decisive-dory / nvfp4 /calibration-inputs.json
rdaum's picture
Replace NVFP4 with NVIDIA Model Optimizer local-Hessian quantization
9d9e572 verified
Raw History Blame Contribute Delete
52.4 kB
{
"source": "Training split; disjoint from validation by question ID and source group",
"sha256": "4d28d1a5620d7dad7694518d0da01d85aea2e81f175ce9ff053370c9f7519d90",
"seed": 421,
"rows": [
{
"id": "state-v1/helpsteer2/67bf4b5c05cd5849e99cc78c3c401aa7f1d09fb2685767e0d5e7f7bd122c1542",
"group_id": "state-v1/helpsteer2/19e62c3a0704c0077e10f0dc94a7ba7b5caeee7001af46fc599657bda5b48f0f",
"tokens": 874
},
{
"id": "state-v1/helpsteer2/e78ec129f452828c39dd2f22c0c5cd1c0535137c3421aea01d5ea428c82b844c/correctness",
"group_id": "state-v1/helpsteer2/30f6a64b7cc99fa2657cefa601df7101e568694758d83d6d08a806b1f755b231",
"tokens": 706
},
{
"id": "state-v1/planning/5aa64991b93618e50a49035236dda437ad29c49e6354ef795f3063abfff3c7a5/best",
"group_id": "state-v1/planning/91ce8ba800186258cb5296a8b530d2465cc3cd4cedb6d18a5a1fb7122860dee9",
"tokens": 364
},
{
"id": "state-v1/planning/9ea093996434082939cf2f7c7ece343876dd887388a934d6442eb88690c2aead/progress",
"group_id": "state-v1/planning/96ba254067662441254984ac30d567f363c23c335877c147c5ed7055445054e3",
"tokens": 246
},
{
"id": "community-diversity-v2/20260921/rubric_judge/comparison_fairness/46/1/choice",
"group_id": "community-diversity-v2/20260921/rubric_judge/comparison_fairness/46",
"tokens": 705
},
{
"id": "v3_817bb20adf77be86_n",
"group_id": "973531833877a9ab0fde7232d224193973eb7ee063161718a418092661b56d8b",
"tokens": 133
},
{
"id": "community-diversity-v2/20260921/rag/contradiction_resolution/63/2/score",
"group_id": "community-diversity-v2/20260921/rag/contradiction_resolution/63",
"tokens": 761
},
{
"id": "state-v1/scone/train-1511/5/position",
"group_id": "state-v1/scone/27a701502841969b5cddcb114503f8824c9d50e53230a5552e9cae7cc2c6228e",
"tokens": 249
},
{
"id": "state-v1/scone/train-D10907/5/colour",
"group_id": "state-v1/scone/f08fe219679748214875c96049021b9b12225daa8b78900e9029184d4a4d0047",
"tokens": 273
},
{
"id": "state-v1/scone/train-D11210/3/amount",
"group_id": "state-v1/scone/6cf1a66eba2a9b308c61d061d740bf7acbe64dcab93fcb8d53c4e99979ff80dc",
"tokens": 257
},
{
"id": "state-v1/helpsteer2/1f0a410cf917cd98476066ba5f1ff33dcf3f37dfa8fe4e8922c18c0fbf19a5e5",
"group_id": "state-v1/helpsteer2/90f6f8b1b6adf86ff0216c7aa64042cc1d2905653045fbe8816b1fd45c93e48a",
"tokens": 838
},
{
"id": "state-v1/helpsteer2/b32e0585cce9073f22bd14e7c9e016674c0a3acf1d05eb4172fb443b09762952/correctness",
"group_id": "state-v1/helpsteer2/dee9d86730a24f845bab5fa1f5255bb14effdf2ea1297a9e41cd0c43097257f9",
"tokens": 561
},
{
"id": "state-v1/planning/f89c1beab8398d093b8476ae4d4d1756920e050a5bd0d17a5b432ac5b42db916/best",
"group_id": "state-v1/planning/6a120e4e31bb9f09aac64d36ccb8152cc27f9e4b18838faebeeb530039878026",
"tokens": 254
},
{
"id": "state-v1/planning/5324597f7700b9362e164f7f63975f5dba4138166d1ec4c74ce83c458ea8f0f7/legal",
"group_id": "state-v1/planning/cae62cbc8c9147030506c49a6a4404db152a633598e441560f4adf087aac751a",
"tokens": 225
},
{
"id": "actions-v1/scienceworld/task-2a-test-conductivity-of-unknown-substances/168/22",
"group_id": "actions-v1/scienceworld/task-2a-test-conductivity-of-unknown-substances/168",
"tokens": 640
},
{
"id": "v3_426a54b3d66b7832_n",
"group_id": "f9fceb7df9890d7e36f7015ffb065abb20056e883444a3a5253c220ac4369024",
"tokens": 134
},
{
"id": "procedural/record_eligibility:train:5295/eligible_count",
"group_id": "record_eligibility:train:5295",
"tokens": 492
},
{
"id": "state-v1/scone/train-2008/4/position",
"group_id": "state-v1/scone/827e80117560b7e4cf38311f08ec6a4eb13a0deb8c0c918a32fbd67253c0545d",
"tokens": 249
},
{
"id": "state-v1/scone/train-C9545/3/colour",
"group_id": "state-v1/scone/081b7656100b5940296558c9501c44c54ea3936dcb7de8912960cd7824ac9a01",
"tokens": 253
},
{
"id": "state-v1/scone/train-C11352/3/amount",
"group_id": "state-v1/scone/289e1edd2cf93d49d6fb8d1cff69eb422f4d8527810bfdf2a13752e14061b52f",
"tokens": 245
},
{
"id": "state-v1/helpsteer2/6c4b48c442dfeccb87a89c4e3785cc59e66cc89b1c5ed3485951d11ad4970a25",
"group_id": "state-v1/helpsteer2/b9e52bd8e012f06ee669a1d32bd3046ccbea8c16d20b501f044b81339ac9c25c",
"tokens": 474
},
{
"id": "state-v1/helpsteer2/9b28f225fd8fb7867f9ad87e8789a9785c225ccb48ef1868b5f94b54e17c4c27/helpfulness",
"group_id": "state-v1/helpsteer2/086bed6f0ee3325e3825e45e32a296f5a102be016d4b009b1e895d165d3dd769",
"tokens": 1000
},
{
"id": "state-v1/planning/92725422fa062c870631054c43e5fb3b94595121e040c8a070ea901fe4f20e81/best",
"group_id": "state-v1/planning/06ab3362eb49f65ec6b1b8dba355f14aa870db145f329de3cdf1ad8a3c2e706e",
"tokens": 271
},
{
"id": "state-v1/planning/ae7ffb91015a19d1f55bb97d0b8c06308f0ec4cf596717e3e9be54e8d26cd04f/legal",
"group_id": "state-v1/planning/762cbcb12be99b498532c71a1fe92019ab7b0fb1cda6fd056083155a819bfac2",
"tokens": 230
},
{
"id": "actions-v1/alfworld/21069",
"group_id": "actions-v1/alfworld/f1418b88372191bdb67990a21c4e7045bd88c4b574ceccabe4452dc3f58c6a85",
"tokens": 495
},
{
"id": "v3_b194acd8dcce0318_n",
"group_id": "c61b9b9cbe45187dc12353563b6b1ed107777e7e423cd783e699c9436371d625",
"tokens": 132
},
{
"id": "community-diversity-v2/20260921/ir/connecting_route/79/0/score",
"group_id": "community-diversity-v2/20260921/ir/connecting_route/79",
"tokens": 751
},
{
"id": "state-v1/scone/train-2852/1/position",
"group_id": "state-v1/scone/57675a89bd6a9101bd76efc5682fc5755ae04f73d271b5f22687a7ae56bc350f",
"tokens": 227
},
{
"id": "state-v1/scone/train-C10818/2/colour",
"group_id": "state-v1/scone/34018762974095effb533953ea86820e2ee799b7eac9fdab66638f0532a3eaa7",
"tokens": 215
},
{
"id": "state-v1/scone/train-D10269/1/amount",
