{
 "id": "GAIR/MathPile_Commercial",
 "owner": "GAIR",
 "name": "MathPile_Commercial",
 "downloads": 67,
 "likes": 34,
 "last_modified": "2025-04-03T10:32:58.000Z",
 "stated_licence": "cc-by-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "auto",
 "tasks": [],
 "citation": "@inproceedings{\nwang2024mathpile,\ntitle={MathPile: A Billion-Token-Scale Pretraining Corpus for Math},\nauthor={Zengzhi Wang and Xuefeng Li and Rui Xia and Pengfei Liu},\nbooktitle={The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track},\nyear={2024},\nurl={https://openreview.net/forum?id=RSvhU69sbG}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "7d97387880ffca4f70bad1b75c9a1ff87aa90104",
 "stated_evidence": "https://huggingface.co/datasets/GAIR/MathPile_Commercial/blob/7d97387880ffca4f70bad1b75c9a1ff87aa90104/README.md",
 "file_evidence": "https://huggingface.co/datasets/GAIR/MathPile_Commercial/tree/7d97387880ffca4f70bad1b75c9a1ff87aa90104",
 "card_nc": false
}