ac.json
index 8b98a2800..b50170dc8 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llamabase_2e-5_2_skyworkstulufull__1__1745386507/e91d3910-4f20-4e82-b1fb-8605f5d2b8ac.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llamabase_2e-5_2_skyworkstulufull__1__1745386507/e91d3910-4f20-4e82-b1fb-8605f5d2b8ac.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llamabase_2e-5_2_skyworkstulufull__1__1745386507/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5598
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5495
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3563
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5902
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.76
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7273
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.3754
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_llamabase_3e-6_1_skyworkstulufull__1__1745386507/f18bfd44-3097-4eb8-a09c-2372c3ecd738.json b/data/reward-bench/allenai/open_instruct_dev-rm_llamabase_3e-6_1_skyworkstulufull__1__1745386507/f18bfd44-3097-4eb8-a09c-2372c3ecd738.json
index 32bdafd8d..2ce4a6752 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_llamabase_3e-6_1_skyworkstulufull__1__1745386507/f18bfd44-3097-4eb8-a09c-2372c3ecd738.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_llamabase_3e-6_1_skyworkstulufull__1__1745386507/f18bfd44-3097-4eb8-a09c-2372c3ecd738.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_llamabase_3e-6_1_skyworkstulufull__1__1745386507/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6101
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6632
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.35
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6175
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7778
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7111
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5408
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_qwen32b_1e-6_skyworkstulufull__8__1748235917/9ca974b9-c5fb-4fc4-ab3e-1246e31ecdb2.json b/data/reward-bench/allenai/open_instruct_dev-rm_qwen32b_1e-6_skyworkstulufull__8__1748235917/9ca974b9-c5fb-4fc4-ab3e-1246e31ecdb2.json
index 308f6d0b2..aef503803 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_qwen32b_1e-6_skyworkstulufull__8__1748235917/9ca974b9-c5fb-4fc4-ab3e-1246e31ecdb2.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_qwen32b_1e-6_skyworkstulufull__8__1748235917/9ca974b9-c5fb-4fc4-ab3e-1246e31ecdb2.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_qwen32b_1e-6_skyworkstulufull__8__1748235917/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7185
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7305
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4125
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7158
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7933
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8545
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.804
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_qwen32b_3e-6_skyworkstulufull__8__1748288961/fb1ab5e0-18db-4e5f-add3-2352d9a1f260.json b/data/reward-bench/allenai/open_instruct_dev-rm_qwen32b_3e-6_skyworkstulufull__8__1748288961/fb1ab5e0-18db-4e5f-add3-2352d9a1f260.json
index a7319cf44..3c5aab68c 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_qwen32b_3e-6_skyworkstulufull__8__1748288961/fb1ab5e0-18db-4e5f-add3-2352d9a1f260.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_qwen32b_3e-6_skyworkstulufull__8__1748288961/fb1ab5e0-18db-4e5f-add3-2352d9a1f260.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_qwen32b_3e-6_skyworkstulufull__8__1748288961/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7325
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7474
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4437
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7158
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7978
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8141
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.8763
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_qwen_1e-6_1_skyworks__1__1744062830/60ba1f0d-7e85-49e4-8c73-330d74de6707.json b/data/reward-bench/allenai/open_instruct_dev-rm_qwen_1e-6_1_skyworks__1__1744062830/60ba1f0d-7e85-49e4-8c73-330d74de6707.json
index 03156b7ff..4f30313c2 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_qwen_1e-6_1_skyworks__1__1744062830/60ba1f0d-7e85-49e4-8c73-330d74de6707.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_qwen_1e-6_1_skyworks__1__1744062830/60ba1f0d-7e85-49e4-8c73-330d74de6707.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_qwen_1e-6_1_skyworks__1__1744062830/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6022
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.325
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.694
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7556
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7616
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5486
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_qwen_1e-6_1_skyworks__2__1744576024/29d1c194-8b87-466c-8701-e0fcf267665c.json b/data/reward-bench/allenai/open_instruct_dev-rm_qwen_1e-6_1_skyworks__2__1744576024/29d1c194-8b87-466c-8701-e0fcf267665c.json
index 2acbfdf87..e82661177 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_qwen_1e-6_1_skyworks__2__1744576024/29d1c194-8b87-466c-8701-e0fcf267665c.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_qwen_1e-6_1_skyworks__2__1744576024/29d1c194-8b87-466c-8701-e0fcf267665c.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_qwen_1e-6_1_skyworks__2__1744576024/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5948
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5579
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.2875
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6776
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.72
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7394
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5863
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_qwen_1e-6_1_skyworkstulufull__1__1743712914/31e8f616-7b64-4d1a-b395-20bf8bb4629c.json b/data/reward-bench/allenai/open_instruct_dev-rm_qwen_1e-6_1_skyworkstulufull__1__1743712914/31e8f616-7b64-4d1a-b395-20bf8bb4629c.json
index 61118bf8f..0ba320e56 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_qwen_1e-6_1_skyworkstulufull__1__1743712914/31e8f616-7b64-4d1a-b395-20bf8bb4629c.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_qwen_1e-6_1_skyworkstulufull__1__1743712914/31e8f616-7b64-4d1a-b395-20bf8bb4629c.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_qwen_1e-6_1_skyworkstulufull__1__1743712914/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6492
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6084
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.35
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6776
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.76
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.699
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_qwen_2e-5_1_skyworkstulufull__1__1743713091/cc3f315d-3cea-47e4-83b4-b5045e778c5e.json b/data/reward-bench/allenai/open_instruct_dev-rm_qwen_2e-5_1_skyworkstulufull__1__1743713091/cc3f315d-3cea-47e4-83b4-b5045e778c5e.json
index f8d27de74..4d27acb60 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_qwen_2e-5_1_skyworkstulufull__1__1743713091/cc3f315d-3cea-47e4-83b4-b5045e778c5e.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_qwen_2e-5_1_skyworkstulufull__1__1743713091/cc3f315d-3cea-47e4-83b4-b5045e778c5e.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_qwen_2e-5_1_skyworkstulufull__1__1743713091/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6764
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7074
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6885
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8622
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.802
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6984
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_qwen_3e-6_1_skyworks__1__1744062829/5d20dbf8-bb14-46af-adcd-b7ba05f8352c.json b/data/reward-bench/allenai/open_instruct_dev-rm_qwen_3e-6_1_skyworks__1__1744062829/5d20dbf8-bb14-46af-adcd-b7ba05f8352c.json
index f7eccad79..68ba40d15 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_qwen_3e-6_1_skyworks__1__1744062829/5d20dbf8-bb14-46af-adcd-b7ba05f8352c.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_qwen_3e-6_1_skyworks__1__1744062829/5d20dbf8-bb14-46af-adcd-b7ba05f8352c.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_qwen_3e-6_1_skyworks__1__1744062829/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6408
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6337
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3063
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6831
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8467
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8222
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5529
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_qwen_3e-6_1_skyworks__2__1744576050/06f2cb33-3937-4fde-84e2-6b5467f051c6.json b/data/reward-bench/allenai/open_instruct_dev-rm_qwen_3e-6_1_skyworks__2__1744576050/06f2cb33-3937-4fde-84e2-6b5467f051c6.json
index 54dfa9a73..69c6a7c36 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_qwen_3e-6_1_skyworks__2__1744576050/06f2cb33-3937-4fde-84e2-6b5467f051c6.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_qwen_3e-6_1_skyworks__2__1744576050/06f2cb33-3937-4fde-84e2-6b5467f051c6.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_qwen_3e-6_1_skyworks__2__1744576050/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6452
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6063
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3187
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7158
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8356
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8343
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5603
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_qwen_3e-6_1_skyworkstulufull__1__1743712916/f35c4efa-3767-4a0e-8769-06230cda2512.json b/data/reward-bench/allenai/open_instruct_dev-rm_qwen_3e-6_1_skyworkstulufull__1__1743712916/f35c4efa-3767-4a0e-8769-06230cda2512.json
index 3fd04e107..3817a0a83 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_qwen_3e-6_1_skyworkstulufull__1__1743712916/f35c4efa-3767-4a0e-8769-06230cda2512.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_qwen_3e-6_1_skyworkstulufull__1__1743712916/f35c4efa-3767-4a0e-8769-06230cda2512.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_qwen_3e-6_1_skyworkstulufull__1__1743712916/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7013
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7263
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3438
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6995
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8222
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8444
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.7714
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_qwen_3e-6_2__1__1743023576/6cb65d6a-6c46-4991-8154-f28b101954f6.json b/data/reward-bench/allenai/open_instruct_dev-rm_qwen_3e-6_2__1__1743023576/6cb65d6a-6c46-4991-8154-f28b101954f6.json
index 958f44c2b..05ff3f527 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_qwen_3e-6_2__1__1743023576/6cb65d6a-6c46-4991-8154-f28b101954f6.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_qwen_3e-6_2__1__1743023576/6cb65d6a-6c46-4991-8154-f28b101954f6.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_qwen_3e-6_2__1__1743023576/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6369
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6905
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3187
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6448
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7844
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7596
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6236
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_qwen_3e-6_3__1__1743023619/6e15a49b-7dc4-4d69-965e-cb962c084e4a.json b/data/reward-bench/allenai/open_instruct_dev-rm_qwen_3e-6_3__1__1743023619/6e15a49b-7dc4-4d69-965e-cb962c084e4a.json
index 7b5c77287..2295c0011 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_qwen_3e-6_3__1__1743023619/6e15a49b-7dc4-4d69-965e-cb962c084e4a.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_qwen_3e-6_3__1__1743023619/6e15a49b-7dc4-4d69-965e-cb962c084e4a.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_qwen_3e-6_3__1__1743023619/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6221
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6674
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.325
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.612
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7978
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7455
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5852
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_1e-6_1_skyworkstulufull__1__1745388583/9f5591f4-751d-48d3-a348-4bb59f6bb1a3.json b/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_1e-6_1_skyworkstulufull__1__1745388583/9f5591f4-751d-48d3-a348-4bb59f6bb1a3.json
index b67cb4765..afd3a2b0e 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_1e-6_1_skyworkstulufull__1__1745388583/9f5591f4-751d-48d3-a348-4bb59f6bb1a3.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_1e-6_1_skyworkstulufull__1__1745388583/9f5591f4-751d-48d3-a348-4bb59f6bb1a3.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_qwenbase_1e-6_1_skyworkstulufull__1__1745388583/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5735
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5895
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.2625
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6448
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6889
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6727
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5823
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_1e-6_2_skyworkstulufull__1__1745388604/b609c002-fa0a-46a8-b5a1-9213ee89606c.json b/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_1e-6_2_skyworkstulufull__1__1745388604/b609c002-fa0a-46a8-b5a1-9213ee89606c.json
index 93b0e4d7c..ce70a17a6 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_1e-6_2_skyworkstulufull__1__1745388604/b609c002-fa0a-46a8-b5a1-9213ee89606c.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_1e-6_2_skyworkstulufull__1__1745388604/b609c002-fa0a-46a8-b5a1-9213ee89606c.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_qwenbase_1e-6_2_skyworkstulufull__1__1745388604/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6336
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6337
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3063
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6885
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7244
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.802
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6465
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_2e-5_1_skyworkstulufull__1__1745388738/b147fc7f-0e31-49ca-abfd-ba990a925097.json b/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_2e-5_1_skyworkstulufull__1__1745388738/b147fc7f-0e31-49ca-abfd-ba990a925097.json
index 303899a02..23d89ab11 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_2e-5_1_skyworkstulufull__1__1745388738/b147fc7f-0e31-49ca-abfd-ba990a925097.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_2e-5_1_skyworkstulufull__1__1745388738/b147fc7f-0e31-49ca-abfd-ba990a925097.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_qwenbase_2e-5_1_skyworkstulufull__1__1745388738/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6824
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6989
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3625
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6831
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8311
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8081
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.7107
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_2e-5_2_skyworkstulufull__1__1745388191/e4fbfe23-2b70-459e-821b-db0116d43d8c.json b/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_2e-5_2_skyworkstulufull__1__1745388191/e4fbfe23-2b70-459e-821b-db0116d43d8c.json
index de6749902..b6f1f989c 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_2e-5_2_skyworkstulufull__1__1745388191/e4fbfe23-2b70-459e-821b-db0116d43d8c.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_2e-5_2_skyworkstulufull__1__1745388191/e4fbfe23-2b70-459e-821b-db0116d43d8c.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_qwenbase_2e-5_2_skyworkstulufull__1__1745388191/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6392
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6589
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3312
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6995
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7933
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7717
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5804
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_3e-6_1_skyworkstulufull__1__1745388737/2ab7dc14-af3e-4fb2-8c0c-fe0e14100321.json b/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_3e-6_1_skyworkstulufull__1__1745388737/2ab7dc14-af3e-4fb2-8c0c-fe0e14100321.json
index 00bf97d41..9f16f2dae 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_3e-6_1_skyworkstulufull__1__1745388737/2ab7dc14-af3e-4fb2-8c0c-fe0e14100321.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_3e-6_1_skyworkstulufull__1__1745388737/2ab7dc14-af3e-4fb2-8c0c-fe0e14100321.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_qwenbase_3e-6_1_skyworkstulufull__1__1745388737/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.664