"group_id": "state-v1/scone/8818b72bcf7095470f66a76facea90334cd8c0ad2dd822ce99ce86e07d9794d3",
"tokens": 250
},
{
"id": "state-v1/helpsteer2/de18fa6562264d1fcba2f4c8d49a6f7a983f6e3d4412c5d48f8d1dc121ea9327",
"group_id": "state-v1/helpsteer2/a15095d9a4eb0b703b15f53f8d5b69a6cc34bd49d6dfb4b70fc68ccb60ed0ad0",
"tokens": 547
},
{
"id": "state-v1/helpsteer2/606c0080222f41c4486a145dc304b03248998c9e3b2c4e937ec80747bae67a3b/helpfulness",
"group_id": "state-v1/helpsteer2/eea17afeaba187666dfbcd39933f3e08a236e9c878f87e7eabd0d69c653dfdb6",
"tokens": 793
},
{
"id": "state-v1/planning/6a80b6d69e7a8df311656de49ad7a06fb2bbbd03a6775cc4c33d2864ea8c8e3b/best",
"group_id": "state-v1/planning/a291aa7d7d4d8d907233f4b236f1972ab91bf1a6887b7018e93c8507b1420f5a",
"tokens": 282
},
{
"id": "state-v1/planning/176a17bf1044e58fd7eba838ecc1f7eca85c8afbe611796c726783255e2b13a2/legal",
"group_id": "state-v1/planning/5ccb3e9615c895fb9283de719ae6b335f9d05e570b4b460da78be9bb4a6d016a",
"tokens": 245
},
{
"id": "reasoning-control-v1:76109:108:decision",
"group_id": "reasoning-control-v1:76109:108",
"tokens": 438
},
{
"id": "community-diversity-v2/20260921/support/refund_window/17/3/noul",
"group_id": "community-diversity-v2/20260921/support/refund_window/17",
"tokens": 760
},
{
"id": "v3_97dbedd905083b1f_s",
"group_id": "5b2a33e39a557520f5782330dca9b43c6d24f4356cc05bf038015d20ed28c015",
"tokens": 183
},
{
"id": "state-v1/scone/train-2904/2/position",
"group_id": "state-v1/scone/5d1d05558d792186340eb3561d413b4ad03dba83e0139826cc202b3cba157d5d",
"tokens": 231
},
{
"id": "state-v1/scone/train-5314/3/present",
"group_id": "state-v1/scone/9fb89a3d32ebd91cbd8d23dc147fee349400053db9d55d2c952a04bf907d52b8",
"tokens": 179
},
{
"id": "state-v1/scone/train-D11101/5/amount",
"group_id": "state-v1/scone/053d5508957ae327345909dca7d034c2f17a440b9c7a580d436d43f1522d5d9b",
"tokens": 294
},
{
"id": "state-v1/helpsteer2/5398564672a302cb1df209e17628f98604b8936e7f70eec712270867fbb4c4f8",
"group_id": "state-v1/helpsteer2/92884a647e7920c97c688ef33b01de67ebe3d7b1d5096d9d4cbb6caf53d78b6d",
"tokens": 621
},
{
"id": "state-v1/helpsteer2/84d7fffba18a618f9827c9e5f9e917f9674bf4df3fc22c891afdf4caaaeb7111/helpfulness",
"group_id": "state-v1/helpsteer2/f7627dd148d270b2e8c6812a85948bde2179bb75d692b81c875ec52e51c29465",
"tokens": 540
},
{
"id": "state-v1/planning/26759b1a17412b8f1f1ff71e32f11669c9bd544da17d50443b10c43cebcffec5/best",
"group_id": "state-v1/planning/9d7f05cd478b689edd8780fe0676aa0010b55e1376c5966b9064b8ddddce1679",
"tokens": 261
},
{
"id": "state-v1/planning/5935d8feec1e5cc54d6612ce761c18b35b65c2a04b2198d454d3eb9e7ca4bba4/progress",
"group_id": "state-v1/planning/65ee3cf6e50470ae1199b181126824f6fca552a6b0f1b98b04381430a6348056",
"tokens": 238
},
{
"id": "v3_ecc64052614d5ec4_c",
"group_id": "ed88351105c7fd564c6e4bcb8cb83f352b12851b53cfa1f9388a4340b6f5f7d5",
"tokens": 165
},
{
"id": "v3_857b58c3d98444ea_n",
"group_id": "62cc370c5a1c76aeaebf00a3703023c7115e4a3cbc28571991ad81af9dd904bb",
"tokens": 136
},
{
"id": "procedural/event_state_reconstruction:train:6319/current_severity",
"group_id": "event_state_reconstruction:train:6319",
"tokens": 213
},
{
"id": "state-v1/scone/train-1337/1/position",
"group_id": "state-v1/scone/ba1de3771b5d9620b63fa9fc52555a3b3a77c315b3a47abf9f49b41ad8001de0",
"tokens": 226
},
{
"id": "state-v1/scone/train-C10665/3/colour",
"group_id": "state-v1/scone/d82112dcef351a0cfb4f0295cc6353f5ae357ededbd2d2862a5aabbabfd2c8da",
"tokens": 231
},
{
"id": "state-v1/scone/train-C10268/3/amount",
"group_id": "state-v1/scone/383d0470ec791d724595c1b87174f9e11685dd8e51f0a7b0eff67045949eb7fb",
"tokens": 264
},
{
"id": "state-v1/helpsteer2/0c53b425970dab03c6c7d4e23ac0ba4e6dd95dd0421bbed39b045196dcdcb212",
"group_id": "state-v1/helpsteer2/7b58fbe0a2641a6f780917432d47a232457e1972ce62d84ece6c083a16eb5b2b",
"tokens": 886
},
{
"id": "state-v1/helpsteer2/6e8acf007b82226084e059afab0b1bbfa9d27c82335636da9d9782f16a8eaac1/coherence",
"group_id": "state-v1/helpsteer2/14f06d6345cff67527864388d71035d246e54c387078810694e224e873599aba",
"tokens": 321
},
{
"id": "state-v1/planning/ec6544277b0b87bd918c4e1c464f6c7f2e6fc5267388adf47c5afce06738d6ae/best",
"group_id": "state-v1/planning/3ed7548dff9ae0dc1f8c451c9db5347f24b79f024133e6f8132ee1550a468ec8",
"tokens": 298
},
{
"id": "state-v1/planning/e9d6569bb86017b1204493be9ef58b7b29f8d186dce44d0c53bd980788e7b59b/legal",
"group_id": "state-v1/planning/75a2ee3a72f422a7d3a59e9a93e7f737e134a1ab269a7bb82c21ded79d01a1d2",
"tokens": 227
},
{
"id": "community-diversity-v2/20260921/ir/inventory_answer/0/0/choice",
"group_id": "community-diversity-v2/20260921/ir/inventory_answer/0",
"tokens": 644
},
{
"id": "community-diversity-v2/20260921/ir/connecting_route/66/2/noul",
"group_id": "community-diversity-v2/20260921/ir/connecting_route/66",
"tokens": 751
},
{
"id": "v3_fbe75097ee4b541a_s",
"group_id": "7f9d20a2939437ab00f9af9d03346eed763e23574f10feb8cfc1ff63dce940ec",
"tokens": 178
},
{
"id": "state-v1/scone/train-2760/2/position",
"group_id": "state-v1/scone/30ff165e747d43e3a44a0b22000b6782ed74c95fecadc29fb9b21a8d310df7b4",
"tokens": 233
},
{
"id": "state-v1/scone/train-3478/4/present",
"group_id": "state-v1/scone/2e710dd6ee1a77ce6aaa67522fd6749c7db95a351e1b3722fb6d9b5ddce9eede",
"tokens": 175
},
{
"id": "state-v1/scone/train-B21565/4/amount",
"group_id": "state-v1/scone/63663a384da186597b744f8868f27caa4b8601718452934598a55f717ba49cb8",
"tokens": 272
},
{
"id": "state-v1/helpsteer2/a9be190e37d6d9806e63b421c4ecc326f85c702b4211295b8e8581b65c7012a1",
"group_id": "state-v1/helpsteer2/18ee24150dcb1d96752a4d6dd0f20dfd8ba8c38527e40aa8509b7adecf78f9c6",
"tokens": 190
},
{
"id": "state-v1/helpsteer2/e830d45d303719a366a70744f66344c2d61a6261955b00b2a005ada2d32230bb/coherence",
