{
 "id": "GenuineWWD/SCS_data",
 "owner": "GenuineWWD",
 "name": "SCS_data",
 "downloads": 33,
 "likes": 1,
 "last_modified": "2025-11-17T02:45:58.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "reinforcement-learning"
 ],
 "citation": "@article{wang2025enhancing,\n  title={Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling},\n  author={Wang, Jiahao and Xu, Weiye and Yang, Aijun and Zhou, Wengang and Lu, Lewei and Li, Houqiang and Wang, Xiaohua and Zhu, Jinguo},\n  journal={arXiv preprint arXiv:2511.10648},\n  year={2025}\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "2ba6ed31d09a6f194f84a98d81ec64861199af2e",
 "stated_evidence": "https://huggingface.co/datasets/GenuineWWD/SCS_data/blob/2ba6ed31d09a6f194f84a98d81ec64861199af2e/README.md",
 "file_evidence": "https://huggingface.co/datasets/GenuineWWD/SCS_data/tree/2ba6ed31d09a6f194f84a98d81ec64861199af2e",
 "card_nc": false
}