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6821
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3312
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6448
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8133
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8061
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.7066
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_3e-6_2_skyworkstulufull__1__1745388138/aca2c665-79f2-4226-b806-307be277ed08.json b/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_3e-6_2_skyworkstulufull__1__1745388138/aca2c665-79f2-4226-b806-307be277ed08.json
index 24ccc05c6..d9c996fb0 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_3e-6_2_skyworkstulufull__1__1745388138/aca2c665-79f2-4226-b806-307be277ed08.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_qwenbase_3e-6_2_skyworkstulufull__1__1745388138/aca2c665-79f2-4226-b806-307be277ed08.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_qwenbase_3e-6_2_skyworkstulufull__1__1745388138/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6678
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6505
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3312
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6831
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7978
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8808
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6632
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_tulu3_70b_1__8__1742924455/d37a63df-6d38-4083-bf87-11064162efde.json b/data/reward-bench/allenai/open_instruct_dev-rm_tulu3_70b_1__8__1742924455/d37a63df-6d38-4083-bf87-11064162efde.json
index 27cd1cbd9..61f3caac6 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_tulu3_70b_1__8__1742924455/d37a63df-6d38-4083-bf87-11064162efde.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_tulu3_70b_1__8__1742924455/d37a63df-6d38-4083-bf87-11064162efde.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_tulu3_70b_1__8__1742924455/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6618
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7958
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.325
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6557
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8311
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6323
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.7311
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/open_instruct_dev-rm_tulu3_70b_2__8__1742982964/16e550cc-e59d-4aaa-b221-8cf71e1b26d2.json b/data/reward-bench/allenai/open_instruct_dev-rm_tulu3_70b_2__8__1742982964/16e550cc-e59d-4aaa-b221-8cf71e1b26d2.json
index d97c5ebcc..2b5278d3d 100644
--- a/data/reward-bench/allenai/open_instruct_dev-rm_tulu3_70b_2__8__1742982964/16e550cc-e59d-4aaa-b221-8cf71e1b26d2.json
+++ b/data/reward-bench/allenai/open_instruct_dev-rm_tulu3_70b_2__8__1742982964/16e550cc-e59d-4aaa-b221-8cf71e1b26d2.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/allenai_open_instruct_dev-rm_tulu3_70b_2__8__1742982964/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6605
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7789
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3688
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6448
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8844
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6667
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6195
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/tulu-2-dpo-13b/47058e2a-dc41-45f8-8c32-bc496a8d3bc5.json b/data/reward-bench/allenai/tulu-2-dpo-13b/47058e2a-dc41-45f8-8c32-bc496a8d3bc5.json
index f588b1e6b..16dc6eef6 100644
--- a/data/reward-bench/allenai/tulu-2-dpo-13b/47058e2a-dc41-45f8-8c32-bc496a8d3bc5.json
+++ b/data/reward-bench/allenai/tulu-2-dpo-13b/47058e2a-dc41-45f8-8c32-bc496a8d3bc5.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/allenai_tulu-2-dpo-13b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7368
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9581
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5833
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7946
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7323
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.4947
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/tulu-2-dpo-70b/7199c8b3-8346-4200-b07e-4362ad13a7db.json b/data/reward-bench/allenai/tulu-2-dpo-70b/7199c8b3-8346-4200-b07e-4362ad13a7db.json
index 8c042ac24..d68ff3ff8 100644
--- a/data/reward-bench/allenai/tulu-2-dpo-70b/7199c8b3-8346-4200-b07e-4362ad13a7db.json
+++ b/data/reward-bench/allenai/tulu-2-dpo-70b/7199c8b3-8346-4200-b07e-4362ad13a7db.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/allenai_tulu-2-dpo-70b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7621
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9749
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6053
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8446
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7407
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5278
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/tulu-2-dpo-7b/de7e59d5-e2ce-4479-bbd9-ab9deb3beed3.json b/data/reward-bench/allenai/tulu-2-dpo-7b/de7e59d5-e2ce-4479-bbd9-ab9deb3beed3.json
index 04b1542bf..bef43cd19 100644
--- a/data/reward-bench/allenai/tulu-2-dpo-7b/de7e59d5-e2ce-4479-bbd9-ab9deb3beed3.json
+++ b/data/reward-bench/allenai/tulu-2-dpo-7b/de7e59d5-e2ce-4479-bbd9-ab9deb3beed3.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/allenai_tulu-2-dpo-7b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7212
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9749
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5614
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7527
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7176
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.4774
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/tulu-v2.5-13b-preference-mix-rm/17e011c3-1a53-40ae-b7b4-cb24c23df3de.json b/data/reward-bench/allenai/tulu-v2.5-13b-preference-mix-rm/17e011c3-1a53-40ae-b7b4-cb24c23df3de.json
index f43f7de4d..15c29fb58 100644
--- a/data/reward-bench/allenai/tulu-v2.5-13b-preference-mix-rm/17e011c3-1a53-40ae-b7b4-cb24c23df3de.json
+++ b/data/reward-bench/allenai/tulu-v2.5-13b-preference-mix-rm/17e011c3-1a53-40ae-b7b4-cb24c23df3de.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/allenai_tulu-v2.5-13b-preference-mix-rm/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8027
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9358
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.682
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.773
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.885
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6724
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/tulu-v2.5-13b-uf-rm/1125dd05-2f0d-48ca-825c-f5efa18564aa.json b/data/reward-bench/allenai/tulu-v2.5-13b-uf-rm/1125dd05-2f0d-48ca-825c-f5efa18564aa.json
index 0c9d35f42..817d26686 100644
--- a/data/reward-bench/allenai/tulu-v2.5-13b-uf-rm/1125dd05-2f0d-48ca-825c-f5efa18564aa.json
+++ b/data/reward-bench/allenai/tulu-v2.5-13b-uf-rm/1125dd05-2f0d-48ca-825c-f5efa18564aa.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/allenai_tulu-v2.5-13b-uf-rm/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.4806
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.3939
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4232
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5554
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.4737
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6326
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/tulu-v2.5-70b-preference-mix-rm/88014e0d-e89b-4fed-9eb6-5276bd7658df.json b/data/reward-bench/allenai/tulu-v2.5-70b-preference-mix-rm/88014e0d-e89b-4fed-9eb6-5276bd7658df.json
index 13869a984..9fc720998 100644
--- a/data/reward-bench/allenai/tulu-v2.5-70b-preference-mix-rm/88014e0d-e89b-4fed-9eb6-5276bd7658df.json
+++ b/data/reward-bench/allenai/tulu-v2.5-70b-preference-mix-rm/88014e0d-e89b-4fed-9eb6-5276bd7658df.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/allenai_tulu-v2.5-70b-preference-mix-rm/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6516
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7737
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5921
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8486
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.4138
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6079
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/allenai/tulu-v2.5-70b-uf-rm/7cc9bfc2-570d-456c-918f-68fd4b711f05.json b/data/reward-bench/allenai/tulu-v2.5-70b-uf-rm/7cc9bfc2-570d-456c-918f-68fd4b711f05.json
index 2b34c68aa..b30d36361 100644
--- a/data/reward-bench/allenai/tulu-v2.5-70b-uf-rm/7cc9bfc2-570d-456c-918f-68fd4b711f05.json
+++ b/data/reward-bench/allenai/tulu-v2.5-70b-uf-rm/7cc9bfc2-570d-456c-918f-68fd4b711f05.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/allenai_tulu-v2.5-70b-uf-rm/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7398
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8659
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7171
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7014
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.757
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5757
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/berkeley-nest/Starling-RM-7B-alpha/77b0957f-8779-4dbe-a6ea-cff50c4ee73b.json b/data/reward-bench/berkeley-nest/Starling-RM-7B-alpha/77b0957f-8779-4dbe-a6ea-cff50c4ee73b.json
index a31abcbec..66d40e95d 100644
--- a/data/reward-bench/berkeley-nest/Starling-RM-7B-alpha/77b0957f-8779-4dbe-a6ea-cff50c4ee73b.json
+++ b/data/reward-bench/berkeley-nest/Starling-RM-7B-alpha/77b0957f-8779-4dbe-a6ea-cff50c4ee73b.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/berkeley-nest_Starling-RM-7B-alpha/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7113
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9804
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4561
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8446
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.58
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6794
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/facebook/Self-taught-Llama-3-70B/ba0ce7ce-a755-4337-bfec-0391680d3625.json b/data/reward-bench/facebook/Self-taught-Llama-3-70B/ba0ce7ce-a755-4337-bfec-0391680d3625.json
index 4bd82d8a1..96835a8ce 100644
--- a/data/reward-bench/facebook/Self-taught-Llama-3-70B/ba0ce7ce-a755-4337-bfec-0391680d3625.json
+++ b/data/reward-bench/facebook/Self-taught-Llama-3-70B/ba0ce7ce-a755-4337-bfec-0391680d3625.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/facebook_Self-taught-Llama-3-70B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8863
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9693
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8399
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9108
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.8251
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/facebook/Self-taught-evaluator-llama3.1-70B/4eb460eb-b3ad-4e0d-b131-5b59ef54015c.json b/data/reward-bench/facebook/Self-taught-evaluator-llama3.1-70B/4eb460eb-b3ad-4e0d-b131-5b59ef54015c.json
index 9dd3e9229..a0b337292 100644
--- a/data/reward-bench/facebook/Self-taught-evaluator-llama3.1-70B/4eb460eb-b3ad-4e0d-b131-5b59ef54015c.json
+++ b/data/reward-bench/facebook/Self-taught-evaluator-llama3.1-70B/4eb460eb-b3ad-4e0d-b131-5b59ef54015c.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/facebook_Self-taught-evaluator-llama3.1-70B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9001
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9693
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8509
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8959
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.8844
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/general-preference/GPM-Gemma-2B/6868a1e5-ee86-4f89-8452-5e939ac19169.json b/data/reward-bench/general-preference/GPM-Gemma-2B/6868a1e5-ee86-4f89-8452-5e939ac19169.json
index c1f8c90fa..30c26da89 100644
--- a/data/reward-bench/general-preference/GPM-Gemma-2B/6868a1e5-ee86-4f89-8452-5e939ac19169.json
+++ b/data/reward-bench/general-preference/GPM-Gemma-2B/6868a1e5-ee86-4f89-8452-5e939ac19169.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/general-preference_GPM-Gemma-2B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7449
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7151
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6974
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8122
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.755
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/general-preference/GPM-Llama-3.1-8B/4a151d43-5fac-4afe-9c23-ba0e86a60849.json b/data/reward-bench/general-preference/GPM-Llama-3.1-8B/4a151d43-5fac-4afe-9c23-ba0e86a60849.json
index ec4043ed2..d66a7ae70 100644
--- a/data/reward-bench/general-preference/GPM-Llama-3.1-8B/4a151d43-5fac-4afe-9c23-ba0e86a60849.json
+++ b/data/reward-bench/general-preference/GPM-Llama-3.1-8B/4a151d43-5fac-4afe-9c23-ba0e86a60849.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/general-preference_GPM-Llama-3.1-8B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9224
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.933
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.886
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9108
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9597
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/google/flame-1.0-24B-july-2024/5f16d574-adef-4016-abcf-9e7936771ba7.json b/data/reward-bench/google/flame-1.0-24B-july-2024/5f16d574-adef-4016-abcf-9e7936771ba7.json
index debba95cf..4f1439052 100644
--- a/data/reward-bench/google/flame-1.0-24B-july-2024/5f16d574-adef-4016-abcf-9e7936771ba7.json
+++ b/data/reward-bench/google/flame-1.0-24B-july-2024/5f16d574-adef-4016-abcf-9e7936771ba7.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/google_flame-1.0-24B-july-2024/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8781
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9218
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7566
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8959
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.938
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/google/gemini-1.5-flash-001/f3e0300f-39ed-4cfd-bd03-218904836037.json b/data/reward-bench/google/gemini-1.5-flash-001/f3e0300f-39ed-4cfd-bd03-218904836037.json
index 47953379d..0c59d6494 100644
--- a/data/reward-bench/google/gemini-1.5-flash-001/f3e0300f-39ed-4cfd-bd03-218904836037.json
+++ b/data/reward-bench/google/gemini-1.5-flash-001/f3e0300f-39ed-4cfd-bd03-218904836037.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/google_gemini-1.5-flash-001/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8054
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9218
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6349
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8696
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8512
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6937
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/google/gemini-1.5-flash-8b/42c82c00-b74e-4152-a222-15d481a13e0c.json b/data/reward-bench/google/gemini-1.5-flash-8b/42c82c00-b74e-4152-a222-15d481a13e0c.json
index d3c96b98e..11fe9a9c7 100644
--- a/data/reward-bench/google/gemini-1.5-flash-8b/42c82c00-b74e-4152-a222-15d481a13e0c.json
+++ b/data/reward-bench/google/gemini-1.5-flash-8b/42c82c00-b74e-4152-a222-15d481a13e0c.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/google_gemini-1.5-flash-8b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.4851
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.4611
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3625
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5082
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6622
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6747
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.2421
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/google/gemini-1.5-pro-0514/68096be8-c49f-4a23-824e-1275248369f7.json b/data/reward-bench/google/gemini-1.5-pro-0514/68096be8-c49f-4a23-824e-1275248369f7.json
index ebd01fc22..1faa0442f 100644
--- a/data/reward-bench/google/gemini-1.5-pro-0514/68096be8-c49f-4a23-824e-1275248369f7.json
+++ b/data/reward-bench/google/gemini-1.5-pro-0514/68096be8-c49f-4a23-824e-1275248369f7.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/google_gemini-1.5-pro-0514/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.882
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9232
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8059
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8791
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9199
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/google/gemini-1.5-pro-0924/c91270bd-3731-452a-b429-6cd4943d1194.json b/data/reward-bench/google/gemini-1.5-pro-0924/c91270bd-3731-452a-b429-6cd4943d1194.json
index d0d312a19..2eb44d882 100644
--- a/data/reward-bench/google/gemini-1.5-pro-0924/c91270bd-3731-452a-b429-6cd4943d1194.json
+++ b/data/reward-bench/google/gemini-1.5-pro-0924/c91270bd-3731-452a-b429-6cd4943d1194.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/google_gemini-1.5-pro-0924/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8678
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9413
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7697
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8581
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9022