"group_id": "state-v1/helpsteer2/8b74b2816b945af47217a8da062e608513ea4b46db51b02867b0b5538dc99d69",
"tokens": 900
},
{
"id": "state-v1/planning/d815613389173b1c6b0bd8157bf9509d1bf52a47944146abbab1566f00537d3e/best",
"group_id": "state-v1/planning/aa63b4302e029fa374f0b2959c57e64f72d1412e2babb3ccba30b629750c1eed",
"tokens": 270
},
{
"id": "state-v1/planning/5f7dcaa72bf929325b10eb05c82c2e035517c1b0aee50b0fd438e9f94f75c32a/progress",
"group_id": "state-v1/planning/c11eb088f0d0b7576df46565f1309bb20627641d13558270e133c2ac8b6f847f",
"tokens": 248
},
{
"id": "actions-v1/alfworld/20724",
"group_id": "actions-v1/alfworld/c20d214b25f18b10fdd7dc2d0f440151a28ab3993e5745f62dff22de17d5af03",
"tokens": 592
},
{
"id": "procedural/event_state_reconstruction:train:4721/is_open",
"group_id": "event_state_reconstruction:train:4721",
"tokens": 250
},
{
"id": "v3_314cec29e88714c9_s",
"group_id": "3b45c48e5d8d99dcfb5a2eb321c2e26ca1190faca9e61dfe4eea52ed6fa94bdd",
"tokens": 183
},
{
"id": "state-v1/scone/train-5307/3/position",
"group_id": "state-v1/scone/d7d64e6968ec6ef563e891d68faafdab2eaedda6ea5e660be02f40b15f9084b0",
"tokens": 252
},
{
"id": "state-v1/scone/train-B21455/4/colour",
"group_id": "state-v1/scone/5a88aec83fd8c1fa48ab16b46ce362849d6da81a64fcab35143a32ed2aa5680f",
"tokens": 251
},
{
"id": "state-v1/scone/train-C9471/3/amount",
"group_id": "state-v1/scone/375870554561b8098e0c6bf5a74c2eaf3519d0f89fc2551b6592842be54f934d",
"tokens": 278
},
{
"id": "state-v1/helpsteer2/55e067c790d7e407308b9624921ab0712b94a26b51fcea5dc7be8bba3280e1fa",
"group_id": "state-v1/helpsteer2/65177d1e46a6032471bd6215561dd19a3637e89f793489232808a433072a928c",
"tokens": 787
},
{
"id": "state-v1/helpsteer2/aa04598190a461c7eb4720772bd05e539f04d25c8aed1d6dae9057aac0057a3d/helpfulness",
"group_id": "state-v1/helpsteer2/8867b407c27776d3f6719dbd9807df4ba3f105ee6b79c0dca128da35ccce2edd",
"tokens": 592
},
{
"id": "state-v1/planning/21264432e02df5aae2fd1e4140bd51156b3de30881e697c2899c7dd9b45a6d5a/best",
"group_id": "state-v1/planning/f161afefd3168e8edcec8ec8a616536a8c2e0267dfe65bcd766559f3fa5d79db",
"tokens": 368
},
{
"id": "state-v1/planning/71d79ea561249689a076ae15b430f23e3740820a39ebfbd2eaa50ebf5b4e34ae/progress",
"group_id": "state-v1/planning/e45e270c812783c83d1b12abebdd583114d50a05655f502daadef6ada4e3941a",
"tokens": 245
},
{
"id": "actions-v1/alfworld/18084",
"group_id": "actions-v1/alfworld/5c62fecffe2d4435fc3427cef269d3884280fbd868635341b26f2bb6ef0d6925",
"tokens": 393
},
{
"id": "procedural/record_aggregation:train:9187/any_out_of_stock",
"group_id": "record_aggregation:train:9187",
"tokens": 151
},
{
"id": "v3_7fe9b80a5659e973_s",
"group_id": "e1efcb940bb843298475f449d92f40a01b3331aee151006a1192c954fa818cd9",
"tokens": 186
},
{
"id": "state-v1/scone/train-4741/4/position",
"group_id": "state-v1/scone/743a78d10d57b2e3fdb5a62525761c86b6d32eaf0b689c3d7b8d2d447b1bcd70",
"tokens": 238
},
{
"id": "state-v1/scone/train-2439/2/present",
"group_id": "state-v1/scone/97710c8377288c2261a1ee4354d0acef69fa658b86e4d89e9670bef0c67ec4ee",
"tokens": 160
},
{
"id": "state-v1/scone/train-D11150/3/amount",
"group_id": "state-v1/scone/8e9f26ba3e2964cf24619de409c0de9051caa19a9344851d9a963eba32fe28ed",
"tokens": 271
},
{
"id": "state-v1/helpsteer2/be91a563c48b9edb286fa8bee4c6a7e5fba6ad4cf5afd02cf181bae33d624ac6",
"group_id": "state-v1/helpsteer2/c84c0b1efc018fd4c5d29919280b64cc4ca42b4edd4318d40ef845d4419519e4",
"tokens": 574
},
{
"id": "state-v1/helpsteer2/1d7d74cd33c69db879fb2c17d4bfa15eadeff6fcc0d4327940d7a9f3dc138264/coherence",
"group_id": "state-v1/helpsteer2/03ad1ac7d94b8d5e01ee51089018443233cb73ad6ae4c0f4c1d9e21613509f4a",
"tokens": 820
},
{
"id": "state-v1/planning/94039a7213fddc598f33568bdbdd4fdcb3e18cd50ff439c12723843aea976d19/best",
"group_id": "state-v1/planning/f77d76acb54365179e98c1b92ad01380337c3900a00b1ff253188a71eb6ac7eb",
"tokens": 298
},
{
"id": "state-v1/planning/71d6a7c1f4a9f68e3de041ef7dedf21d2ddc589e8eb4e32fba2202a69cc6506e/legal",
"group_id": "state-v1/planning/165230566d46d75538059ee613b43cf68fde552b50beab9e6cd1d332683764ca",
"tokens": 245
},
{
"id": "reasoning-control-v1:76109:1221:decision",
"group_id": "reasoning-control-v1:76109:1221",
"tokens": 439
},
{
"id": "community-diversity-v2/20260921/rubric_judge/unit_conversion/75/1/noul",
"group_id": "community-diversity-v2/20260921/rubric_judge/unit_conversion/75",
"tokens": 687
},
{
"id": "reasoning-control-v1:76109:1594:ordinal",
"group_id": "reasoning-control-v1:76109:1594",
"tokens": 224
},
{
"id": "state-v1/scone/train-4084/4/position",
"group_id": "state-v1/scone/4c1dfa21c782628c1a17876197cc4a1e858029458a1f13849341c7f9417c5743",
"tokens": 255
},
{
"id": "state-v1/scone/train-C10866/3/colour",
"group_id": "state-v1/scone/f8f505cfd3f6f996efa5d3528438b07e0a7562ff2ce4e3213fac0e295a4f5f66",
"tokens": 238
},
{
"id": "state-v1/scone/train-C9602/4/amount",
"group_id": "state-v1/scone/36a3afcf00cf7a53cb35874e5b1643df507266a5b2b1d7a8c4e4362f4aaef63a",
"tokens": 290
},
{
"id": "state-v1/helpsteer2/5f46e7c52bbb395d0b1d7cfd631687f55301510e72d4bf079e1cdb218712eda9",
"group_id": "state-v1/helpsteer2/0f65c3a392cac342d48695ca2c3506ca1241b819ced8cde8e7c10f37d7b7d53d",
"tokens": 353
},
{
"id": "state-v1/helpsteer2/f810ba9abecca19ba8b925c00216d57f4ba6adc14e535a5a0a7dba66a1af8a45/coherence",
"group_id": "state-v1/helpsteer2/59117a4c464be48e8de73e46e2828863cd7cd6039726e9db3a6a1e36e531766b",
"tokens": 415
},
{
"id": "state-v1/planning/50929b1c18a8c87b185b403dcd7fcc5f79ff6fed60443ec0d5d5225f9b25e050/best",
"group_id": "state-v1/planning/58160478279a215474f567cf2f79837aedb6e2cf681ebafe015f8608170ed02b",
"tokens": 289
},
{
"id": "state-v1/planning/891aeb50a38556b4dd6180857fa189c9f6a908f20e22cb6695cb501e3efdf96a/progress",
"group_id": "state-v1/planning/3f7a03aae70bc03eb80534c82c0f59549772fc71209959b2d56c1aa680a4fe52",
