{
 "id": "AnnaWegmann/Training-Misc",
 "owner": "AnnaWegmann",
 "name": "Training-Misc",
 "downloads": 98,
 "likes": 0,
 "last_modified": "2025-07-15T15:16:30.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@article{wegmann2025tokenization,\n  title={Tokenization is Sensitive to Language Variation},\n  author={Wegmann, Anna and Nguyen, Dong and Jurgens, David},\n  journal={arXiv preprint arXiv:2502.15343},\n  year={2025}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "d114df8df2f3a69ac2e9a3db9550a3774af7c578",
 "stated_evidence": "https://huggingface.co/datasets/AnnaWegmann/Training-Misc/blob/d114df8df2f3a69ac2e9a3db9550a3774af7c578/README.md",
 "file_evidence": "https://huggingface.co/datasets/AnnaWegmann/Training-Misc/tree/d114df8df2f3a69ac2e9a3db9550a3774af7c578",
 "card_nc": false
}