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/google/gemini-2.5-flash-preview-04-17/337c7a43-46a7-4acb-b7f1-936e1f2cf46f.json b/data/reward-bench/google/gemini-2.5-flash-preview-04-17/337c7a43-46a7-4acb-b7f1-936e1f2cf46f.json
index a742b1b32..8abf7e861 100644
--- a/data/reward-bench/google/gemini-2.5-flash-preview-04-17/337c7a43-46a7-4acb-b7f1-936e1f2cf46f.json
+++ b/data/reward-bench/google/gemini-2.5-flash-preview-04-17/337c7a43-46a7-4acb-b7f1-936e1f2cf46f.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/google_gemini-2.5-flash-preview-04-17/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7721
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6574
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5531
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8115
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9094
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8672
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.8341
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/google/gemini-2.5-flash/3b00f881-8f73-4608-8cbb-846fe7d1cfea.json b/data/reward-bench/google/gemini-2.5-flash/3b00f881-8f73-4608-8cbb-846fe7d1cfea.json
index 6446b47a9..5a4a0577c 100644
--- a/data/reward-bench/google/gemini-2.5-flash/3b00f881-8f73-4608-8cbb-846fe7d1cfea.json
+++ b/data/reward-bench/google/gemini-2.5-flash/3b00f881-8f73-4608-8cbb-846fe7d1cfea.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/google_gemini-2.5-flash/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7767
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.674
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.575
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.852
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.909
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.841
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.809
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/google/gemini-2.5-pro-preview-05-06/2821dfdc-291b-405e-bd81-cf536c802885.json b/data/reward-bench/google/gemini-2.5-pro-preview-05-06/2821dfdc-291b-405e-bd81-cf536c802885.json
index e1e5d510c..a4d4ee1dd 100644
--- a/data/reward-bench/google/gemini-2.5-pro-preview-05-06/2821dfdc-291b-405e-bd81-cf536c802885.json
+++ b/data/reward-bench/google/gemini-2.5-pro-preview-05-06/2821dfdc-291b-405e-bd81-cf536c802885.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/google_gemini-2.5-pro-preview-05-06/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6775
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6532
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4688
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5342
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8806
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8308
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6973
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/google/gemini-2.5-pro/7d441240-7e85-4776-b51c-3c1bc84456ba.json b/data/reward-bench/google/gemini-2.5-pro/7d441240-7e85-4776-b51c-3c1bc84456ba.json
index a31100099..f67d63bbb 100644
--- a/data/reward-bench/google/gemini-2.5-pro/7d441240-7e85-4776-b51c-3c1bc84456ba.json
+++ b/data/reward-bench/google/gemini-2.5-pro/7d441240-7e85-4776-b51c-3c1bc84456ba.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/google_gemini-2.5-pro/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7948
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.755
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.619
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.898
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.881
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.805
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.811
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/google/gemma-2-27b-it/840d35d9-441e-4ba3-bbc3-1f4ff2627517.json b/data/reward-bench/google/gemma-2-27b-it/840d35d9-441e-4ba3-bbc3-1f4ff2627517.json
index 20d232e8c..5bc50f14c 100644
--- a/data/reward-bench/google/gemma-2-27b-it/840d35d9-441e-4ba3-bbc3-1f4ff2627517.json
+++ b/data/reward-bench/google/gemma-2-27b-it/840d35d9-441e-4ba3-bbc3-1f4ff2627517.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/google_gemma-2-27b-it/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.809
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9483
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.591
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8635
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.833
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/hendrydong/Mistral-RM-for-RAFT-GSHF-v0/0127f3c5-9657-4eb6-a77a-5a6476a8fc79.json b/data/reward-bench/hendrydong/Mistral-RM-for-RAFT-GSHF-v0/0127f3c5-9657-4eb6-a77a-5a6476a8fc79.json
index 8909aa067..b2d697ddd 100644
--- a/data/reward-bench/hendrydong/Mistral-RM-for-RAFT-GSHF-v0/0127f3c5-9657-4eb6-a77a-5a6476a8fc79.json
+++ b/data/reward-bench/hendrydong/Mistral-RM-for-RAFT-GSHF-v0/0127f3c5-9657-4eb6-a77a-5a6476a8fc79.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/hendrydong_Mistral-RM-for-RAFT-GSHF-v0/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7847
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9832
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5789
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.85
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7434
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.7508
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/hendrydong/Mistral-RM-for-RAFT-GSHF-v0/b72e2988-75e4-4d26-9a47-daae4786b02f.json b/data/reward-bench/hendrydong/Mistral-RM-for-RAFT-GSHF-v0/b72e2988-75e4-4d26-9a47-daae4786b02f.json
index 9d40f5e06..53579af56 100644
--- a/data/reward-bench/hendrydong/Mistral-RM-for-RAFT-GSHF-v0/b72e2988-75e4-4d26-9a47-daae4786b02f.json
+++ b/data/reward-bench/hendrydong/Mistral-RM-for-RAFT-GSHF-v0/b72e2988-75e4-4d26-9a47-daae4786b02f.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/hendrydong_Mistral-RM-for-RAFT-GSHF-v0/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5851
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5779
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3625
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6011
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6956
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6747
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5988
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/infly/INF-ORM-Llama3.1-70B/643cf5a3-8992-4126-87c9-814887314266.json b/data/reward-bench/infly/INF-ORM-Llama3.1-70B/643cf5a3-8992-4126-87c9-814887314266.json
index b55666165..4bce79497 100644
--- a/data/reward-bench/infly/INF-ORM-Llama3.1-70B/643cf5a3-8992-4126-87c9-814887314266.json
+++ b/data/reward-bench/infly/INF-ORM-Llama3.1-70B/643cf5a3-8992-4126-87c9-814887314266.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/infly_INF-ORM-Llama3.1-70B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7648
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7411
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4188
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6995
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9644
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.903
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.8622
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/infly/INF-ORM-Llama3.1-70B/f81f1f67-6506-481f-87ce-a17a6a7578f3.json b/data/reward-bench/infly/INF-ORM-Llama3.1-70B/f81f1f67-6506-481f-87ce-a17a6a7578f3.json
index f1498d55c..d0e17fefb 100644
--- a/data/reward-bench/infly/INF-ORM-Llama3.1-70B/f81f1f67-6506-481f-87ce-a17a6a7578f3.json
+++ b/data/reward-bench/infly/INF-ORM-Llama3.1-70B/f81f1f67-6506-481f-87ce-a17a6a7578f3.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/infly_INF-ORM-Llama3.1-70B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9511
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9665
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.9101
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9365
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9912
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/internlm/internlm2-1_8b-reward/32b35218-a099-410e-8a65-a0d6e2f380a6.json b/data/reward-bench/internlm/internlm2-1_8b-reward/32b35218-a099-410e-8a65-a0d6e2f380a6.json
index ca734a8e5..009a9841f 100644
--- a/data/reward-bench/internlm/internlm2-1_8b-reward/32b35218-a099-410e-8a65-a0d6e2f380a6.json
+++ b/data/reward-bench/internlm/internlm2-1_8b-reward/32b35218-a099-410e-8a65-a0d6e2f380a6.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/internlm_internlm2-1_8b-reward/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.3902
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.2758
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3625
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.4426
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.4711
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.596
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.1934
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/internlm/internlm2-1_8b-reward/deec1e7c-0cb8-4e6f-b3ac-d37790b709f3.json b/data/reward-bench/internlm/internlm2-1_8b-reward/deec1e7c-0cb8-4e6f-b3ac-d37790b709f3.json
index a8db9512e..c3fbd28d8 100644
--- a/data/reward-bench/internlm/internlm2-1_8b-reward/deec1e7c-0cb8-4e6f-b3ac-d37790b709f3.json
+++ b/data/reward-bench/internlm/internlm2-1_8b-reward/deec1e7c-0cb8-4e6f-b3ac-d37790b709f3.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/internlm_internlm2-1_8b-reward/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8217
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9358
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6623
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8162
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.8724
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/internlm/internlm2-20b-reward/e42a9986-4dcc-4017-be97-8135646c7424.json b/data/reward-bench/internlm/internlm2-20b-reward/e42a9986-4dcc-4017-be97-8135646c7424.json
index 7c100da57..332851441 100644
--- a/data/reward-bench/internlm/internlm2-20b-reward/e42a9986-4dcc-4017-be97-8135646c7424.json
+++ b/data/reward-bench/internlm/internlm2-20b-reward/e42a9986-4dcc-4017-be97-8135646c7424.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/internlm_internlm2-20b-reward/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9016
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9888
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7654
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8946
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9576
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/internlm/internlm2-20b-reward/ffc92063-606a-4f31-bfdd-5683aa748ccc.json b/data/reward-bench/internlm/internlm2-20b-reward/ffc92063-606a-4f31-bfdd-5683aa748ccc.json
index be1a99b56..ceaeec27a 100644
--- a/data/reward-bench/internlm/internlm2-20b-reward/ffc92063-606a-4f31-bfdd-5683aa748ccc.json
+++ b/data/reward-bench/internlm/internlm2-20b-reward/ffc92063-606a-4f31-bfdd-5683aa748ccc.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/internlm_internlm2-20b-reward/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5628
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5558
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3625
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5738
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6111
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7253
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5483
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/internlm/internlm2-7b-reward/23a5398c-0911-4a66-930d-abada12bf985.json b/data/reward-bench/internlm/internlm2-7b-reward/23a5398c-0911-4a66-930d-abada12bf985.json
index 9bfc27874..3c136cd53 100644
--- a/data/reward-bench/internlm/internlm2-7b-reward/23a5398c-0911-4a66-930d-abada12bf985.json
+++ b/data/reward-bench/internlm/internlm2-7b-reward/23a5398c-0911-4a66-930d-abada12bf985.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/internlm_internlm2-7b-reward/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5335
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.4211
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5628
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.5956
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7051
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5164
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/internlm/internlm2-7b-reward/80b0bbcb-a57a-453c-8fff-502646520b1d.json b/data/reward-bench/internlm/internlm2-7b-reward/80b0bbcb-a57a-453c-8fff-502646520b1d.json
index 36efccc5e..2273cb29a 100644
--- a/data/reward-bench/internlm/internlm2-7b-reward/80b0bbcb-a57a-453c-8fff-502646520b1d.json
+++ b/data/reward-bench/internlm/internlm2-7b-reward/80b0bbcb-a57a-453c-8fff-502646520b1d.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/internlm_internlm2-7b-reward/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8759
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9916
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6952
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8716
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9453
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/jondurbin/bagel-dpo-34b-v0.5/e383c939-b952-4fdd-94e3-eb3716691860.json b/data/reward-bench/jondurbin/bagel-dpo-34b-v0.5/e383c939-b952-4fdd-94e3-eb3716691860.json
index 6343b6db0..090fb16d8 100644
--- a/data/reward-bench/jondurbin/bagel-dpo-34b-v0.5/e383c939-b952-4fdd-94e3-eb3716691860.json
+++ b/data/reward-bench/jondurbin/bagel-dpo-34b-v0.5/e383c939-b952-4fdd-94e3-eb3716691860.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/jondurbin_bagel-dpo-34b-v0.5/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7215
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9385
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5504
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6446
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8889
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.4487
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/llm-blender/PairRM-hf/daf873f9-ab03-49df-96cb-a0f5a8613048.json b/data/reward-bench/llm-blender/PairRM-hf/daf873f9-ab03-49df-96cb-a0f5a8613048.json
index d9c5f6c62..ed400926f 100644
--- a/data/reward-bench/llm-blender/PairRM-hf/daf873f9-ab03-49df-96cb-a0f5a8613048.json
+++ b/data/reward-bench/llm-blender/PairRM-hf/daf873f9-ab03-49df-96cb-a0f5a8613048.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/llm-blender_PairRM-hf/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6087
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9022
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5219
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.477
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.4898
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6961
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/mattshumer/Reflection-70B/f4cff132-3b2f-4e03-bb49-098b16d87cef.json b/data/reward-bench/mattshumer/Reflection-70B/f4cff132-3b2f-4e03-bb49-098b16d87cef.json
index c24b6696c..48058a174 100644
--- a/data/reward-bench/mattshumer/Reflection-70B/f4cff132-3b2f-4e03-bb49-098b16d87cef.json
+++ b/data/reward-bench/mattshumer/Reflection-70B/f4cff132-3b2f-4e03-bb49-098b16d87cef.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/mattshumer_Reflection-70B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8422
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9749
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7061
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8318
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.8562
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/meta-llama/Meta-Llama-3-70B-Instruct/f80685de-058c-4ab8-aa35-dc7321d1cea6.json b/data/reward-bench/meta-llama/Meta-Llama-3-70B-Instruct/f80685de-058c-4ab8-aa35-dc7321d1cea6.json
index d392ad9e8..d29586253 100644
--- a/data/reward-bench/meta-llama/Meta-Llama-3-70B-Instruct/f80685de-058c-4ab8-aa35-dc7321d1cea6.json
+++ b/data/reward-bench/meta-llama/Meta-Llama-3-70B-Instruct/f80685de-058c-4ab8-aa35-dc7321d1cea6.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/meta-llama_Meta-Llama-3-70B-Instruct/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7627
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9763
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5888
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7297
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7854
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.7035
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/meta-llama/Meta-Llama-3-8B-Instruct/c8e4349d-a084-4eb5-990f-403ba930a9ad.json b/data/reward-bench/meta-llama/Meta-Llama-3-8B-Instruct/c8e4349d-a084-4eb5-990f-403ba930a9ad.json
index 9fb252ef8..21b28918d 100644
--- a/data/reward-bench/meta-llama/Meta-Llama-3-8B-Instruct/c8e4349d-a084-4eb5-990f-403ba930a9ad.json
+++ b/data/reward-bench/meta-llama/Meta-Llama-3-8B-Instruct/c8e4349d-a084-4eb5-990f-403ba930a9ad.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/meta-llama_Meta-Llama-3-8B-Instruct/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.645
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8547
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4156
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6797
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6482
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6082
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo/729ca9c0-0680-49f1-97b9-5581be17a352.json b/data/reward-bench/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo/729ca9c0-0680-49f1-97b9-5581be17a352.json
index 0b144abbe..2f6cdcbbc 100644
--- a/data/reward-bench/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo/729ca9c0-0680-49f1-97b9-5581be17a352.json
+++ b/data/reward-bench/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo/729ca9c0-0680-49f1-97b9-5581be17a352.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/meta-llama_Meta-Llama-3.1-405B-Instruct-Turbo/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8412