"tokens": 235
},
{
"id": "procedural/instruction_execution:train:2030/resolution",
"group_id": "instruction_execution:train:2030",
"tokens": 517
},
{
"id": "community-diversity-v2/20260921/games/projectile_dodge/40/0/noul",
"group_id": "community-diversity-v2/20260921/games/projectile_dodge/40",
"tokens": 767
},
{
"id": "community-diversity-v2/20260921/games/reload_cover/66/1/score",
"group_id": "community-diversity-v2/20260921/games/reload_cover/66",
"tokens": 741
},
{
"id": "state-v1/scone/train-1484/1/position",
"group_id": "state-v1/scone/ecd5165a02aa4eab3019917836cd09d68867889f3fb5612d915b9dff77858d5f",
"tokens": 224
},
{
"id": "state-v1/scone/train-2815/4/present",
"group_id": "state-v1/scone/515e9e9d71b1b28d1a38de994af19628faa0ae51ac6068ad8f1325ab64ebda4d",
"tokens": 189
},
{
"id": "state-v1/scone/train-C11098/3/amount",
"group_id": "state-v1/scone/ca0a3105b6771c85ebd9dc7a889dd71fa2c4040ac0531d96a44994150a7b2c87",
"tokens": 249
},
{
"id": "state-v1/helpsteer2/13a2958e5a8bf9c4c76c579d4fab7f183b6ec21cdf41a298ab8bacaaaeac55ab",
"group_id": "state-v1/helpsteer2/54c730147ee1e4a3dfe0510335b7df946666e488a865e74c5c440245e5c02776",
"tokens": 775
},
{
"id": "state-v1/helpsteer2/20ad6b2ca58042ee2cef349fa4dec01cada3bad28ade6d88be2d1de08be6e5f2/correctness",
"group_id": "state-v1/helpsteer2/f440f56517bd9b5aa20f09261f153655847a5d81dd308f6674eca05755bbb7b5",
"tokens": 841
},
{
"id": "state-v1/planning/135bc8d3e3cad73bd52d3d9852400f7363d849ea9d901f42ef17d61505d2bbce/best",
"group_id": "state-v1/planning/f09baecf02249e7c78d986431131f3383a1d097558ab35e7eef8448aaa56ae62",
"tokens": 266
},
{
"id": "state-v1/planning/4674fe32dd06b202e4c522e493b4459beb2c35000ae169cb0a4e9a62ed789936/legal",
"group_id": "state-v1/planning/8fc5f3f7d89bc6cffe660c9b81dd02115737a1709b69c45f902f6c413bc470b3",
"tokens": 247
},
{
"id": "actions-v1/scienceworld/task-1-melt/4/12",
"group_id": "actions-v1/scienceworld/task-1-melt/4",
"tokens": 776
},
{
"id": "procedural/taxonomy_routing:train:1305/belongs_to",
"group_id": "taxonomy_routing:train:1305",
"tokens": 613
},
{
"id": "procedural/arithmetic:train:8927/net_change",
"group_id": "arithmetic:train:8927",
"tokens": 170
},
{
"id": "state-v1/scone/train-2006/4/position",
"group_id": "state-v1/scone/5337e0dd085cf3a1ab6c613bcc84588407a95c8e5fd6eac09e7726bb9c0e125f",
"tokens": 244
},
{
"id": "state-v1/scone/train-D11414/4/colour",
"group_id": "state-v1/scone/964d8cecef43e134b08d26ee091520d820b066349736effeeff9da67289e12d4",
"tokens": 272
},
{
"id": "state-v1/scone/train-B21532/5/amount",
"group_id": "state-v1/scone/c3a662eddb3f57e0f31b7a4dfa488358c2d65f694620c73bd9b5e49797565f18",
"tokens": 279
},
{
"id": "state-v1/helpsteer2/4e094c32a734d6946e4b7954b35e121acacaa5c499cbfd8bdbbb314ec33f600a",
"group_id": "state-v1/helpsteer2/41b5090c628c343c96871f06142da8c73ee7f86b28bf013ba4b226f32f4ac84e",
"tokens": 844
},
{
"id": "state-v1/helpsteer2/aa821a83f3bf672994b1c4d1ffa3d749cb5266a75a6da47512cebcd0ae3e6dde/helpfulness",
"group_id": "state-v1/helpsteer2/9f3c4bc0a85516ba935552ad95ec93e9719b310cfb8babc791949757d37942b4",
"tokens": 723
},
{
"id": "state-v1/planning/9cf5a6c0fd82c6a98e48525ca3c248e73c41805b7bf8028de6848a8175b45fbf/best",
"group_id": "state-v1/planning/900cd5cf6aa46650f258f4599ba12cef00d9f7172fa5738393898da5b69d9e3d",
"tokens": 254
},
{
"id": "state-v1/planning/be5200cc52bf173764f4bc5909221cf4ff7ded9781ec075eb5d12a13ff30ab26/legal",
"group_id": "state-v1/planning/1d57f3ef34dc4a94de94521bb6c5197f7291b52cb2a156d730d40048dae7dd67",
"tokens": 231
},
{
"id": "actions-v1/alfworld/456",
"group_id": "actions-v1/alfworld/6c4b0de55f907af1c16361075368241805dfc92e3d141b94fba9efae28c095ac",
"tokens": 423
},
{
"id": "v3_4581267193470c7f_n",
"group_id": "be0eca2ebe053a4d3cd060e27283ebda813469f1b9951ef3cad50c19383445e3",
"tokens": 135
},
{
"id": "v3_2cea7a72409074b8_s",
"group_id": "49f88cc8f60618d7c283e76f3a44816fe42cc3f468a55cd1403b5d98d67f8710",
"tokens": 183
},
{
"id": "state-v1/scone/train-4500/2/position",
"group_id": "state-v1/scone/eb6f784cf811c83e170f8598a735cc4708be66a7c922199e96fbe07cc9a06e3b",
"tokens": 242
},
{
"id": "state-v1/scone/train-D11582/5/colour",
"group_id": "state-v1/scone/d256a3ff3234e41e15fe2aaee32b26b6ec2b75c2a5cd02c19b9d7d8b4008b31e",
"tokens": 226
},
{
"id": "state-v1/scone/train-D11396/3/amount",
"group_id": "state-v1/scone/fd7147038073d24e929e6ab9a5abc5a4759fde2bf5b7a4bb68ba0359d5a3e22c",
"tokens": 260
},
{
"id": "state-v1/helpsteer2/63e10f8838cce3f243ea844040600586ef37cb3de77d6d9dd424c53a538d147c",
"group_id": "state-v1/helpsteer2/8c5957f260bf7eca9515ff891fc72bb8bb3100abc3c29cc039148d5b77b9e65b",
"tokens": 669
},
{
"id": "state-v1/helpsteer2/255dcc494a554f7d07c59fb81ef2e7e709c9340ce3c99b07b96a3f6eefadabc2/correctness",
"group_id": "state-v1/helpsteer2/2022eaf53787c99d5242f16ceb8448d27fdfd1f5a0dfd03063ae44822a3971ca",
"tokens": 674
},
{
"id": "state-v1/planning/1019d788f576348380144828fd5107211cbae15433afd590356304666b9a8858/best",
"group_id": "state-v1/planning/2da96a667f507f6ec97f9b7aec425b691a82ae1bb40bd6cb7c3da97ed3c08645",
"tokens": 279
},
{
"id": "state-v1/planning/11d290a432393a82b041351e1a7227e530bee82ae1826d9b8fa958df133bfb07/legal",
"group_id": "state-v1/planning/b70a11f9ce8508cceca65c1f60c81423d5b5239fb3152d4d7713edc00f97e0a1",
"tokens": 239
},
{
"id": "procedural/entity_belief_tracking:train:6067/agent_belief_location",
"group_id": "entity_belief_tracking:train:6067",
"tokens": 437
},
{
"id": "procedural/policy_applicability:train:8655/access_allowed",
"group_id": "policy_applicability:train:8655",
"tokens": 299
},
{
"id": "v3_e86900e8b47c30d7_s",
"group_id": "e1ca862df05edd6e12943ac5d234d9f4eabd88cd3456b78e6e9963cdf11d41be",
"tokens": 182
},
{
