{
 "id": "ByteDance-Seed/mga-fineweb-edu",
 "owner": "ByteDance-Seed",
 "name": "mga-fineweb-edu",
 "downloads": 1909,
 "likes": 44,
 "last_modified": "2025-05-19T03:19:15.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@article{hao2025reformulation,\n  title = {Reformulation for Pretraining Data Augmentation},\n  author = {Hao, Xintong and Zhu, Ruijie and Zhang, Ge and Shen, Ke and Li, Chenggang},\n  journal={arXiv preprint arXiv:2502.04235},\n  url = {https://arxiv.org/abs/2502.04235}\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "25aac3c59f6b15fc538dfd025df5ad920bca5d02",
 "stated_evidence": "https://huggingface.co/datasets/ByteDance-Seed/mga-fineweb-edu/blob/25aac3c59f6b15fc538dfd025df5ad920bca5d02/README.md",
 "file_evidence": "https://huggingface.co/datasets/ByteDance-Seed/mga-fineweb-edu/tree/25aac3c59f6b15fc538dfd025df5ad920bca5d02",
 "card_nc": false
}