{
 "id": "AdaMLLab/JpnMix",
 "owner": "AdaMLLab",
 "name": "JpnMix",
 "downloads": 2400,
 "likes": 3,
 "last_modified": "2026-04-27T03:06:36.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "```bib\n@misc{alrashed2025mixminmatch,\n      title={Mix, MinHash, and Match: Cross-Source Agreement for Multilingual Pretraining Datasets},\n      author={Sultan Alrashed and Francesco Orabona},\n      year={2025},\n      eprint={2512.18834v2},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2512.18834v2},\n}\n```",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "4b957f65b323053a3e4f802c56c9e103815e0fba",
 "stated_evidence": "https://huggingface.co/datasets/AdaMLLab/JpnMix/blob/4b957f65b323053a3e4f802c56c9e103815e0fba/README.md",
 "file_evidence": "https://huggingface.co/datasets/AdaMLLab/JpnMix/tree/4b957f65b323053a3e4f802c56c9e103815e0fba",
 "card_nc": false
}