"id": "state-v1/scone/train-1393/2/position",
"group_id": "state-v1/scone/7f8eab77c96fe348ea1859b73184cd919f1faab7782f00442a552231e7d77614",
"tokens": 238
},
{
"id": "state-v1/scone/train-C9656/1/colour",
"group_id": "state-v1/scone/07bba56841b7ea050b3b5bdd00e6c54fec687c31b6296500795d41020c34ac4f",
"tokens": 216
},
{
"id": "state-v1/scone/train-B21153/2/amount",
"group_id": "state-v1/scone/ada68f88e44f42fcb45adffad2168c87e0771d75ef8886b3da4537a368acb43b",
"tokens": 262
},
{
"id": "state-v1/helpsteer2/daf94dfcf5bf3a67d1368ea6e5dac62ff8f673cfeb66111cd461efdb16920765",
"group_id": "state-v1/helpsteer2/11e67086868cd606d93f9addf818ceef58b504ad09bc0f2e04a7f515dff5a0b1",
"tokens": 753
},
{
"id": "state-v1/helpsteer2/ee04a14bafc3d2d3943f96c518abcfde9c90744e3f37cfaf12f02f1dbd23b721/correctness",
"group_id": "state-v1/helpsteer2/1f41d50898f0d39a385e025700bf229937e26cfec42a33b679d0a092cd2ba86a",
"tokens": 934
},
{
"id": "state-v1/planning/392f9c34119e1fd553f5dc9a0f1a394d8fde6c4165bf0b24b8056088dfe269c8/best",
"group_id": "state-v1/planning/3be0ae7f09340c874c89776fee064352e004daad5d30cb0fd73da818a55b3356",
"tokens": 366
},
{
"id": "state-v1/planning/7b1d0b2a6ed750728810e756b3b74af5e498a88ccf897c85471ace1e4574b097/legal",
"group_id": "state-v1/planning/b021d5b6a5c09b466fc04cb66b7f3ae196ee94616fe2bf116d84b3d831feff04",
"tokens": 243
},
{
"id": "reasoning-control-v1:76109:1563:decision",
"group_id": "reasoning-control-v1:76109:1563",
"tokens": 216
},
{
"id": "procedural/state_perturbation:train:18464/material_change",
"group_id": "state_perturbation:train:18464",
"tokens": 609
},
{
"id": "v3_40d0e01901f1c80d_s",
"group_id": "157a23d2f6d4a906f041a22e50a1d97c187177de866068c60cb4aadfc239b715",
"tokens": 182
},
{
"id": "state-v1/scone/train-4787/1/position",
"group_id": "state-v1/scone/b618c7b73cb9b0ea5e66ae49125e32c7cf31f694c256ab38d56f1013a611ba3e",
"tokens": 226
},
{
"id": "state-v1/scone/train-5429/3/present",
"group_id": "state-v1/scone/050fb660a46a1adffdbc511a8e5a8f326e44171aac7a6dbfa01c6bcea92193a9",
"tokens": 164
},
{
"id": "state-v1/scone/train-A9302/2/amount",
"group_id": "state-v1/scone/775309ce725c02949844ec0f82ffceb7580317fb2a640878218bde3a641838e1",
"tokens": 261
},
{
"id": "state-v1/helpsteer2/a299b0cfac1487fb5e01d36082b3b4f9decefd6b04a53ca384b583a7a338e866",
"group_id": "state-v1/helpsteer2/78a7d3995f6c010a7653f5f99b6c44bbe1f0921c400448e593c2f1c383c7e085",
"tokens": 852
},
{
"id": "state-v1/helpsteer2/9e1179d03b330b8f2103152a172c588bdffb0c11f9389ade32b5740bef97b67b/helpfulness",
"group_id": "state-v1/helpsteer2/871ce3053dcb66cf98721466e8a86b527cad237fd45731bb0915c1619326cd3c",
"tokens": 517
},
{
"id": "state-v1/planning/ef39536b48f22989e77ae10c98dc1f537d188cacafc88ca6dd03daf3fe307a2c/best",
"group_id": "state-v1/planning/f80afe0cb4571646c086e1969a730fb2e21a66d565c484b71bcb33753cb1a7fc",
"tokens": 267
},
{
"id": "state-v1/planning/d4669eb5ecbdca5ceb2c4d0ccaae377f34f5052a06c599eb56f729b61732e44a/legal",
"group_id": "state-v1/planning/aa6f95cd8a2b36e67b2133af0f0555bfac005df6c8c48ddc14e819112612efb7",
"tokens": 247
},
{
"id": "procedural/goal_directed_planning:train:890/first_legal_action",
"group_id": "goal_directed_planning:train:890",
"tokens": 414
},
{
"id": "community-diversity-v2/20260921/rag/numerical_claim/0/2/noul",
"group_id": "community-diversity-v2/20260921/rag/numerical_claim/0",
"tokens": 667
},
{
"id": "procedural/table_lookup:train:15009/count_matching",
"group_id": "table_lookup:train:15009",
"tokens": 490
},
{
"id": "state-v1/scone/train-3789/2/position",
"group_id": "state-v1/scone/78336b2332b241bda75c2d3685751dccfcee80fe4f72db12094054d7e59e5524",
"tokens": 231
},
{
"id": "state-v1/scone/train-3398/1/present",
"group_id": "state-v1/scone/e7252ab78e9e374aad65848984d579d9bcb9d36dc18609f01d11bd442573d033",
"tokens": 156
},
{
"id": "state-v1/scone/train-B21120/1/amount",
"group_id": "state-v1/scone/9d1c137e6ffba0910475041aa1d1fca62cd1ba1f83f05c6418c6ef46f43e479c",
"tokens": 256
},
{
"id": "state-v1/helpsteer2/40181b32a2b8960d5360017d255aacdb7bdf94bf3f20eed8c6b6a906ea70b924",
"group_id": "state-v1/helpsteer2/68d3c01e8a50841e9a07caf13859e9d89480fc78bf748ba7f4c63c155511a83f",
"tokens": 526
},
{
"id": "state-v1/helpsteer2/4df3c7d7d9900889284cdee827c88c7d2500af0e40f4f4e447ef338cc8d020dc/correctness",
"group_id": "state-v1/helpsteer2/5f59bbc440d43c110bd0fa4527ee734a9e81a7a45dbdef70337f21154be192f0",
"tokens": 321
},
{
"id": "state-v1/planning/231fb2debfee264dbf68405bf3b441d09251f1ba7a59256fe1c9adaee1dadfae/best",
"group_id": "state-v1/planning/64d32d73644d3ed217c72ed897e501d4a921e5ea1e3fa976fe238d5e439b3ee6",
"tokens": 351
},
{
"id": "state-v1/planning/39925b907cc083b77e16e0f8a98fa94509026e31a90e92c32e01b11464e089c5/progress",
"group_id": "state-v1/planning/dfae884248161e55d2983a45ad60d3a10de16a1d1e66c019fd16892ca1b2b94d",
"tokens": 250
},
{
"id": "community-diversity-v2/20260921/shell_history/archive_extract/61/2/choice",
"group_id": "community-diversity-v2/20260921/shell_history/archive_extract/61",
"tokens": 601
},
{
"id": "procedural/arithmetic:train:6792/random_is_long",
"group_id": "arithmetic:train:6792",
"tokens": 139
},
{
"id": "community-diversity-v2/20260921/rag/numerical_claim/73/2/score",
"group_id": "community-diversity-v2/20260921/rag/numerical_claim/73",
"tokens": 730
},
{
"id": "state-v1/scone/train-2387/1/position",
"group_id": "state-v1/scone/d23f84f1a3aceee9d3e32ee2e232e7ddc55c8751716cbcf56ffaa491af257023",
"tokens": 230
},
{
"id": "state-v1/scone/train-D11702/2/colour",
"group_id": "state-v1/scone/ee41f092ce70bc0636dd4a952120cdb0d0cd7f9f2050a2b1570ce71effe21bde",
"tokens": 227
},
{
"id": "state-v1/scone/train-C10006/4/amount",
"group_id": "state-v1/scone/57aa2d4d55f01465bfb70040c271838c02022820ea6abe842dc2e713e8ecca44",