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9721
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7456
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7757
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.8715
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo/fdd4add5-b44d-46f9-8c98-da3120df4161.json b/data/reward-bench/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo/fdd4add5-b44d-46f9-8c98-da3120df4161.json
index 3716eb41b..1181fd3d1 100644
--- a/data/reward-bench/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo/fdd4add5-b44d-46f9-8c98-da3120df4161.json
+++ b/data/reward-bench/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo/fdd4add5-b44d-46f9-8c98-da3120df4161.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/meta-llama_Meta-Llama-3.1-70B-Instruct-Turbo/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7808
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8757
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6689
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7507
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.828
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/meta-llama/Meta-Llama-3.1-70B-Instruct/6b5ef643-30dd-4381-b66f-e9ecd6b0d06e.json b/data/reward-bench/meta-llama/Meta-Llama-3.1-70B-Instruct/6b5ef643-30dd-4381-b66f-e9ecd6b0d06e.json
index 854546b01..2f41e3adc 100644
--- a/data/reward-bench/meta-llama/Meta-Llama-3.1-70B-Instruct/6b5ef643-30dd-4381-b66f-e9ecd6b0d06e.json
+++ b/data/reward-bench/meta-llama/Meta-Llama-3.1-70B-Instruct/6b5ef643-30dd-4381-b66f-e9ecd6b0d06e.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/meta-llama_Meta-Llama-3.1-70B-Instruct/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8405
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9721
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7018
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.8599
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo/95271b8c-4135-48bf-bbad-ae94baa37640.json b/data/reward-bench/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo/95271b8c-4135-48bf-bbad-ae94baa37640.json
index 30a79283f..47e395707 100644
--- a/data/reward-bench/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo/95271b8c-4135-48bf-bbad-ae94baa37640.json
+++ b/data/reward-bench/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo/95271b8c-4135-48bf-bbad-ae94baa37640.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/meta-llama_Meta-Llama-3.1-8B-Instruct-Turbo/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6565
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8073
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4978
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6399
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.6811
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/meta-metrics/MetaMetrics-RM-v1.0/f437e790-efe1-4dc5-8ccc-5b0bfd800069.json b/data/reward-bench/meta-metrics/MetaMetrics-RM-v1.0/f437e790-efe1-4dc5-8ccc-5b0bfd800069.json
index aa32c142b..5a185daab 100644
--- a/data/reward-bench/meta-metrics/MetaMetrics-RM-v1.0/f437e790-efe1-4dc5-8ccc-5b0bfd800069.json
+++ b/data/reward-bench/meta-metrics/MetaMetrics-RM-v1.0/f437e790-efe1-4dc5-8ccc-5b0bfd800069.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/meta-metrics_MetaMetrics-RM-v1.0/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9342
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9832
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.864
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9081
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9816
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/mightbe/Better-PairRM/7d0f761a-2650-4029-b1e9-13af2f0cc69d.json b/data/reward-bench/mightbe/Better-PairRM/7d0f761a-2650-4029-b1e9-13af2f0cc69d.json
index 01de5c6fa..46baee169 100644
--- a/data/reward-bench/mightbe/Better-PairRM/7d0f761a-2650-4029-b1e9-13af2f0cc69d.json
+++ b/data/reward-bench/mightbe/Better-PairRM/7d0f761a-2650-4029-b1e9-13af2f0cc69d.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/mightbe_Better-PairRM/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.673
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9553
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3925
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8203
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.4983
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.724
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/mistralai/Mixtral-8x7B-Instruct-v0.1/49fc601e-4ac6-4672-a53d-0e89f19959c1.json b/data/reward-bench/mistralai/Mixtral-8x7B-Instruct-v0.1/49fc601e-4ac6-4672-a53d-0e89f19959c1.json
index 078f1bc19..83daa1359 100644
--- a/data/reward-bench/mistralai/Mixtral-8x7B-Instruct-v0.1/49fc601e-4ac6-4672-a53d-0e89f19959c1.json
+++ b/data/reward-bench/mistralai/Mixtral-8x7B-Instruct-v0.1/49fc601e-4ac6-4672-a53d-0e89f19959c1.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/mistralai_Mixtral-8x7B-Instruct-v0.1/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7455
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9497
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6404
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7257
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7872
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5033
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/my_model/6195e81a-d5a5-40af-96f6-259252009ad7.json b/data/reward-bench/my_model/6195e81a-d5a5-40af-96f6-259252009ad7.json
index e482bb5fe..366e80763 100644
--- a/data/reward-bench/my_model/6195e81a-d5a5-40af-96f6-259252009ad7.json
+++ b/data/reward-bench/my_model/6195e81a-d5a5-40af-96f6-259252009ad7.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/my_model_/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5267
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.4553
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5592
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.4392
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.6532
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/nicolinho/QRM-Gemma-2-27B/2dec0f50-d374-4af3-9d27-80fcf50dac2c.json b/data/reward-bench/nicolinho/QRM-Gemma-2-27B/2dec0f50-d374-4af3-9d27-80fcf50dac2c.json
index 661fe8b53..e2fe3a9e8 100644
--- a/data/reward-bench/nicolinho/QRM-Gemma-2-27B/2dec0f50-d374-4af3-9d27-80fcf50dac2c.json
+++ b/data/reward-bench/nicolinho/QRM-Gemma-2-27B/2dec0f50-d374-4af3-9d27-80fcf50dac2c.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/nicolinho_QRM-Gemma-2-27B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7667
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.7853
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3719
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6995
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9578
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.9535
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.8321
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/nicolinho/QRM-Gemma-2-27B/96722888-0cc9-4dfd-b38d-91f4118c0be2.json b/data/reward-bench/nicolinho/QRM-Gemma-2-27B/96722888-0cc9-4dfd-b38d-91f4118c0be2.json
index cb05973d0..d61d3e0af 100644
--- a/data/reward-bench/nicolinho/QRM-Gemma-2-27B/96722888-0cc9-4dfd-b38d-91f4118c0be2.json
+++ b/data/reward-bench/nicolinho/QRM-Gemma-2-27B/96722888-0cc9-4dfd-b38d-91f4118c0be2.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/nicolinho_QRM-Gemma-2-27B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9444
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9665
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.9013
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.927
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9826
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/nicolinho/QRM-Llama3-8B/683abc2a-fce0-4d3d-bdcc-5cac2c76a46a.json b/data/reward-bench/nicolinho/QRM-Llama3-8B/683abc2a-fce0-4d3d-bdcc-5cac2c76a46a.json
index 627fa84e2..52e654851 100644
--- a/data/reward-bench/nicolinho/QRM-Llama3-8B/683abc2a-fce0-4d3d-bdcc-5cac2c76a46a.json
+++ b/data/reward-bench/nicolinho/QRM-Llama3-8B/683abc2a-fce0-4d3d-bdcc-5cac2c76a46a.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/nicolinho_QRM-Llama3-8B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.911
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9581
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8114
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8986
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9758
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/nicolinho/QRM-Llama3.1-8B-v2/121344ec-61ef-49c5-a74b-b86f605d513e.json b/data/reward-bench/nicolinho/QRM-Llama3.1-8B-v2/121344ec-61ef-49c5-a74b-b86f605d513e.json
index 182b54745..aef21f0ec 100644
--- a/data/reward-bench/nicolinho/QRM-Llama3.1-8B-v2/121344ec-61ef-49c5-a74b-b86f605d513e.json
+++ b/data/reward-bench/nicolinho/QRM-Llama3.1-8B-v2/121344ec-61ef-49c5-a74b-b86f605d513e.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/nicolinho_QRM-Llama3.1-8B-v2/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7074
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6653
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4062
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.612
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9467
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.8909
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.7234
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/nicolinho/QRM-Llama3.1-8B-v2/8594f86b-a7f2-4046-a3a7-830d7ac20690.json b/data/reward-bench/nicolinho/QRM-Llama3.1-8B-v2/8594f86b-a7f2-4046-a3a7-830d7ac20690.json
index ecf41624c..45f32ccdc 100644
--- a/data/reward-bench/nicolinho/QRM-Llama3.1-8B-v2/8594f86b-a7f2-4046-a3a7-830d7ac20690.json
+++ b/data/reward-bench/nicolinho/QRM-Llama3.1-8B-v2/8594f86b-a7f2-4046-a3a7-830d7ac20690.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/nicolinho_QRM-Llama3.1-8B-v2/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9314
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9637
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8684
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9257
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9677
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/nicolinho/QRM-Llama3.1-8B/c0c5e5e1-801c-48fd-a994-a4a69c0b1213.json b/data/reward-bench/nicolinho/QRM-Llama3.1-8B/c0c5e5e1-801c-48fd-a994-a4a69c0b1213.json
index 7663fc8b5..d0517b2db 100644
--- a/data/reward-bench/nicolinho/QRM-Llama3.1-8B/c0c5e5e1-801c-48fd-a994-a4a69c0b1213.json
+++ b/data/reward-bench/nicolinho/QRM-Llama3.1-8B/c0c5e5e1-801c-48fd-a994-a4a69c0b1213.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/nicolinho_QRM-Llama3.1-8B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9306
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9441
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8969
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.923
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9583
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/nvidia/Llama-3.1-Nemotron-70B-Reward/0411ac30-1536-4639-8350-fc11d53298e3.json b/data/reward-bench/nvidia/Llama-3.1-Nemotron-70B-Reward/0411ac30-1536-4639-8350-fc11d53298e3.json
index c6cfcb55e..639ea033b 100644
--- a/data/reward-bench/nvidia/Llama-3.1-Nemotron-70B-Reward/0411ac30-1536-4639-8350-fc11d53298e3.json
+++ b/data/reward-bench/nvidia/Llama-3.1-Nemotron-70B-Reward/0411ac30-1536-4639-8350-fc11d53298e3.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/nvidia_Llama-3.1-Nemotron-70B-Reward/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.9411
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9749
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8575
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9514
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9807
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/nvidia/Llama3-70B-SteerLM-RM/92281e58-4160-4d76-9119-b38fb47ffd8f.json b/data/reward-bench/nvidia/Llama3-70B-SteerLM-RM/92281e58-4160-4d76-9119-b38fb47ffd8f.json
index 4d74cb3a3..34cb0b116 100644
--- a/data/reward-bench/nvidia/Llama3-70B-SteerLM-RM/92281e58-4160-4d76-9119-b38fb47ffd8f.json
+++ b/data/reward-bench/nvidia/Llama3-70B-SteerLM-RM/92281e58-4160-4d76-9119-b38fb47ffd8f.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/nvidia_Llama3-70B-SteerLM-RM/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8877
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9134
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8026
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9064
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/nvidia/Nemotron-4-340B-Reward/43687871-2e19-4d2b-9754-1cb6527496c1.json b/data/reward-bench/nvidia/Nemotron-4-340B-Reward/43687871-2e19-4d2b-9754-1cb6527496c1.json
index e9305d7aa..81a8ec028 100644
--- a/data/reward-bench/nvidia/Nemotron-4-340B-Reward/43687871-2e19-4d2b-9754-1cb6527496c1.json
+++ b/data/reward-bench/nvidia/Nemotron-4-340B-Reward/43687871-2e19-4d2b-9754-1cb6527496c1.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/nvidia_Nemotron-4-340B-Reward/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.92
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9581
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.8706
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.9149
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9363
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/openai/gpt-3.5-turbo-0125/1debe1de-b394-4856-a946-9d14bd867bf6.json b/data/reward-bench/openai/gpt-3.5-turbo-0125/1debe1de-b394-4856-a946-9d14bd867bf6.json
index a806badc9..53333618b 100644
--- a/data/reward-bench/openai/gpt-3.5-turbo-0125/1debe1de-b394-4856-a946-9d14bd867bf6.json
+++ b/data/reward-bench/openai/gpt-3.5-turbo-0125/1debe1de-b394-4856-a946-9d14bd867bf6.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/openai_gpt-3.5-turbo-0125/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6534
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9218
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4452
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6547
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.5912
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6548
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/openai/gpt-4-0125-preview/80c589d2-c1eb-4dcf-8be8-042f4f66b7eb.json b/data/reward-bench/openai/gpt-4-0125-preview/80c589d2-c1eb-4dcf-8be8-042f4f66b7eb.json
index f7eab0bc7..24b1269d5 100644
--- a/data/reward-bench/openai/gpt-4-0125-preview/80c589d2-c1eb-4dcf-8be8-042f4f66b7eb.json
+++ b/data/reward-bench/openai/gpt-4-0125-preview/80c589d2-c1eb-4dcf-8be8-042f4f66b7eb.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/openai_gpt-4-0125-preview/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8434
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9525
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7434
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8757
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8692
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.7085
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/openai/gpt-4-turbo-2024-04-09/62478772-bb85-4d3f-a916-c3d17db3ee61.json b/data/reward-bench/openai/gpt-4-turbo-2024-04-09/62478772-bb85-4d3f-a916-c3d17db3ee61.json
index de6b17e12..8fbd65118 100644
--- a/data/reward-bench/openai/gpt-4-turbo-2024-04-09/62478772-bb85-4d3f-a916-c3d17db3ee61.json
+++ b/data/reward-bench/openai/gpt-4-turbo-2024-04-09/62478772-bb85-4d3f-a916-c3d17db3ee61.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/openai_gpt-4-turbo-2024-04-09/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8395
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9525
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7544
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8757
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.827
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.7363
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/openai/gpt-4.1-2025-04-14/a070bae2-c927-418b-91cc-161781c4f5b7.json b/data/reward-bench/openai/gpt-4.1-2025-04-14/a070bae2-c927-418b-91cc-161781c4f5b7.json
index d66bbee74..7ad659dc4 100644
--- a/data/reward-bench/openai/gpt-4.1-2025-04-14/a070bae2-c927-418b-91cc-161781c4f5b7.json
+++ b/data/reward-bench/openai/gpt-4.1-2025-04-14/a070bae2-c927-418b-91cc-161781c4f5b7.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/openai_gpt-4.1-2025-04-14/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7232
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8289
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3974
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6521
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8726
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7338
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.8542
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/openai/gpt-4.1-mini-2025-04-14/b884c919-a272-4f67-9a09-3d232f56d083.json b/data/reward-bench/openai/gpt-4.1-mini-2025-04-14/b884c919-a272-4f67-9a09-3d232f56d083.json
index c6287632a..fe081bf47 100644
--- a/data/reward-bench/openai/gpt-4.1-mini-2025-04-14/b884c919-a272-4f67-9a09-3d232f56d083.json
+++ b/data/reward-bench/openai/gpt-4.1-mini-2025-04-14/b884c919-a272-4f67-9a09-3d232f56d083.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/openai_gpt-4.1-mini-2025-04-14/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6573
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6084
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4125
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7213
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7265
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7354
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.74
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/openai/gpt-4.1-nano-2025-04-14/deac33dd-187b-4406-a76a-b33caf417380.json b/data/reward-bench/openai/gpt-4.1-nano-2025-04-14/deac33dd-187b-4406-a76a-b33caf417380.json
