{
 "id": "tasksource/prm800k_dpo",
 "owner": "tasksource",
 "name": "prm800k_dpo",
 "downloads": 266,
 "likes": 4,
 "last_modified": "2026-09-24T13:55:50.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "reinforcement-learning"
 ],
 "citation": "@article{lightman2023lets,\n  title={Let's Verify Step by Step},\n  author={Lightman, Hunter and Kosaraju, Vineet and Burda, Yura and Edwards, Harri and Baker, Bowen and Lee, Teddy and Leike, Jan and Schulman, John and Sutskever, Ilya and Cobbe, Karl},\n  journal={arXiv preprint arXiv:2305.20050},\n  year={2023}\n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "33c3d8ed2f3a3375cc9ebbfd05ff6d11b7ee6ba6",
 "stated_evidence": "https://huggingface.co/datasets/tasksource/prm800k_dpo/blob/33c3d8ed2f3a3375cc9ebbfd05ff6d11b7ee6ba6/README.md",
 "file_evidence": "https://huggingface.co/datasets/tasksource/prm800k_dpo/tree/33c3d8ed2f3a3375cc9ebbfd05ff6d11b7ee6ba6",
 "card_nc": false
}