"tokens": 293
},
{
"id": "state-v1/helpsteer2/f3e6a657b1ad301d3374c5e1bb3e3a41b5369f816a3db6cdaeff06e21fb7bceb",
"group_id": "state-v1/helpsteer2/f2ad656357cfce864a68f2b0846ad510223802eb801efdcc785654ecd325772b",
"tokens": 672
},
{
"id": "state-v1/helpsteer2/51c1eb5481dc5fae37cfd528c389a71d84b490dc37b64ec4ca5492fc38e8c6a5/correctness",
"group_id": "state-v1/helpsteer2/fc2628c9e95044ac5908d49e7b194614207674aa148e527ae36aa4f6add58215",
"tokens": 624
},
{
"id": "state-v1/planning/550c2f40c47f794aa07737316c84fd677c1149a128344646454849841e835df2/best",
"group_id": "state-v1/planning/4c0318c6296a6e34213fb355cac6b4a49d8bd227ece025e2f7830aab73025f26",
"tokens": 298
},
{
"id": "state-v1/planning/cbd2eee84615919f523f14d292601007c97c65314163fef65ecee6dab00d4865/progress",
"group_id": "state-v1/planning/18e05134beb0305e3d91e08e3ea77e527f4dcd05b48baa79c1ee2f84b4195492",
"tokens": 250
},
{
"id": "procedural/record_aggregation:train:11399/largest_quantity",
"group_id": "record_aggregation:train:11399",
"tokens": 258
},
{
"id": "community-diversity-v2/20260921/rag/negative_evidence/79/3/noul",
"group_id": "community-diversity-v2/20260921/rag/negative_evidence/79",
"tokens": 599
},
{
"id": "procedural/instruction_execution:train:224/target_count",
"group_id": "instruction_execution:train:224",
"tokens": 686
},
{
"id": "state-v1/scone/train-984/2/position",
"group_id": "state-v1/scone/53071dfd4669403220e62bf9e3eb17bbcd864ccd91393a401f8f94862d53363f",
"tokens": 232
},
{
"id": "state-v1/scone/train-D9676/5/colour",
"group_id": "state-v1/scone/ac0d85ed6125bfd7b893603b1466d1ef3bee35ef9bb754f5a02138b097249dd9",
"tokens": 252
},
{
"id": "state-v1/scone/train-C10474/3/amount",
"group_id": "state-v1/scone/e56207c4f60317575f6a0f844fe73721f8c03774bd03fa6a0b28600805f9fb9e",
"tokens": 280
},
{
"id": "state-v1/helpsteer2/bb1147b2ce8e915dec3fb8ad029275a43cecd405254e94f8d9f0c242b125f774",
"group_id": "state-v1/helpsteer2/263084687109f671d2d5e9a940e845e0f04da49c0187c1754df905af12dc462f",
"tokens": 776
},
{
"id": "state-v1/helpsteer2/e92e95aa4cb7a18f33bafa1caaf620443f00d464ff1ba2d17c31c7d72fdadc08/correctness",
"group_id": "state-v1/helpsteer2/ae7acd4558eb20774a315331c66f8abb168a5eb1b71dd4efe0576eccd0a82cdf",
"tokens": 744
},
{
"id": "state-v1/planning/7297f2c1f883ae8377876bfe42daf06368b42619e5016db55945105492c9b0ec/best",
"group_id": "state-v1/planning/e0c3996d531e12023260ae1d7c08422c7a7dd9c5dfd62f89961665975df01613",
"tokens": 270
},
{
"id": "state-v1/planning/f45eb2e5e95e110cddd34e92296d560149845548d5f024dc2cc0dfb26b782d48/progress",
"group_id": "state-v1/planning/b69fe8c1de8693c6df48f8e8276108b4571666fb862a36570fd5862516187714",
"tokens": 251
},
{
"id": "actions-v1/alfworld/5996",
"group_id": "actions-v1/alfworld/edc1ec61e629a50518a1ca354b17631819ae0e521f783942672f36901d193763",
"tokens": 838
},
{
"id": "procedural/graph_navigation:train:16949/within_budget",
"group_id": "graph_navigation:train:16949",
"tokens": 506
},
{
"id": "v3_0aaa1c17a3fa2807_s",
"group_id": "93a0cc8db6759693b16b227058da886c34586ecd581e597dc9b9552fc9f6bc42",
"tokens": 188
},
{
"id": "state-v1/scone/train-4299/2/position",
"group_id": "state-v1/scone/aacda5e3e76e5bebc03f85b89cf5617b3138909a3995ee3d43c51311fcc2ad92",
"tokens": 228
},
{
"id": "state-v1/scone/train-783/3/present",
"group_id": "state-v1/scone/8162c7cc9c72213dc259ee2da489e4e89586ab82c5e2966266252ae1a983e562",
"tokens": 176
},
{
"id": "state-v1/scone/train-A9218/2/amount",
"group_id": "state-v1/scone/dfc1c7fd1ac158ad4f81d284da72b518e43ffa25e97a62e4c242539ca0c92e5d",
"tokens": 268
},
{
"id": "state-v1/helpsteer2/aead7f3edc00abfcdabf71cbbbed587e1b15be248bcc97e67392d9a8178a0af9",
"group_id": "state-v1/helpsteer2/04f5dab920f3bde9bc367d741eca4ea77bbc97f3363ffbe7f3eb98f5cbb16643",
"tokens": 768
},
{
"id": "state-v1/helpsteer2/ec030534076b0cecdf7f222a825ff29f21815c8062362802d4a70225f42c1ef8/helpfulness",
"group_id": "state-v1/helpsteer2/36d6f65552cc2d8a2d1df2854f61e06d2aeb3a99e3cd53e723e8926eb0057f84",
"tokens": 766
},
{
"id": "state-v1/planning/6c231f6ebb0cdbd9e6f6a13bcfc5caf72a70064850ced5881e22892c6eaa0cc6/best",
"group_id": "state-v1/planning/e7c32e09f1aa06bdff882dfe11a66571764783fa8f0c76bb5ad59bdae65d90d6",
"tokens": 292
},
{
"id": "state-v1/planning/865032ab7eeb19b15bf322859654e6b8acb9e9f85af322f5868eb17ef734f1c6/legal",
"group_id": "state-v1/planning/e0d912a3203c369e147ea341b4b42cb7255c7eb560700c700f30a83612388768",
"tokens": 248
},
{
"id": "v3_a5887e9c46d98b5c_c",
"group_id": "1651c299f6bd60c058f43599376707905e869d3e33b20526a8e3d9663f17ec85",
"tokens": 156
},
{
"id": "workflow-controls-v1:security_incidents:42:145:v1:REVOKE SESSIONS",
"group_id": "workflow-controls-v1:security_incidents:42:145",
"tokens": 392
},
{
"id": "v3_3e31e936b369de81_s",
"group_id": "97799fd05233a58f3e6f0ef9b3c3c4953f61068f1ff1af439cfd7b3791c753e9",
"tokens": 184
},
{
"id": "state-v1/scone/train-5152/3/position",
"group_id": "state-v1/scone/07a39ee0478ddc21955c46c4b53fa1faad48e6ab96fb775af975a820bf0f06ee",
"tokens": 236
},
{
"id": "state-v1/scone/train-2271/3/present",
"group_id": "state-v1/scone/cc880145c1e21d36f351f9e99e255a50188aeac258ae65c1fb428e28f46b7e5c",
"tokens": 171
},
{
"id": "state-v1/scone/train-C9826/3/amount",
"group_id": "state-v1/scone/07c7653aa957ec0a31a752df2d95247a59e383d7df28bd89e5a7a28de363407b",
"tokens": 260
},
{
"id": "state-v1/helpsteer2/790e96def75215a7baeb983f617ae6405c58363aecb8c3182365995bc9248da6",
"group_id": "state-v1/helpsteer2/f6ce3bbedfe5b3be944dc3bcea77e1ed4a62c456da38f8540524bf08f5f464c4",
"tokens": 456
},
{
"id": "state-v1/helpsteer2/396f8b1cdf34439c3d50d3257eaf0c60f897c0db7579ea4fe382efa4b158547e/helpfulness",
"group_id": "state-v1/helpsteer2/d071a24ee9f44a05be72b9e875a229bdaa7c38341abb4dd8dfc7f75e308d7c42",
"tokens": 558