index b8c07d779..9236ca4a4 100644
--- a/data/reward-bench/openai/gpt-4.1-nano-2025-04-14/deac33dd-187b-4406-a76a-b33caf417380.json
+++ b/data/reward-bench/openai/gpt-4.1-nano-2025-04-14/deac33dd-187b-4406-a76a-b33caf417380.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/openai_gpt-4.1-nano-2025-04-14/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.4849
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.4646
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.2578
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5041
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7156
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.466
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5015
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/openai/gpt-4o-2024-05-13/185bd742-d7d4-4600-86bd-bcda75ed2ebc.json b/data/reward-bench/openai/gpt-4o-2024-05-13/185bd742-d7d4-4600-86bd-bcda75ed2ebc.json
index 8d3b140c6..e598746ee 100644
--- a/data/reward-bench/openai/gpt-4o-2024-05-13/185bd742-d7d4-4600-86bd-bcda75ed2ebc.json
+++ b/data/reward-bench/openai/gpt-4o-2024-05-13/185bd742-d7d4-4600-86bd-bcda75ed2ebc.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/openai_gpt-4o-2024-05-13/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8327
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9665
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7039
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8649
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8487
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.7262
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/openai/gpt-4o-2024-08-06/901e4de6-3ef6-4c2a-873c-cdcc47201974.json b/data/reward-bench/openai/gpt-4o-2024-08-06/901e4de6-3ef6-4c2a-873c-cdcc47201974.json
index 23f51655d..92a4b0914 100644
--- a/data/reward-bench/openai/gpt-4o-2024-08-06/901e4de6-3ef6-4c2a-873c-cdcc47201974.json
+++ b/data/reward-bench/openai/gpt-4o-2024-08-06/901e4de6-3ef6-4c2a-873c-cdcc47201974.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/openai_gpt-4o-2024-08-06/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8673
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9609
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.761
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8811
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.8661
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/openai/gpt-4o-2024-08-06/a051d5d6-18e6-483d-a000-4a52a06de676.json b/data/reward-bench/openai/gpt-4o-2024-08-06/a051d5d6-18e6-483d-a000-4a52a06de676.json
index e3cbd5105..44c5bcc27 100644
--- a/data/reward-bench/openai/gpt-4o-2024-08-06/a051d5d6-18e6-483d-a000-4a52a06de676.json
+++ b/data/reward-bench/openai/gpt-4o-2024-08-06/a051d5d6-18e6-483d-a000-4a52a06de676.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/openai_gpt-4o-2024-08-06/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6493
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5684
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3312
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.623
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8619
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7293
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.7819
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/openai/gpt-4o-mini-2024-07-18/94d77182-8952-4a63-b02b-3d8bd8a8dead.json b/data/reward-bench/openai/gpt-4o-mini-2024-07-18/94d77182-8952-4a63-b02b-3d8bd8a8dead.json
index bc9ec44b3..653bf1c3b 100644
--- a/data/reward-bench/openai/gpt-4o-mini-2024-07-18/94d77182-8952-4a63-b02b-3d8bd8a8dead.json
+++ b/data/reward-bench/openai/gpt-4o-mini-2024-07-18/94d77182-8952-4a63-b02b-3d8bd8a8dead.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/openai_gpt-4o-mini-2024-07-18/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8007
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9497
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6075
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8081
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.8374
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/openai/gpt-4o-mini-2024-07-18/9a48d808-0280-4175-a28a-7e9ba8ac6deb.json b/data/reward-bench/openai/gpt-4o-mini-2024-07-18/9a48d808-0280-4175-a28a-7e9ba8ac6deb.json
index 9e94f068b..4e0668e59 100644
--- a/data/reward-bench/openai/gpt-4o-mini-2024-07-18/9a48d808-0280-4175-a28a-7e9ba8ac6deb.json
+++ b/data/reward-bench/openai/gpt-4o-mini-2024-07-18/9a48d808-0280-4175-a28a-7e9ba8ac6deb.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/openai_gpt-4o-mini-2024-07-18/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5796
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.4105
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3438
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5191
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7667
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7414
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6962
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/openbmb/Eurus-7b-kto/f0d9f57d-d552-44ea-a91c-751854133316.json b/data/reward-bench/openbmb/Eurus-7b-kto/f0d9f57d-d552-44ea-a91c-751854133316.json
index 6052e166d..f4c92b674 100644
--- a/data/reward-bench/openbmb/Eurus-7b-kto/f0d9f57d-d552-44ea-a91c-751854133316.json
+++ b/data/reward-bench/openbmb/Eurus-7b-kto/f0d9f57d-d552-44ea-a91c-751854133316.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/openbmb_Eurus-7b-kto/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.69
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9525
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5373
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6054
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7467
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5261
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/openbmb/Eurus-RM-7b/561cfba1-856d-4809-b5c7-41481735e1d6.json b/data/reward-bench/openbmb/Eurus-RM-7b/561cfba1-856d-4809-b5c7-41481735e1d6.json
index bbe1d3987..2ceca85c7 100644
--- a/data/reward-bench/openbmb/Eurus-RM-7b/561cfba1-856d-4809-b5c7-41481735e1d6.json
+++ b/data/reward-bench/openbmb/Eurus-RM-7b/561cfba1-856d-4809-b5c7-41481735e1d6.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/openbmb_Eurus-RM-7b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5806
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.6
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3438
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5683
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6267
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7475
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.5972
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/openbmb/Eurus-RM-7b/995d1caf-b735-44dd-adff-875e3203aa46.json b/data/reward-bench/openbmb/Eurus-RM-7b/995d1caf-b735-44dd-adff-875e3203aa46.json
index 29c8dd2fe..83d393244 100644
--- a/data/reward-bench/openbmb/Eurus-RM-7b/995d1caf-b735-44dd-adff-875e3203aa46.json
+++ b/data/reward-bench/openbmb/Eurus-RM-7b/995d1caf-b735-44dd-adff-875e3203aa46.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/openbmb_Eurus-RM-7b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8159
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9804
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6557
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8135
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8633
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.7172
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/openbmb/MiniCPM-2B-dpo-fp32/81767043-23c2-4229-b3b5-1c24e470d52a.json b/data/reward-bench/openbmb/MiniCPM-2B-dpo-fp32/81767043-23c2-4229-b3b5-1c24e470d52a.json
index 896ebfae3..94f6c97ac 100644
--- a/data/reward-bench/openbmb/MiniCPM-2B-dpo-fp32/81767043-23c2-4229-b3b5-1c24e470d52a.json
+++ b/data/reward-bench/openbmb/MiniCPM-2B-dpo-fp32/81767043-23c2-4229-b3b5-1c24e470d52a.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/openbmb_MiniCPM-2B-dpo-fp32/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.673
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8911
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4934
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.573
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8233
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.4958
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/openbmb/UltraRM-13b/4f6344bc-af30-46f9-b6f8-41ff925d064e.json b/data/reward-bench/openbmb/UltraRM-13b/4f6344bc-af30-46f9-b6f8-41ff925d064e.json
index 3c1927c24..2c68b9ca5 100644
--- a/data/reward-bench/openbmb/UltraRM-13b/4f6344bc-af30-46f9-b6f8-41ff925d064e.json
+++ b/data/reward-bench/openbmb/UltraRM-13b/4f6344bc-af30-46f9-b6f8-41ff925d064e.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/openbmb_UltraRM-13b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6903
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9637
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5548
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5986
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6244
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.7294
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/openbmb/UltraRM-13b/abac8640-40be-4eb5-9035-2bf6fd436a7a.json b/data/reward-bench/openbmb/UltraRM-13b/abac8640-40be-4eb5-9035-2bf6fd436a7a.json
index 4a8e3095f..0b4c10b89 100644
--- a/data/reward-bench/openbmb/UltraRM-13b/abac8640-40be-4eb5-9035-2bf6fd436a7a.json
+++ b/data/reward-bench/openbmb/UltraRM-13b/abac8640-40be-4eb5-9035-2bf6fd436a7a.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/openbmb_UltraRM-13b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.4683
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5063
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3312
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5519
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.5089
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.6081
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.3036
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/opencompass/CompassJudger-1-1.5B-Instruct/6fd972ab-c45f-4ccd-a5cf-4aac5e703342.json b/data/reward-bench/opencompass/CompassJudger-1-1.5B-Instruct/6fd972ab-c45f-4ccd-a5cf-4aac5e703342.json
index b19fd4605..4c9d57828 100644
--- a/data/reward-bench/opencompass/CompassJudger-1-1.5B-Instruct/6fd972ab-c45f-4ccd-a5cf-4aac5e703342.json
+++ b/data/reward-bench/opencompass/CompassJudger-1-1.5B-Instruct/6fd972ab-c45f-4ccd-a5cf-4aac5e703342.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/opencompass_CompassJudger-1-1.5B-Instruct/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7344
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9637
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4923
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7818
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.6999
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/opencompass/CompassJudger-1-14B-Instruct/8eb1bcf2-a6bd-467c-bc37-090fdb7a9460.json b/data/reward-bench/opencompass/CompassJudger-1-14B-Instruct/8eb1bcf2-a6bd-467c-bc37-090fdb7a9460.json
index d6cbfe2cd..4299d154c 100644
--- a/data/reward-bench/opencompass/CompassJudger-1-14B-Instruct/8eb1bcf2-a6bd-467c-bc37-090fdb7a9460.json
+++ b/data/reward-bench/opencompass/CompassJudger-1-14B-Instruct/8eb1bcf2-a6bd-467c-bc37-090fdb7a9460.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/opencompass_CompassJudger-1-14B-Instruct/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8409
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9749
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6228
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8392
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9268
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/opencompass/CompassJudger-1-32B-Instruct/5ad53725-ed5a-41f3-8ff6-7404f3f981db.json b/data/reward-bench/opencompass/CompassJudger-1-32B-Instruct/5ad53725-ed5a-41f3-8ff6-7404f3f981db.json
index a63b6c3a9..49134a927 100644
--- a/data/reward-bench/opencompass/CompassJudger-1-32B-Instruct/5ad53725-ed5a-41f3-8ff6-7404f3f981db.json
+++ b/data/reward-bench/opencompass/CompassJudger-1-32B-Instruct/5ad53725-ed5a-41f3-8ff6-7404f3f981db.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/opencompass_CompassJudger-1-32B-Instruct/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8522
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9804
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6513
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8527
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.9244
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/opencompass/CompassJudger-1-7B-Instruct/ae2d05b4-5e80-4b00-af67-b94609b073eb.json b/data/reward-bench/opencompass/CompassJudger-1-7B-Instruct/ae2d05b4-5e80-4b00-af67-b94609b073eb.json
index 5e86fdf7e..145d5b3e9 100644
--- a/data/reward-bench/opencompass/CompassJudger-1-7B-Instruct/ae2d05b4-5e80-4b00-af67-b94609b073eb.json
+++ b/data/reward-bench/opencompass/CompassJudger-1-7B-Instruct/ae2d05b4-5e80-4b00-af67-b94609b073eb.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/opencompass_CompassJudger-1-7B-Instruct/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8317
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9777
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6096
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8446
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.8948
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/prometheus-eval/prometheus-7b-v2.0/592f2811-c197-423e-89d4-e25ee5a324fb.json b/data/reward-bench/prometheus-eval/prometheus-7b-v2.0/592f2811-c197-423e-89d4-e25ee5a324fb.json
index 3165413d5..e934ef88d 100644
--- a/data/reward-bench/prometheus-eval/prometheus-7b-v2.0/592f2811-c197-423e-89d4-e25ee5a324fb.json
+++ b/data/reward-bench/prometheus-eval/prometheus-7b-v2.0/592f2811-c197-423e-89d4-e25ee5a324fb.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/prometheus-eval_prometheus-7b-v2.0/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7204
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8547
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4912
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7709
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.7648
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/prometheus-eval/prometheus-8x7b-v2.0/17795e7b-e912-440f-a80e-63233d3b6d8c.json b/data/reward-bench/prometheus-eval/prometheus-8x7b-v2.0/17795e7b-e912-440f-a80e-63233d3b6d8c.json
index 21cf27bec..d2deb1a71 100644
--- a/data/reward-bench/prometheus-eval/prometheus-8x7b-v2.0/17795e7b-e912-440f-a80e-63233d3b6d8c.json
+++ b/data/reward-bench/prometheus-eval/prometheus-8x7b-v2.0/17795e7b-e912-440f-a80e-63233d3b6d8c.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/prometheus-eval_prometheus-8x7b-v2.0/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7451
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9302
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4715
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8047
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.774
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/sfairXC/FsfairX-LLaMA3-RM-v0.1/375cf55f-64f6-42f6-a947-1487feffb196.json b/data/reward-bench/sfairXC/FsfairX-LLaMA3-RM-v0.1/375cf55f-64f6-42f6-a947-1487feffb196.json
index 8570295e2..494a96669 100644
--- a/data/reward-bench/sfairXC/FsfairX-LLaMA3-RM-v0.1/375cf55f-64f6-42f6-a947-1487feffb196.json
+++ b/data/reward-bench/sfairXC/FsfairX-LLaMA3-RM-v0.1/375cf55f-64f6-42f6-a947-1487feffb196.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/sfairXC_FsfairX-LLaMA3-RM-v0.1/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8338
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9944
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6513
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8676
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8644
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.7492
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/sfairXC/FsfairX-LLaMA3-RM-v0.1/94d2eddd-f7db-4360-ac58-0af39ce66935.json b/data/reward-bench/sfairXC/FsfairX-LLaMA3-RM-v0.1/94d2eddd-f7db-4360-ac58-0af39ce66935.json
index 4d7ceaaeb..8dad45261 100644
--- a/data/reward-bench/sfairXC/FsfairX-LLaMA3-RM-v0.1/94d2eddd-f7db-4360-ac58-0af39ce66935.json
+++ b/data/reward-bench/sfairXC/FsfairX-LLaMA3-RM-v0.1/94d2eddd-f7db-4360-ac58-0af39ce66935.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/sfairXC_FsfairX-LLaMA3-RM-v0.1/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6292
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5916
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4188
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6284
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7667
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7051
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6647
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/stabilityai/stable-code-instruct-3b/996ca604-e01c-4a95-9286-60b6dc04f67d.json b/data/reward-bench/stabilityai/stable-code-instruct-3b/996ca604-e01c-4a95-9286-60b6dc04f67d.json
index a33ed8633..74acfeed3 100644
--- a/data/reward-bench/stabilityai/stable-code-instruct-3b/996ca604-e01c-4a95-9286-60b6dc04f67d.json
+++ b/data/reward-bench/stabilityai/stable-code-instruct-3b/996ca604-e01c-4a95-9286-60b6dc04f67d.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/stabilityai_stable-code-instruct-3b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6216
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5782
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5855
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6554
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7528
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.4506
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/stabilityai/stablelm-2-12b-chat/b6f0089f-d04b-4bcd-be84-ce3bc0d6c2b9.json b/data/reward-bench/stabilityai/stablelm-2-12b-chat/b6f0089f-d04b-4bcd-be84-ce3bc0d6c2b9.json
