{
 "id": "gaotang/RM-R1-Distill-SFT",
 "owner": "gaotang",
 "name": "RM-R1-Distill-SFT",
 "downloads": 93,
 "likes": 2,
 "last_modified": "2025-05-20T21:23:17.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-ranking"
 ],
 "citation": "@article{chen2025rm,\n  title={RM-R1: Reward Modeling as Reasoning},\n  author={Chen, Xiusi and Li, Gaotang and Wang, Ziqi and Jin, Bowen and Qian, Cheng and Wang, Yu and Wang, Hongru and Zhang, Yu and Zhang, Denghui and Zhang, Tong and others},\n  journal={arXiv preprint arXiv:2505.02387},\n  year={2025}\n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "ed8bd2a136623a0334369b5e2ac7753430ebf794",
 "stated_evidence": "https://huggingface.co/datasets/gaotang/RM-R1-Distill-SFT/blob/ed8bd2a136623a0334369b5e2ac7753430ebf794/README.md",
 "file_evidence": "https://huggingface.co/datasets/gaotang/RM-R1-Distill-SFT/tree/ed8bd2a136623a0334369b5e2ac7753430ebf794",
 "card_nc": false
}