},
{
"id": "state-v1/planning/042ea5350ba298a7fcf8b4032f4117c2ff9eaa4f7915f2f7f7c018a5125683f4/best",
"group_id": "state-v1/planning/9ad71ae61aa12f761c775a0cdee866930cd4e42197d44057660eec0e1a072f32",
"tokens": 283
},
{
"id": "state-v1/planning/7e03f411b160c814e588466f5fcf2417e42b6ddae2a687ee0d6ef4d67961c153/legal",
"group_id": "state-v1/planning/a5d1869433789d2b3f3f92ce0b423c7383e4f4067fd5cdec6c52098a692c86af",
"tokens": 245
},
{
"id": "actions-v1/alfworld/5330",
"group_id": "actions-v1/alfworld/80728d21f8bf1e653d74afa77ed48ef6442f834703dab2ab67d2c0b08ae31f05",
"tokens": 634
},
{
"id": "community-diversity-v2/20260921/rubric_judge/unit_conversion/59/1/noul",
"group_id": "community-diversity-v2/20260921/rubric_judge/unit_conversion/59",
"tokens": 617
},
{
"id": "v3_1f7c09550c70f630_s",
"group_id": "50777b677aa39fa92cc50c75d93eacf06e231d8da1f359f8b6b519b4e09446bd",
"tokens": 185
},
{
"id": "state-v1/scone/train-4155/3/position",
"group_id": "state-v1/scone/d294fc394efe204bc0beccea46fb8e6f4b8208afcc6e74ea897b63a745c89eca",
"tokens": 237
},
{
"id": "state-v1/scone/train-4015/2/present",
"group_id": "state-v1/scone/39825a416f0c550837462f9cb1635e91e9ef4e6f88b5d5884049d2be04c322bc",
"tokens": 167
},
{
"id": "state-v1/scone/train-D10139/1/amount",
"group_id": "state-v1/scone/df3399440e76459846c4b6d1a157f2cbb8c1f2543b1a56e884a9833efb29175e",
"tokens": 274
},
{
"id": "state-v1/helpsteer2/9b5363083d98d30fe6726ca728b398db01b02d88cc17fa5a9e20f46c03297d7b",
"group_id": "state-v1/helpsteer2/36362d0987db05e57c38da4bd8bcca664b3bd0f79ecdb59ea3526811a9bcdc6a",
"tokens": 916
},
{
"id": "state-v1/helpsteer2/b5223adb1165fa78b097deefe44f6cf7eb8258bfb07997978a1cbd050ef4e3f7/correctness",
"group_id": "state-v1/helpsteer2/6ced4116c50a34512c17eeeef2d9140984247ca5f7f3037cf64b3ec5bde504a2",
"tokens": 761
},
{
"id": "state-v1/planning/cf3b2b33da7ca6e79bdf5e2f77ee2b852bbc0e03326e5f06f2bb0ff669e1a5db/best",
"group_id": "state-v1/planning/fc593ba45ef7029805a39ed325d5f5c65f35a9b5eeb41aa0b23e2f58debcfaf3",
"tokens": 282
},
{
"id": "state-v1/planning/3811c7460d89a245ccbeb29d9ef4c0a5f724db80d55436236cf277f475f5425b/legal",
"group_id": "state-v1/planning/2877a8ed27a9f2a9510017d845e3c9bfc3b9b4423c519476eabdb703b113d996",
"tokens": 246
},
{
"id": "reasoning-control-v1:76109:2264:decision",
"group_id": "reasoning-control-v1:76109:2264",
"tokens": 438
},
{
"id": "community-diversity-v2/20260921/shell_history/archive_extract/70/0/noul",
"group_id": "community-diversity-v2/20260921/shell_history/archive_extract/70",
"tokens": 527
},
{
"id": "community-diversity-v2/20260921/support/delayed_parcel/36/3/score",
"group_id": "community-diversity-v2/20260921/support/delayed_parcel/36",
"tokens": 716
},
{
"id": "state-v1/scone/train-2605/3/position",
"group_id": "state-v1/scone/689dbab7a65dbbe23379413dd726bd1cc1caf7917357b1a01a76ee94d0617745",
"tokens": 237
},
{
"id": "state-v1/scone/train-3462/3/present",
"group_id": "state-v1/scone/1e004b1be3ff0d89cec043021f3e0402bab0556cbd1a9901546d05574b3844e3",
"tokens": 171
},
{
"id": "state-v1/scone/train-B21187/5/amount",
"group_id": "state-v1/scone/2cdc9c619cc987ec2f2d70569193accecd4cf703e293425ca9ea16c283cac75e",
"tokens": 291
},
{
"id": "state-v1/helpsteer2/f9858ecf4cfb38bee9a49fbca95e222043ccd6a88aa737b39f84ea7a4a85cebd",
"group_id": "state-v1/helpsteer2/605bf5b382bd1a21dc4b46ce5d020b4e1f0584e16ec35c6f757aae523472de7a",
"tokens": 570
},
{
"id": "state-v1/helpsteer2/0864a439aed0f03733f924c8e3e65847bbbca1b7e203d163b6c31abf49b234d0/coherence",
"group_id": "state-v1/helpsteer2/3545102d95f006f31d298f0bcb41d296e33c0d5de932c15ebc4940c5302680a9",
"tokens": 625
},
{
"id": "state-v1/planning/bf151ba4c96f454c19222a3ed686ad62b62793f36286b1e8eac54ca59f00d7d4/best",
"group_id": "state-v1/planning/2002bfc9a0a2894020dc2e00409d0f6c00f815d5a982c996a2f9f07f570df090",
"tokens": 480
},
{
"id": "state-v1/planning/5f928c0fbd9117ea9e05482d56d6da57e59a87286eb40fd9b9d45a2ce251b7b8/legal",
"group_id": "state-v1/planning/1ff5035d3b551698c28962941d054449abfc37656e774f633cbd8beaf7cded82",
"tokens": 243
},
{
"id": "community-diversity-v2/20260921/games/projectile_dodge/64/1/choice",
"group_id": "community-diversity-v2/20260921/games/projectile_dodge/64",
"tokens": 768
},
{
"id": "community-diversity-v2/20260921/contracts/confidentiality_survival/75/3/noul",
"group_id": "community-diversity-v2/20260921/contracts/confidentiality_survival/75",
"tokens": 647
},
{
"id": "community-diversity-v2/20260921/shell_history/search_scope/37/2/score",
"group_id": "community-diversity-v2/20260921/shell_history/search_scope/37",
"tokens": 650
},
{
"id": "state-v1/scone/train-3551/5/position",
"group_id": "state-v1/scone/0cae89520c07c40e8da9b1deade5ac7de54e2fc5188b598a98800b0678a501f8",
"tokens": 247
},
{
"id": "state-v1/scone/train-D10004/1/colour",
"group_id": "state-v1/scone/c605d9ca8a4a625e318bf81d160829e2451564efb5171d9f110947ce41e5583a",
"tokens": 207
},
{
"id": "state-v1/scone/train-D10393/1/amount",
"group_id": "state-v1/scone/7f72878e6621aa001e1ef3b10d0e6bf33ab5e55d8f60d955a266074bd6680c0b",
"tokens": 265
},
{
"id": "state-v1/helpsteer2/e5d66f367e85bdb17d288a29c4b71112390979660502cfa52c77af8b65ed25d4",
"group_id": "state-v1/helpsteer2/a50947edb7dffe261af506ea4940cf175797a84b1c49d7fac45ff2847eaa74e3",
"tokens": 373
},
{
"id": "state-v1/helpsteer2/bd2a0f9e5cf88a1a129a1214b3bfd46d95a3c1a838dee64149352ac75d53f5a6/coherence",
"group_id": "state-v1/helpsteer2/9284635d21b09bbb02798c3510070f22d95d940ba66b65ebe7ae811787c9b76c",
"tokens": 442
},
{
"id": "state-v1/planning/dc3d3d7c04cf55e250aa2198662921dcc46fc97e540470a44efc9decf416cd79/best",
"group_id": "state-v1/planning/90fd16c9e35de2780db842e4dd197c6a880c3ce011c89b1e10e0012bdfebbd71",
"tokens": 298
},
{