index 267923a0a..491861cbd 100644
--- a/data/reward-bench/stabilityai/stablelm-2-12b-chat/b6f0089f-d04b-4bcd-be84-ce3bc0d6c2b9.json
+++ b/data/reward-bench/stabilityai/stablelm-2-12b-chat/b6f0089f-d04b-4bcd-be84-ce3bc0d6c2b9.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/stabilityai_stablelm-2-12b-chat/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7642
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9665
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5548
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7811
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.8945
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.4839
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/stabilityai/stablelm-2-zephyr-1_6b/83e15cba-4fec-48f2-9be4-78decbd96f66.json b/data/reward-bench/stabilityai/stablelm-2-zephyr-1_6b/83e15cba-4fec-48f2-9be4-78decbd96f66.json
index 96b9cccee..3406eee45 100644
--- a/data/reward-bench/stabilityai/stablelm-2-zephyr-1_6b/83e15cba-4fec-48f2-9be4-78decbd96f66.json
+++ b/data/reward-bench/stabilityai/stablelm-2-zephyr-1_6b/83e15cba-4fec-48f2-9be4-78decbd96f66.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/stabilityai_stablelm-2-zephyr-1_6b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6574
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9665
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4671
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6027
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6784
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.4868
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/stabilityai/stablelm-zephyr-3b/493617c0-37eb-4c83-b175-2507a3647b5e.json b/data/reward-bench/stabilityai/stablelm-zephyr-3b/493617c0-37eb-4c83-b175-2507a3647b5e.json
index 86b5e6605..47f135b1d 100644
--- a/data/reward-bench/stabilityai/stablelm-zephyr-3b/493617c0-37eb-4c83-b175-2507a3647b5e.json
+++ b/data/reward-bench/stabilityai/stablelm-zephyr-3b/493617c0-37eb-4c83-b175-2507a3647b5e.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/stabilityai_stablelm-zephyr-3b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7146
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8631
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6009
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7405
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7573
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.5075
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/stanfordnlp/SteamSHP-flan-t5-large/97f494ce-3c9c-4a19-a237-d458be611a0a.json b/data/reward-bench/stanfordnlp/SteamSHP-flan-t5-large/97f494ce-3c9c-4a19-a237-d458be611a0a.json
index 6959fb49d..47e44c557 100644
--- a/data/reward-bench/stanfordnlp/SteamSHP-flan-t5-large/97f494ce-3c9c-4a19-a237-d458be611a0a.json
+++ b/data/reward-bench/stanfordnlp/SteamSHP-flan-t5-large/97f494ce-3c9c-4a19-a237-d458be611a0a.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/stanfordnlp_SteamSHP-flan-t5-large/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.4962
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8575
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3311
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.3743
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.3563
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6273
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/stanfordnlp/SteamSHP-flan-t5-xl/f8bf1e92-3cc3-4c7e-9770-485a3074e85f.json b/data/reward-bench/stanfordnlp/SteamSHP-flan-t5-xl/f8bf1e92-3cc3-4c7e-9770-485a3074e85f.json
index 05a9b1b28..6a0de9161 100644
--- a/data/reward-bench/stanfordnlp/SteamSHP-flan-t5-xl/f8bf1e92-3cc3-4c7e-9770-485a3074e85f.json
+++ b/data/reward-bench/stanfordnlp/SteamSHP-flan-t5-xl/f8bf1e92-3cc3-4c7e-9770-485a3074e85f.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/stanfordnlp_SteamSHP-flan-t5-xl/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5135
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8547
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3684
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.3784
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.3841
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6498
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/unknown/Cohere March 2024/5bf73fba-520f-4a2f-9296-8240847eb8ec.json b/data/reward-bench/unknown/Cohere March 2024/5bf73fba-520f-4a2f-9296-8240847eb8ec.json
index 9bd7881e2..b2e8c1248 100644
--- a/data/reward-bench/unknown/Cohere March 2024/5bf73fba-520f-4a2f-9296-8240847eb8ec.json	
+++ b/data/reward-bench/unknown/Cohere March 2024/5bf73fba-520f-4a2f-9296-8240847eb8ec.json	
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Cohere March 2024/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8511
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9469
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6513
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.877
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9817
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.7458
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/unknown/Cohere May 2024/3dd2c89f-64f5-4bbc-a621-791a9f0538b2.json b/data/reward-bench/unknown/Cohere May 2024/3dd2c89f-64f5-4bbc-a621-791a9f0538b2.json
index 0945d9e1d..a50e32313 100644
--- a/data/reward-bench/unknown/Cohere May 2024/3dd2c89f-64f5-4bbc-a621-791a9f0538b2.json	
+++ b/data/reward-bench/unknown/Cohere May 2024/3dd2c89f-64f5-4bbc-a621-791a9f0538b2.json	
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/Cohere May 2024/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.8816
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9637
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.7127
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.923
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.9768
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.782
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/unknown/gemini-1.5-flash-8b/ef987556-7277-48d8-ac07-532586773a3a.json b/data/reward-bench/unknown/gemini-1.5-flash-8b/ef987556-7277-48d8-ac07-532586773a3a.json
index 7a9d537f7..dd83d6018 100644
--- a/data/reward-bench/unknown/gemini-1.5-flash-8b/ef987556-7277-48d8-ac07-532586773a3a.json
+++ b/data/reward-bench/unknown/gemini-1.5-flash-8b/ef987556-7277-48d8-ac07-532586773a3a.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/gemini-1.5-flash-8b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7601
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9441
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5987
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.7399
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,7 +101,12 @@
       },
       "score_details": {
         "score": 0.7575
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/upstage/SOLAR-10.7B-Instruct-v1.0/add7eddb-7a8b-4c78-9864-c4316a97ce5e.json b/data/reward-bench/upstage/SOLAR-10.7B-Instruct-v1.0/add7eddb-7a8b-4c78-9864-c4316a97ce5e.json
index 959f86ef9..5df4ce7b8 100644
--- a/data/reward-bench/upstage/SOLAR-10.7B-Instruct-v1.0/add7eddb-7a8b-4c78-9864-c4316a97ce5e.json
+++ b/data/reward-bench/upstage/SOLAR-10.7B-Instruct-v1.0/add7eddb-7a8b-4c78-9864-c4316a97ce5e.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/upstage_SOLAR-10.7B-Instruct-v1.0/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7391
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8156
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6864
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8514
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7252
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.4949
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/wenbopan/Faro-Yi-9B-DPO/caf02954-1eed-44eb-b5f4-df47c90828d7.json b/data/reward-bench/wenbopan/Faro-Yi-9B-DPO/caf02954-1eed-44eb-b5f4-df47c90828d7.json
index 1ed12c67e..78244f3ff 100644
--- a/data/reward-bench/wenbopan/Faro-Yi-9B-DPO/caf02954-1eed-44eb-b5f4-df47c90828d7.json
+++ b/data/reward-bench/wenbopan/Faro-Yi-9B-DPO/caf02954-1eed-44eb-b5f4-df47c90828d7.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/wenbopan_Faro-Yi-9B-DPO/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6461
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9218
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5307
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5514
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.5839
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6395
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/weqweasdas/RM-Gemma-2B/00798930-daa2-4e79-82c6-2cccf1c3a0cb.json b/data/reward-bench/weqweasdas/RM-Gemma-2B/00798930-daa2-4e79-82c6-2cccf1c3a0cb.json
index b2a906172..8856c5e7a 100644
--- a/data/reward-bench/weqweasdas/RM-Gemma-2B/00798930-daa2-4e79-82c6-2cccf1c3a0cb.json
+++ b/data/reward-bench/weqweasdas/RM-Gemma-2B/00798930-daa2-4e79-82c6-2cccf1c3a0cb.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/weqweasdas_RM-Gemma-2B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6549
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9441
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4079
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.4986
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7637
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6652
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/weqweasdas/RM-Gemma-2B/71658cf8-0189-49dc-847f-b9a9b5faee4a.json b/data/reward-bench/weqweasdas/RM-Gemma-2B/71658cf8-0189-49dc-847f-b9a9b5faee4a.json
index 2ca9f1e1b..c3e2d4a3c 100644
--- a/data/reward-bench/weqweasdas/RM-Gemma-2B/71658cf8-0189-49dc-847f-b9a9b5faee4a.json
+++ b/data/reward-bench/weqweasdas/RM-Gemma-2B/71658cf8-0189-49dc-847f-b9a9b5faee4a.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/weqweasdas_RM-Gemma-2B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.3057
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.3705
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.2812
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.4317
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.3311
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.2343
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.1851
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/weqweasdas/RM-Gemma-7B-4096/3d506b91-5b0d-47e3-a3a0-bc09808bf5b5.json b/data/reward-bench/weqweasdas/RM-Gemma-7B-4096/3d506b91-5b0d-47e3-a3a0-bc09808bf5b5.json
index e041d4d42..81934bf6a 100644
--- a/data/reward-bench/weqweasdas/RM-Gemma-7B-4096/3d506b91-5b0d-47e3-a3a0-bc09808bf5b5.json
+++ b/data/reward-bench/weqweasdas/RM-Gemma-7B-4096/3d506b91-5b0d-47e3-a3a0-bc09808bf5b5.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/weqweasdas_RM-Gemma-7B-4096/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6922
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9497
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.5022
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5608
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7511
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.7024
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/weqweasdas/RM-Gemma-7B/04c71231-2025-4e1a-b7ed-56b245868089.json b/data/reward-bench/weqweasdas/RM-Gemma-7B/04c71231-2025-4e1a-b7ed-56b245868089.json
index 5c579948e..02ba525c2 100644
--- a/data/reward-bench/weqweasdas/RM-Gemma-7B/04c71231-2025-4e1a-b7ed-56b245868089.json
+++ b/data/reward-bench/weqweasdas/RM-Gemma-7B/04c71231-2025-4e1a-b7ed-56b245868089.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/weqweasdas_RM-Gemma-7B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.6967
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9693
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.4978
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5784
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7362
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.7069
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/weqweasdas/RM-Gemma-7B/08b2edd0-f8e9-47cd-b19d-53fdc7209917.json b/data/reward-bench/weqweasdas/RM-Gemma-7B/08b2edd0-f8e9-47cd-b19d-53fdc7209917.json
index 07fd2fbc9..ed03af39d 100644
--- a/data/reward-bench/weqweasdas/RM-Gemma-7B/08b2edd0-f8e9-47cd-b19d-53fdc7209917.json
+++ b/data/reward-bench/weqweasdas/RM-Gemma-7B/08b2edd0-f8e9-47cd-b19d-53fdc7209917.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/weqweasdas_RM-Gemma-7B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.4826
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.4926
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3937
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.6066
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.4822
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.497
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.4232
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/weqweasdas/RM-Mistral-7B/79a43841-4032-4a20-8b5a-83b4b446d107.json b/data/reward-bench/weqweasdas/RM-Mistral-7B/79a43841-4032-4a20-8b5a-83b4b446d107.json
index 6afc5be13..7abde633d 100644
--- a/data/reward-bench/weqweasdas/RM-Mistral-7B/79a43841-4032-4a20-8b5a-83b4b446d107.json
+++ b/data/reward-bench/weqweasdas/RM-Mistral-7B/79a43841-4032-4a20-8b5a-83b4b446d107.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/weqweasdas_RM-Mistral-7B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.7982
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.9665
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.6053
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.8703
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.7736
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.753
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/weqweasdas/RM-Mistral-7B/a2c16ab8-1098-490a-8d0a-392d835427e0.json b/data/reward-bench/weqweasdas/RM-Mistral-7B/a2c16ab8-1098-490a-8d0a-392d835427e0.json
index 7abeeaa13..d53f1986e 100644
--- a/data/reward-bench/weqweasdas/RM-Mistral-7B/a2c16ab8-1098-490a-8d0a-392d835427e0.json
+++ b/data/reward-bench/weqweasdas/RM-Mistral-7B/a2c16ab8-1098-490a-8d0a-392d835427e0.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/weqweasdas_RM-Mistral-7B/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.596
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.5937
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3438
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.5956
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.6911
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.7293
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.6226
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/weqweasdas/hh_rlhf_rm_open_llama_3b/0aa12860-7ebe-49c2-a5af-1926d23e34f8.json b/data/reward-bench/weqweasdas/hh_rlhf_rm_open_llama_3b/0aa12860-7ebe-49c2-a5af-1926d23e34f8.json
index 765de8cd1..dbe32c629 100644
--- a/data/reward-bench/weqweasdas/hh_rlhf_rm_open_llama_3b/0aa12860-7ebe-49c2-a5af-1926d23e34f8.json
+++ b/data/reward-bench/weqweasdas/hh_rlhf_rm_open_llama_3b/0aa12860-7ebe-49c2-a5af-1926d23e34f8.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench/weqweasdas_hh_rlhf_rm_open_llama_3b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/spaces/allenai/reward-bench"
-  ],
   "source_metadata": {
     "source_name": "RewardBench",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.5027
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.8184
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.3728
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.4149
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.3281
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     },
     {
@@ -97,7 +119,12 @@
       },
       "score_details": {
         "score": 0.6564
+      },
+      "source_data": {
+        "dataset_name": "RewardBench",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/data/reward-bench/weqweasdas/hh_rlhf_rm_open_llama_3b/796d3ec1-9c26-4ead-87cb-4eb866209120.json b/data/reward-bench/weqweasdas/hh_rlhf_rm_open_llama_3b/796d3ec1-9c26-4ead-87cb-4eb866209120.json
index ca35ed864..7e050faee 100644
--- a/data/reward-bench/weqweasdas/hh_rlhf_rm_open_llama_3b/796d3ec1-9c26-4ead-87cb-4eb866209120.json
+++ b/data/reward-bench/weqweasdas/hh_rlhf_rm_open_llama_3b/796d3ec1-9c26-4ead-87cb-4eb866209120.json
@@ -1,10 +1,7 @@
 {
-  "schema_version": "0.1.0",
+  "schema_version": "0.2.0",
   "evaluation_id": "reward-bench-2/weqweasdas_hh_rlhf_rm_open_llama_3b/1766412838.146816",
   "retrieved_timestamp": "1766412838.146816",
-  "source_data": [
-    "https://huggingface.co/datasets/allenai/reward-bench-2-results"
-  ],
   "source_metadata": {
     "source_name": "RewardBench 2",
     "source_type": "documentation",
@@ -32,6 +29,11 @@
       },
       "score_details": {
         "score": 0.2498
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -45,6 +47,11 @@
       },
       "score_details": {
         "score": 0.3642
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -58,6 +65,11 @@
       },
       "score_details": {
         "score": 0.275
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -71,6 +83,11 @@
       },
       "score_details": {
         "score": 0.3497
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -84,6 +101,11 @@
       },
       "score_details": {
         "score": 0.24
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -97,6 +119,11 @@
       },
       "score_details": {
         "score": 0.2384
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     },
     {
@@ -110,7 +137,12 @@
       },
       "score_details": {
         "score": 0.0315
+      },
+      "source_data": {
+        "dataset_name": "RewardBench 2",
+        "source_type": "hf_dataset",
+        "hf_repo": "allenai/reward-bench-2-results"
       }
     }
   ]
-}
\ No newline at end of file
+}
diff --git a/scripts/rewardbench/adapter.py b/scripts/rewardbench/adapter.py
index eb3133905..e450b3835 100644
--- a/scripts/rewardbench/adapter.py
+++ b/scripts/rewardbench/adapter.py
@@ -21,12 +21,15 @@
 sys.path.insert(0, str(Path(__file__).parent.parent))
 
