{
 "id": "openbmb/DCAD-2000",
 "owner": "openbmb",
 "name": "DCAD-2000",
 "downloads": 2603,
 "likes": 24,
 "last_modified": "2025-12-05T20:06:09.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "license",
 "licence_link": "LICENSE",
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@article{shen2025dcad,\n  title={DCAD-2000: A Multilingual Dataset across 2000+ Languages with Data Cleaning as Anomaly Detection},\n  author={Shen, Yingli and Lai, Wen and Wang, Shuo and Zhang, Xueren and Luo, Kangyang and Fraser, Alexander and Sun, Maosong},\n  journal={arXiv preprint arXiv:2502.11546},\n  year={2025}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "233fa6dd3b0eabbc78f48aabbf024436354894dc",
 "stated_evidence": "https://huggingface.co/datasets/openbmb/DCAD-2000/blob/233fa6dd3b0eabbc78f48aabbf024436354894dc/README.md",
 "file_evidence": "https://huggingface.co/datasets/openbmb/DCAD-2000/tree/233fa6dd3b0eabbc78f48aabbf024436354894dc",
 "card_nc": false
}