"id": "state-v1/planning/c7156bd01967421d9cf5179f25792c948a79099e7717cc89a9c1927a87ce45c2/progress",
"group_id": "state-v1/planning/296863b26657b26a801984c1f4d55f75121754b24ee8d0c72cf84cf3cbaf380e",
"tokens": 251
},
{
"id": "procedural/goal_directed_planning:train:6690/first_legal_action",
"group_id": "goal_directed_planning:train:6690",
"tokens": 649
},
{
"id": "v3_37fedc95bf3a0c79_n",
"group_id": "e51711a8f1760ebef664ecaf358a33ec0d9bb7ecb65d7eee08cdc3e5b3049ef8",
"tokens": 142
},
{
"id": "v3_431e320f202b461d_s",
"group_id": "0ed4c9690742a6a5f0a48e107e075f49896a74a2b240a619fb093c0f4fc319d5",
"tokens": 179
},
{
"id": "state-v1/scone/train-3032/5/position",
"group_id": "state-v1/scone/e2c4f955e9e0cdf8b278548a24de86fab2ebc7066f25bed0f290e4aa20c10aef",
"tokens": 260
},
{
"id": "state-v1/scone/train-B21259/2/colour",
"group_id": "state-v1/scone/250c0060badd6268897e6278f429671db970727b0aac7a8a8746173f321e447d",
"tokens": 235
},
{
"id": "state-v1/scone/train-D10972/2/amount",
"group_id": "state-v1/scone/1b5bbe64bff4d6ce865f5887b153323efb8842071965aa974be1dd28893abdf7",
"tokens": 255
},
{
"id": "state-v1/helpsteer2/da8f3b7dbd1d13ea6135402c5885aa6b5bdc31eb45cdc70d1a1ffdc218df6f29",
"group_id": "state-v1/helpsteer2/f4979c6ac282fc182c76b2f030514bbaa8e86ba133bb2e99d80dee425687d303",
"tokens": 343
},
{
"id": "state-v1/helpsteer2/320c22ef383e8e7649807e254d97af66bb9cab4fc14c1bb41aeb39244a5889e1/correctness",
"group_id": "state-v1/helpsteer2/9c79416ba035c646d8440a9bfe0b874618658b01766d15829b91cafe05896c69",
"tokens": 620
},
{
"id": "state-v1/planning/9300cac0dd3f08663b47ea5937751d275d1824dc2a6d1b5b188d73d8d1ba3430/best",
"group_id": "state-v1/planning/34eaec0bab551aa982fd79aeb014b439d7077b6b2628ccc08be95741f5ddfa6c",
"tokens": 289
},
{
"id": "state-v1/planning/2592fd03e6f5b9ff4ad00445fd45ca2415231d55da2c789fd60f5f64ba74d89b/legal",
"group_id": "state-v1/planning/87b2a8d78db0fcb29d2c1add32de59508ffffc8076ca5f7b7cebc03b926ae9e3",
"tokens": 242
},
{
"id": "actions-v1/alfworld/16211",
"group_id": "actions-v1/alfworld/1ee90eb03669ac11cdaea340a57721df79807b4305411d849cee0073b91ddba3",
"tokens": 411
},
{
"id": "v3_b9c5ba6656e76271_n",
"group_id": "09593869d0ecb5b326484d8233513a339f2a06eaf5e6d991e64998ef04b81bd1",
"tokens": 135
},
{
"id": "community-diversity-v2/20260921/ir/inventory_answer/3/2/score",
"group_id": "community-diversity-v2/20260921/ir/inventory_answer/3",
"tokens": 677
},
{
"id": "state-v1/scone/train-2640/2/position",
"group_id": "state-v1/scone/fa524ea8d586d72586fb2958aa51f3973994f8275b16a4dc3960cc28d07b525c",
"tokens": 229
},
{
"id": "state-v1/scone/train-C10066/4/colour",
"group_id": "state-v1/scone/d1e81370b37f2750bf926c72cec2e206c4cbd6b6395c8b35870182ef4c47a0bb",
"tokens": 262
},
{
"id": "state-v1/scone/train-D9878/4/amount",
"group_id": "state-v1/scone/08e58b6892f2ee8863f2d57462eb04cd2265e3c4a14117ae9fb0f1e8282be4f9",
"tokens": 273
},
{
"id": "state-v1/helpsteer2/263eb30a889362cca8cde368ba578a4cc47b2ccf1f48db889cda15fd57389f50",
"group_id": "state-v1/helpsteer2/80d724d44f2330adc8ecb14c4be1ab1969b2a329099079957e94506533afd405",
"tokens": 850
},
{
"id": "state-v1/helpsteer2/ce0648cb44daa9c9c04d374080ed7921e4593ff702f708923f7f3712ec1de8f4/correctness",
"group_id": "state-v1/helpsteer2/7d5c8314f48c34e9318e54a7b499e130c559d4b342cf6eb56980e50501df379d",
"tokens": 407
},
{
"id": "state-v1/planning/a5272921e7572cb89872b148f14cc5ddfdf571cd5e6a25de6b7ba3d70c009568/best",
"group_id": "state-v1/planning/1a7a55e398a6a9c3eb1a9c6c911e03a73af478bc1915245adcf4b250bf753c81",
"tokens": 368
},
{
"id": "state-v1/planning/659444f52ccbcde2c5167fb0a1b3a95506627869cdfbd597746171a50b806dd4/progress",
"group_id": "state-v1/planning/b64aa551a27e015690dff7e4d3f1f313ea3273e6e33a0649a47bc2484ae39680",
"tokens": 254
},
{
"id": "procedural/multi_view_adjudication:train:316/intent",
"group_id": "multi_view_adjudication:train:316",
"tokens": 711
},
{
"id": "procedural/partial_observation_calibration:train:4007/incident_real",
"group_id": "partial_observation_calibration:train:4007",
"tokens": 208
},
{
"id": "procedural/multi_view_adjudication:train:4439/workflow_impact",
"group_id": "multi_view_adjudication:train:4439",
"tokens": 650
},
{
"id": "state-v1/scone/train-1750/2/position",
"group_id": "state-v1/scone/882d6755b27b10703838d3c3e9d9d6744ce50120f79ea17c1d9f6778e3da599c",
"tokens": 229
},
{
"id": "state-v1/scone/train-D11309/2/colour",
"group_id": "state-v1/scone/2f5cefd256143ee0d53d357c5217538dd7c0dde115e9a397123b9f50c18069d6",
"tokens": 217
},
{
"id": "state-v1/scone/train-D10222/2/amount",
"group_id": "state-v1/scone/23e5b92b81c4f96e7133e1bbdc1e0ba26d0ef578d399d06cef472fecf48124a1",
"tokens": 282
},
{
"id": "state-v1/helpsteer2/a28aa87d778d18e5ccb9a45784dda138968594f33d2b7fbdf6c587e5de1e1ffe",
"group_id": "state-v1/helpsteer2/4627ebd3bb206abd6df7e63eae192f92dd5ef1854443308fc3accd45b1d1419b",
"tokens": 729
},
{
"id": "state-v1/helpsteer2/553c11788359358c007310d1aad661e3eb380730d7f899307af4c7ebac49c079/correctness",
"group_id": "state-v1/helpsteer2/059b513b2f66586b56ad80cfe7b32c7733e6beee72861381feae8f430c678540",
"tokens": 653
},
{
"id": "state-v1/planning/ee42de3e1b0b8799c7911c36021d9ae4b7f0f85a4ed7a885aaf94e558b15227f/best",
"group_id": "state-v1/planning/80599250f49ba976be09f6c0464956fd9fc29519ca08eba91cd0573becb94476",
"tokens": 298
},
{
"id": "state-v1/planning/03f6aac5f44f72666cc121b8dca460de1e774c985299cfc340f17d682b1640d2/progress",
"group_id": "state-v1/planning/caccc86082d4c6f9fb6c5d8e38b9d1cd42dd8f3a4b3a2992d30a7336bfab6618",
"tokens": 255
},
{
"id": "procedural/arithmetic:train:19671/final_balance",
"group_id": "arithmetic:train:19671",
"tokens": 194
},
{
"id": "procedural/needle_retrieval:train:12116/id_listed",
"group_id": "needle_retrieval:train:12116",
"tokens": 717
}
]
}