 from utils import (
+    SCHEMA_VERSION,
     fetch_csv,
     fetch_json,
     get_developer,
     make_evaluation_result,
     make_source_metadata,
     make_model_info,
+    make_source_data_hf,
+    make_source_data_url,
     save_evaluation_log,
 )
 
@@ -38,6 +41,18 @@
 
 OUTPUT_DIR = "data/reward-bench"
 
+# RewardBench v1 source data (shared across all v1 evaluation results)
+V1_SOURCE_DATA = make_source_data_hf(
+    dataset_name="RewardBench",
+    hf_repo="allenai/reward-bench",
+)
+
+# RewardBench v2 source data (shared across all v2 evaluation results)
+V2_SOURCE_DATA = make_source_data_hf(
+    dataset_name="RewardBench 2",
+    hf_repo="allenai/reward-bench-2-results",
+)
+
 # RewardBench v1 metrics with descriptions
 V1_METRICS = {
     "Score": "Overall RewardBench Score",
@@ -111,6 +126,7 @@ def fetch_rewardbench_v1(retrieved_timestamp: str) -> int:
                         name=metric_name,
                         score=score,
                         description=description,
+                        source_data=V1_SOURCE_DATA,
                     )
                 )
 
@@ -127,10 +143,9 @@ def fetch_rewardbench_v1(retrieved_timestamp: str) -> int:
         # Build evaluation log
         evaluation_id = f"reward-bench/{model_info.id.replace('/', '_')}/{retrieved_timestamp}"
         eval_log = EvaluationLog(
-            schema_version="0.1.0",
+            schema_version=SCHEMA_VERSION,
             evaluation_id=evaluation_id,
             retrieved_timestamp=retrieved_timestamp,
-            source_data=["https://huggingface.co/spaces/allenai/reward-bench"],
             source_metadata=make_source_metadata(
                 source_name="RewardBench",
                 organization_name="Allen Institute for AI",
@@ -208,6 +223,7 @@ def fetch_rewardbench_v2(retrieved_timestamp: str) -> int:
                                 name=metric_name,
                                 score=score,
                                 description=description,
+                                source_data=V2_SOURCE_DATA,
                             )
                         )
                     except (ValueError, TypeError):
@@ -225,6 +241,7 @@ def fetch_rewardbench_v2(retrieved_timestamp: str) -> int:
                         name="Score",
                         score=mean_score,
                         description="Overall RewardBench 2 Score (mean of all metrics)",
+                        source_data=V2_SOURCE_DATA,
                     ),
                 )
 
@@ -238,10 +255,9 @@ def fetch_rewardbench_v2(retrieved_timestamp: str) -> int:
             # Build evaluation log
             evaluation_id = f"reward-bench-2/{model_info.id.replace('/', '_')}/{retrieved_timestamp}"
             eval_log = EvaluationLog(
-                schema_version="0.1.0",
+                schema_version=SCHEMA_VERSION,
                 evaluation_id=evaluation_id,
                 retrieved_timestamp=retrieved_timestamp,
-                source_data=["https://huggingface.co/datasets/allenai/reward-bench-2-results"],
                 source_metadata=make_source_metadata(
                     source_name="RewardBench 2",
                     organization_name="Allen Institute for AI",
diff --git a/scripts/rewardbench/migrate_to_v020.py b/scripts/rewardbench/migrate_to_v020.py
new file mode 100644
index 000000000..e36880a16
--- /dev/null
+++ b/scripts/rewardbench/migrate_to_v020.py
@@ -0,0 +1,113 @@
+"""
+Migration script to update reward-bench JSON files from schema v0.1.0 to v0.2.0.
+
+Key changes:
+- schema_version: "0.1.0" -> "0.2.0"
+- Remove top-level "source_data" field
+- Add "source_data" to each evaluation result item
+- Remove "inference_platform": "unknown" from model_info (now optional)
+
+For RewardBench v1 results (evaluation_id starts with "reward-bench/"):
+    source_data = {"dataset_name": "RewardBench", "source_type": "hf_dataset", "hf_repo": "allenai/reward-bench"}
+
+For RewardBench v2 results (evaluation_id starts with "reward-bench-2/"):
+    source_data = {"dataset_name": "RewardBench 2", "source_type": "hf_dataset", "hf_repo": "allenai/reward-bench-2-results"}
+
+Usage:
+    python -m scripts.rewardbench.migrate_to_v020
+"""
+
+import json
+from pathlib import Path
+
+
+DATA_DIR = Path("data/reward-bench")
+
+V1_SOURCE_DATA = {
+    "dataset_name": "RewardBench",
+    "source_type": "hf_dataset",
+    "hf_repo": "allenai/reward-bench",
+}
+
+V2_SOURCE_DATA = {
+    "dataset_name": "RewardBench 2",
+    "source_type": "hf_dataset",
+    "hf_repo": "allenai/reward-bench-2-results",
+}
+
+
+def migrate_file(filepath: Path) -> bool:
+    """
+    Migrate a single JSON file from v0.1.0 to v0.2.0.
+
+    Returns True if the file was modified, False if it was already up to date.
+    """
+    with open(filepath, "r") as f:
+        data = json.load(f)
+
+    # Skip files that are already v0.2.0
+    if data.get("schema_version") == "0.2.0":
+        return False
+
+    # Determine source_data based on evaluation_id
+    evaluation_id = data.get("evaluation_id", "")
+    if evaluation_id.startswith("reward-bench-2/"):
+        source_data = V2_SOURCE_DATA
+    else:
+        source_data = V1_SOURCE_DATA
+
+    # 1. Update schema_version
+    data["schema_version"] = "0.2.0"
+
+    # 2. Remove top-level source_data
+    data.pop("source_data", None)
+
+    # 3. Add source_data to each evaluation result
+    for result in data.get("evaluation_results", []):
+        if "source_data" not in result:
+            result["source_data"] = source_data
+
+    # 4. Clean up model_info: remove inference_platform if "unknown"
+    model_info = data.get("model_info", {})
+    if model_info.get("inference_platform") == "unknown":
+        del model_info["inference_platform"]
+
+    # Write back
+    with open(filepath, "w") as f:
+        json.dump(data, f, indent=2)
+        f.write("\n")
+
+    return True
+
+
+def main():
+    """Migrate all reward-bench JSON files to v0.2.0."""
+    if not DATA_DIR.exists():
+        print(f"Error: {DATA_DIR} does not exist")
+        return
+
+    json_files = sorted(DATA_DIR.rglob("*.json"))
+    print(f"Found {len(json_files)} JSON files in {DATA_DIR}")
+
+    migrated = 0
+    skipped = 0
+    errors = 0
+
+    for filepath in json_files:
+        try:
+            if migrate_file(filepath):
+                migrated += 1
+            else:
+                skipped += 1
+        except Exception as e:
+            print(f"  Error migrating {filepath}: {e}")
+            errors += 1
+
+    print(f"\nMigration complete:")
+    print(f"  Migrated: {migrated}")
+    print(f"  Skipped (already v0.2.0): {skipped}")
+    print(f"  Errors: {errors}")
+
+
+if __name__ == "__main__":
+    main()
diff --git a/scripts/utils/__init__.py b/scripts/utils/__init__.py
index 0ce4c3702..08b5f76fb 100644
--- a/scripts/utils/__init__.py
+++ b/scripts/utils/__init__.py
@@ -4,11 +4,15 @@
 from .fetch import fetch_json, fetch_csv, FetchError
 from .io import save_evaluation_log, generate_output_path, sanitize_filename
 from .schema import (
+    SCHEMA_VERSION,
     make_metric_config,
     make_evaluation_result,
     make_source_metadata,
     make_model_info,
     make_evaluation_log,
+    make_source_data_url,
+    make_source_data_hf,
+    make_source_data_private,
 )
 
 __all__ = [
@@ -24,9 +28,13 @@
     "generate_output_path",
     "sanitize_filename",
     # schema.py
+    "SCHEMA_VERSION",
     "make_metric_config",
     "make_evaluation_result",
     "make_source_metadata",
     "make_model_info",
     "make_evaluation_log",
+    "make_source_data_url",
+    "make_source_data_hf",
+    "make_source_data_private",
 ]
diff --git a/scripts/utils/schema.py b/scripts/utils/schema.py
index 08d66e4ac..870ba208a 100644
--- a/scripts/utils/schema.py
+++ b/scripts/utils/schema.py
@@ -1,7 +1,7 @@
 """Schema construction helpers for building evaluation logs."""
 
 import time
-from typing import Any, Dict, List, Optional
+from typing import Any, Dict, List, Optional, Union
 
 from eval_types import (
     EvaluationLog,
@@ -11,11 +11,88 @@
     ModelInfo,
     ScoreDetails,
     ScoreType,
+    SourceDataHf,
+    SourceDataPrivate,
+    SourceDataUrl,
     SourceMetadata,
 )
 
 from .developer import get_developer, get_model_id
 
+# Schema version constant
+SCHEMA_VERSION = "0.2.0"
+
+# Type alias for source data variants
+SourceData = Union[SourceDataUrl, SourceDataHf, SourceDataPrivate]
+
+
+def make_source_data_url(
+    dataset_name: str,
+    url: List[str],
+    **additional_details: Any,
+) -> SourceDataUrl:
+    """
+    Create a SourceDataUrl for URL-based evaluation data sources.
+
+    Args:
+        dataset_name: Name of the source dataset
+        url: List of URL(s) for the source of the evaluation data
+        **additional_details: Additional metadata key-value pairs
+
+    Returns:
+        Configured SourceDataUrl instance
+    """
+    return SourceDataUrl(
+        dataset_name=dataset_name,
+        source_type="url",
+        url=url,
+    )
+
+
+def make_source_data_hf(
+    dataset_name: str,
+    hf_repo: Optional[str] = None,
+    hf_split: Optional[str] = None,
+    samples_number: Optional[int] = None,
+) -> SourceDataHf:
+    """
+    Create a SourceDataHf for HuggingFace dataset sources.
+
+    Args:
+        dataset_name: Name of the source dataset
+        hf_repo: HuggingFace repository identifier
+        hf_split: Dataset split (train, val, or test)
+        samples_number: Number of samples in the dataset
+
+    Returns:
+        Configured SourceDataHf instance
+    """
+    return SourceDataHf(
+        dataset_name=dataset_name,
+        source_type="hf_dataset",
+        hf_repo=hf_repo,
+        hf_split=hf_split,
+        samples_number=samples_number,
+    )
+
+
+def make_source_data_private(
+    dataset_name: str,
+) -> SourceDataPrivate:
+    """
+    Create a SourceDataPrivate for private/custom dataset sources.
+
+    Args:
+        dataset_name: Name of the source dataset
+
+    Returns:
+        Configured SourceDataPrivate instance
+    """
+    return SourceDataPrivate(
+        dataset_name=dataset_name,
+        source_type="other",
+    )
+
 
 def make_metric_config(
     description: str,
@@ -64,6 +141,7 @@ def make_evaluation_result(
     name: str,
     score: float,
     description: str,
+    source_data: SourceData,
     lower_is_better: bool = False,
     score_type: ScoreType = ScoreType.continuous,
     min_score: float = 0.0,
@@ -80,6 +158,7 @@ def make_evaluation_result(
         name: Name of the evaluation (e.g., "MMLU", "GSM8K")
         score: The score value
         description: Human-readable description of what this measures
+        source_data: Source dataset information (URL, HuggingFace, or private)
         lower_is_better: Whether lower scores are better
         score_type: Type of score
         min_score: Minimum possible score
@@ -92,6 +171,7 @@ def make_evaluation_result(
     """
     return EvaluationResult(
         evaluation_name=name,
+        source_data=source_data,
         metric_config=make_metric_config(
             description=description,
             lower_is_better=lower_is_better,
@@ -139,7 +219,7 @@ def make_source_metadata(
 def make_model_info(
     model_name: str,
     developer: Optional[str] = None,
-    inference_platform: str = "unknown",
+    inference_platform: Optional[str] = None,
     additional_details: Optional[Dict[str, Any]] = None,
 ) -> ModelInfo:
     """
@@ -150,7 +230,7 @@ def make_model_info(
     Args:
         model_name: Name of the model
         developer: Optional developer override
-        inference_platform: Platform used for inference
+        inference_platform: Optional platform used for inference
         additional_details: Extra model metadata
 
     Returns:
@@ -172,13 +252,12 @@ def make_evaluation_log(
     source_name: str,
     model_name: str,
     evaluation_results: List[EvaluationResult],
-    source_data: List[str],
     organization_name: str,
     source_type: str = "documentation",
     evaluator_relationship: EvaluatorRelationship = EvaluatorRelationship.third_party,
     organization_url: Optional[str] = None,
     developer: Optional[str] = None,
-    inference_platform: str = "unknown",
+    inference_platform: Optional[str] = None,
     model_additional_details: Optional[Dict[str, Any]] = None,
     retrieved_timestamp: Optional[str] = None,
 ) -> EvaluationLog:
@@ -190,14 +269,13 @@ def make_evaluation_log(
     Args:
         source_name: Name of the evaluation source
         model_name: Name of the model being evaluated
-        evaluation_results: List of evaluation results
-        source_data: URLs or dataset info for the source data
+        evaluation_results: List of evaluation results (each must include source_data)
         organization_name: Organization providing the evaluation
         source_type: Either "documentation" or "evaluation_run"
         evaluator_relationship: Relationship to model developer
         organization_url: Optional URL for the organization
         developer: Optional developer override
-        inference_platform: Platform used for inference
+        inference_platform: Optional platform used for inference
         model_additional_details: Extra model metadata
         retrieved_timestamp: Optional timestamp override
 
@@ -213,10 +291,9 @@ def make_evaluation_log(
     evaluation_id = f"{source_name}/{sanitized_model_id}/{timestamp}"
 
     return EvaluationLog(
-        schema_version="0.1.0",
+        schema_version=SCHEMA_VERSION,
         evaluation_id=evaluation_id,
         retrieved_timestamp=timestamp,
-        source_data=source_data,
         source_metadata=make_source_metadata(
             source_name=source_name,
             organization_name=organization_name,

From 83a3a4fd70d95421662af96a0a92a40725074dfd Mon Sep 17 00:00:00 2001
From: Asaf Yehudai <Asaf.Yehudai@ibm.com>
Date: Wed, 11 Feb 2026 10:47:42 +0200
Subject: [PATCH 2/2] update RewardBench to v0.2

Update RewardBench to v0.2, make it self contained, and check that it pass the schema tests.
---
 scripts/rewardbench/adapter.py | 130 ++++++++++++++++++++++++---------
 scripts/utils/__init__.py      |   8 --
 scripts/utils/schema.py        |  97 +++---------------------
 3 files changed, 107 insertions(+), 128 deletions(-)

diff --git a/scripts/rewardbench/adapter.py b/scripts/rewardbench/adapter.py
index e450b3835..09ceef8d1 100644
--- a/scripts/rewardbench/adapter.py
+++ b/scripts/rewardbench/adapter.py
@@ -12,47 +12,74 @@
 
 import re
 import time
-from typing import List, Optional
-
-from eval_types import EvaluationLog, EvaluationResult, EvaluatorRelationship
+import uuid
+from pathlib import Path
+from typing import Any, Dict, List, Optional
+
+from eval_types import (
+    EvaluationLog,
+    EvaluationResult,
+    EvaluatorRelationship,
+    MetricConfig,
+    ModelInfo,
+    ScoreDetails,
+    ScoreType,
+    SourceDataHf,
+    SourceMetadata,
+)
 
 import sys
-from pathlib import Path
 sys.path.insert(0, str(Path(__file__).parent.parent))
 
 from utils import (
-    SCHEMA_VERSION,
     fetch_csv,
     fetch_json,
     get_developer,
-    make_evaluation_result,
-    make_source_metadata,
-    make_model_info,
-    make_source_data_hf,
-    make_source_data_url,
-    save_evaluation_log,
+    get_model_id,
+    sanitize_filename,
 )
 
