{
 "id": "gaotang/RM-R1-after-Distill-RLVR",
 "owner": "gaotang",
 "name": "RM-R1-after-Distill-RLVR",
 "downloads": 39,
 "likes": 1,
 "last_modified": "2025-05-20T21:23:48.000Z",
 "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": "0085ccc47233f954b2b7530059f55c36cb68b5c9",
 "stated_evidence": "https://huggingface.co/datasets/gaotang/RM-R1-after-Distill-RLVR/blob/0085ccc47233f954b2b7530059f55c36cb68b5c9/README.md",
 "file_evidence": "https://huggingface.co/datasets/gaotang/RM-R1-after-Distill-RLVR/tree/0085ccc47233f954b2b7530059f55c36cb68b5c9",
 "card_nc": false
}