{
 "id": "lefft/math-step-dpo-v1",
 "owner": "lefft",
 "name": "math-step-dpo-v1",
 "downloads": 47,
 "likes": 0,
 "last_modified": "2026-09-28T22:38:00.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "see-source",
 "licence_link": "https://huggingface.co/datasets/xinlai/Math-Step-DPO-10K",
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@article{lai2024stepdpo,\n  title   = {Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs},\n  author  = {Lai, Xin and Tian, Zhuotao and Chen, Yukang and Yang, Senqiao and Peng, Xiangru and Jia, Jiaya},\n  journal = {arXiv preprint arXiv:2406.18629},\n  year    = {2024}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "ba38c2d9f562ddb74098bfce3ca00c26c02472f8",
 "stated_evidence": "https://huggingface.co/datasets/lefft/math-step-dpo-v1/blob/ba38c2d9f562ddb74098bfce3ca00c26c02472f8/README.md",
 "file_evidence": "https://huggingface.co/datasets/lefft/math-step-dpo-v1/tree/ba38c2d9f562ddb74098bfce3ca00c26c02472f8",
 "card_nc": false
}