{
 "id": "aisingapore/WangchanLION-Web",
 "owner": "aisingapore",
 "name": "WangchanLION-Web",
 "downloads": 1442,
 "likes": 4,
 "last_modified": "2025-09-03T14:21:47.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "fill-mask"
 ],
 "citation": "@misc{phatthiyaphaibun2025mangosteenopenthaicorpus,\n      title={Mangosteen: An Open Thai Corpus for Language Model Pretraining}, \n      author={Wannaphong Phatthiyaphaibun and Can Udomcharoenchaikit and Pakpoom Singkorapoom and Kunat Pipatanakul and Ekapol Chuangsuwanich and Peerat Limkonchotiwat and Sarana Nutanong},\n      year={2025},\n      eprint={2507.14664},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2507.14664}, \n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "db9f1f5914b3c84c8428942334b99099a4f685d5",
 "stated_evidence": "https://huggingface.co/datasets/aisingapore/WangchanLION-Web/blob/db9f1f5914b3c84c8428942334b99099a4f685d5/README.md",
 "file_evidence": "https://huggingface.co/datasets/aisingapore/WangchanLION-Web/tree/db9f1f5914b3c84c8428942334b99099a4f685d5",
 "card_nc": false
}