+# Schema version
+SCHEMA_VERSION = "0.2.0"
 
 # Data source URLs
 REWARDBENCH_V1_CSV = "https://huggingface.co/spaces/allenai/reward-bench/resolve/main/leaderboard/final-rbv1-data.csv"
 REWARDBENCH_V2_TREE_API = "https://huggingface.co/api/datasets/allenai/reward-bench-2-results/tree/main/eval-set"
 REWARDBENCH_V2_FILE_BASE = "https://huggingface.co/datasets/allenai/reward-bench-2-results/resolve/main/eval-set"
 
-OUTPUT_DIR = "data/reward-bench"
+OUTPUT_DIR = Path("data/reward-bench")
 
 # RewardBench v1 source data (shared across all v1 evaluation results)
-V1_SOURCE_DATA = make_source_data_hf(
+V1_SOURCE_DATA = SourceDataHf(
     dataset_name="RewardBench",
+    source_type="hf_dataset",
     hf_repo="allenai/reward-bench",
 )
 
 # RewardBench v2 source data (shared across all v2 evaluation results)
-V2_SOURCE_DATA = make_source_data_hf(
+V2_SOURCE_DATA = SourceDataHf(
     dataset_name="RewardBench 2",
+    source_type="hf_dataset",
     hf_repo="allenai/reward-bench-2-results",
 )
 
+# Source metadata (shared)
+V1_SOURCE_METADATA = SourceMetadata(
+    source_name="RewardBench",
+    source_type="documentation",
+    source_organization_name="Allen Institute for AI",
+    source_organization_url="https://allenai.org",
+    evaluator_relationship=EvaluatorRelationship.third_party,
+)
+
+V2_SOURCE_METADATA = SourceMetadata(
+    source_name="RewardBench 2",
+    source_type="documentation",
+    source_organization_name="Allen Institute for AI",
+    source_organization_url="https://allenai.org",
+    evaluator_relationship=EvaluatorRelationship.third_party,
+)
+
 # RewardBench v1 metrics with descriptions
 V1_METRICS = {
     "Score": "Overall RewardBench Score",
@@ -74,6 +101,53 @@
 ]
 
 
+def _make_eval_result(
+    name: str,
+    score: float,
+    description: str,
+    source_data: SourceDataHf,
+) -> EvaluationResult:
+    """Create an EvaluationResult for a continuous 0-1 metric."""
+    return EvaluationResult(
+        evaluation_name=name,
+        source_data=source_data,
+        metric_config=MetricConfig(
+            evaluation_description=description,
+            lower_is_better=False,
+            score_type=ScoreType.continuous,
+            min_score=0.0,
+            max_score=1.0,
+        ),
+        score_details=ScoreDetails(score=round(score, 4)),
+    )
+
+
+def _make_model_info(
+    model_name: str,
+    developer: str,
+    additional_details: Optional[Dict[str, Any]] = None,
+) -> ModelInfo:
+    """Create ModelInfo without setting inference_platform."""
+    model_id = get_model_id(model_name, developer)
+    return ModelInfo(
+        name=model_name,
+        id=model_id,
+        developer=developer,
+        additional_details=additional_details,
+    )
+
+
+def _save_eval_log(eval_log: EvaluationLog, developer: str, model: str) -> Path:
+    """Save an evaluation log to the standard directory structure."""
+    dir_path = OUTPUT_DIR / sanitize_filename(developer) / sanitize_filename(model)
+    dir_path.mkdir(parents=True, exist_ok=True)
+
+    filepath = dir_path / f"{uuid.uuid4()}.json"
+    json_str = eval_log.model_dump_json(indent=2, exclude_none=True)
+    filepath.write_text(json_str)
+    return filepath
+
+
 def extract_model_name_from_html(html_string: str) -> str:
     """Extract the model name from an HTML anchor tag."""
     pattern = r">([^<]+)<"
@@ -122,7 +196,7 @@ def fetch_rewardbench_v1(retrieved_timestamp: str) -> int:
             score = parse_score(row.get(metric_name, ""))
             if score is not None:
                 eval_results.append(
-                    make_evaluation_result(
+                    _make_eval_result(
                         name=metric_name,
                         score=score,
                         description=description,
@@ -134,7 +208,7 @@ def fetch_rewardbench_v1(retrieved_timestamp: str) -> int:
             continue
 
         # Build model info
-        model_info = make_model_info(
+        model_info = _make_model_info(
             model_name=model_name,
             developer=developer,
             additional_details={"model_type": model_type} if model_type else None,
@@ -146,12 +220,7 @@ def fetch_rewardbench_v1(retrieved_timestamp: str) -> int:
             schema_version=SCHEMA_VERSION,
             evaluation_id=evaluation_id,
             retrieved_timestamp=retrieved_timestamp,
-            source_metadata=make_source_metadata(
-                source_name="RewardBench",
-                organization_name="Allen Institute for AI",
-                organization_url="https://allenai.org",
-                evaluator_relationship=EvaluatorRelationship.third_party,
-            ),
+            source_metadata=V1_SOURCE_METADATA,
             model_info=model_info,
             evaluation_results=eval_results,
         )
@@ -162,7 +231,7 @@ def fetch_rewardbench_v1(retrieved_timestamp: str) -> int:
         else:
             dev, model = "unknown", model_info.id
 
-        filepath = save_evaluation_log(eval_log, OUTPUT_DIR, dev, model)
+        filepath = _save_eval_log(eval_log, dev, model)
         print(f"Saved: {filepath}")
         count += 1
 
@@ -219,7 +288,7 @@ def fetch_rewardbench_v2(retrieved_timestamp: str) -> int:
                         score = float(model_data[metric_name])
                         scores_for_average.append(score)
                         eval_results.append(
-                            make_evaluation_result(
+                            _make_eval_result(
                                 name=metric_name,
                                 score=score,
                                 description=description,
@@ -237,7 +306,7 @@ def fetch_rewardbench_v2(retrieved_timestamp: str) -> int:
                 mean_score = sum(scores_for_average) / len(scores_for_average)
                 eval_results.insert(
                     0,
-                    make_evaluation_result(
+                    _make_eval_result(
                         name="Score",
                         score=mean_score,
                         description="Overall RewardBench 2 Score (mean of all metrics)",
@@ -246,7 +315,7 @@ def fetch_rewardbench_v2(retrieved_timestamp: str) -> int:
                 )
 
             # Build model info
-            model_info = make_model_info(
+            model_info = _make_model_info(
                 model_name=model_name,
                 developer=developer,
                 additional_details={"model_type": model_type} if model_type else None,
@@ -258,12 +327,7 @@ def fetch_rewardbench_v2(retrieved_timestamp: str) -> int:
                 schema_version=SCHEMA_VERSION,
                 evaluation_id=evaluation_id,
                 retrieved_timestamp=retrieved_timestamp,
-                source_metadata=make_source_metadata(
-                    source_name="RewardBench 2",
-                    organization_name="Allen Institute for AI",
-                    organization_url="https://allenai.org",
-                    evaluator_relationship=EvaluatorRelationship.third_party,
-                ),
+                source_metadata=V2_SOURCE_METADATA,
                 model_info=model_info,
                 evaluation_results=eval_results,
             )
@@ -274,7 +338,7 @@ def fetch_rewardbench_v2(retrieved_timestamp: str) -> int:
             else:
                 dev, model = "unknown", model_info.id
 
-            filepath = save_evaluation_log(eval_log, OUTPUT_DIR, dev, model)
+            filepath = _save_eval_log(eval_log, dev, model)
             print(f"    Saved: {filepath}")
             count += 1
 
diff --git a/scripts/utils/__init__.py b/scripts/utils/__init__.py
index 08b5f76fb..0ce4c3702 100644
--- a/scripts/utils/__init__.py
+++ b/scripts/utils/__init__.py
@@ -4,15 +4,11 @@
 from .fetch import fetch_json, fetch_csv, FetchError
 from .io import save_evaluation_log, generate_output_path, sanitize_filename
 from .schema import (
-    SCHEMA_VERSION,
     make_metric_config,
     make_evaluation_result,
     make_source_metadata,
     make_model_info,
     make_evaluation_log,
-    make_source_data_url,
-    make_source_data_hf,
-    make_source_data_private,
 )
 
 __all__ = [
@@ -28,13 +24,9 @@
     "generate_output_path",
     "sanitize_filename",
     # schema.py
-    "SCHEMA_VERSION",
     "make_metric_config",
     "make_evaluation_result",
     "make_source_metadata",
     "make_model_info",
     "make_evaluation_log",
-    "make_source_data_url",
-    "make_source_data_hf",
-    "make_source_data_private",
 ]
diff --git a/scripts/utils/schema.py b/scripts/utils/schema.py
index 870ba208a..08d66e4ac 100644
--- a/scripts/utils/schema.py
+++ b/scripts/utils/schema.py
@@ -1,7 +1,7 @@
 """Schema construction helpers for building evaluation logs."""
 
 import time
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, List, Optional
 
 from eval_types import (
     EvaluationLog,
@@ -11,88 +11,11 @@
     ModelInfo,
     ScoreDetails,
     ScoreType,
-    SourceDataHf,
-    SourceDataPrivate,
-    SourceDataUrl,
     SourceMetadata,
 )
 
 from .developer import get_developer, get_model_id
 
-# Schema version constant
-SCHEMA_VERSION = "0.2.0"
-
-# Type alias for source data variants
-SourceData = Union[SourceDataUrl, SourceDataHf, SourceDataPrivate]
-
-
-def make_source_data_url(
-    dataset_name: str,
-    url: List[str],
-    **additional_details: Any,
-) -> SourceDataUrl:
-    """
-    Create a SourceDataUrl for URL-based evaluation data sources.
-
-    Args:
-        dataset_name: Name of the source dataset
-        url: List of URL(s) for the source of the evaluation data
-        **additional_details: Additional metadata key-value pairs
-
-    Returns:
-        Configured SourceDataUrl instance
-    """
-    return SourceDataUrl(
-        dataset_name=dataset_name,
-        source_type="url",
-        url=url,
-    )
-
-
-def make_source_data_hf(
-    dataset_name: str,
-    hf_repo: Optional[str] = None,
-    hf_split: Optional[str] = None,
-    samples_number: Optional[int] = None,
-) -> SourceDataHf:
-    """
-    Create a SourceDataHf for HuggingFace dataset sources.
-
-    Args:
-        dataset_name: Name of the source dataset
-        hf_repo: HuggingFace repository identifier
-        hf_split: Dataset split (train, val, or test)
-        samples_number: Number of samples in the dataset
-
-    Returns:
-        Configured SourceDataHf instance
-    """
-    return SourceDataHf(
-        dataset_name=dataset_name,
-        source_type="hf_dataset",
-        hf_repo=hf_repo,
-        hf_split=hf_split,
-        samples_number=samples_number,
-    )
-
-
-def make_source_data_private(
-    dataset_name: str,
-) -> SourceDataPrivate:
-    """
-    Create a SourceDataPrivate for private/custom dataset sources.
-
-    Args:
-        dataset_name: Name of the source dataset
-
-    Returns:
-        Configured SourceDataPrivate instance
-    """
-    return SourceDataPrivate(
-        dataset_name=dataset_name,
-        source_type="other",
-    )
-
 
 def make_metric_config(
     description: str,
@@ -141,7 +64,6 @@ def make_evaluation_result(
     name: str,
     score: float,
     description: str,
-    source_data: SourceData,
     lower_is_better: bool = False,
     score_type: ScoreType = ScoreType.continuous,
     min_score: float = 0.0,
@@ -158,7 +80,6 @@ def make_evaluation_result(
         name: Name of the evaluation (e.g., "MMLU", "GSM8K")
         score: The score value
         description: Human-readable description of what this measures
-        source_data: Source dataset information (URL, HuggingFace, or private)
         lower_is_better: Whether lower scores are better
         score_type: Type of score
         min_score: Minimum possible score
@@ -171,7 +92,6 @@ def make_evaluation_result(
     """
     return EvaluationResult(
         evaluation_name=name,
-        source_data=source_data,
         metric_config=make_metric_config(
             description=description,
             lower_is_better=lower_is_better,
@@ -219,7 +139,7 @@ def make_source_metadata(
 def make_model_info(
     model_name: str,
     developer: Optional[str] = None,
-    inference_platform: Optional[str] = None,
+    inference_platform: str = "unknown",
     additional_details: Optional[Dict[str, Any]] = None,
 ) -> ModelInfo:
     """
@@ -230,7 +150,7 @@ def make_model_info(
     Args:
         model_name: Name of the model
         developer: Optional developer override
-        inference_platform: Optional platform used for inference
+        inference_platform: Platform used for inference
         additional_details: Extra model metadata
 
     Returns:
@@ -252,12 +172,13 @@ def make_evaluation_log(
     source_name: str,
     model_name: str,
     evaluation_results: List[EvaluationResult],
+    source_data: List[str],
     organization_name: str,
     source_type: str = "documentation",
     evaluator_relationship: EvaluatorRelationship = EvaluatorRelationship.third_party,
     organization_url: Optional[str] = None,
     developer: Optional[str] = None,
-    inference_platform: Optional[str] = None,
+    inference_platform: str = "unknown",
     model_additional_details: Optional[Dict[str, Any]] = None,
     retrieved_timestamp: Optional[str] = None,
 ) -> EvaluationLog:
@@ -269,13 +190,14 @@ def make_evaluation_log(
     Args:
         source_name: Name of the evaluation source
         model_name: Name of the model being evaluated
-        evaluation_results: List of evaluation results (each must include source_data)
+        evaluation_results: List of evaluation results
+        source_data: URLs or dataset info for the source data
         organization_name: Organization providing the evaluation
         source_type: Either "documentation" or "evaluation_run"
         evaluator_relationship: Relationship to model developer
         organization_url: Optional URL for the organization
         developer: Optional developer override
-        inference_platform: Optional platform used for inference
+        inference_platform: Platform used for inference
         model_additional_details: Extra model metadata
         retrieved_timestamp: Optional timestamp override
 
@@ -291,9 +213,10 @@ def make_evaluation_log(
     evaluation_id = f"{source_name}/{sanitized_model_id}/{timestamp}"
 
     return EvaluationLog(
-        schema_version=SCHEMA_VERSION,
+        schema_version="0.1.0",
         evaluation_id=evaluation_id,
         retrieved_timestamp=timestamp,
+        source_data=source_data,
         source_metadata=make_source_metadata(
             source_name=source_name,
             organization_name=organization_name,