{
 "id": "AnnaWegmann/Dialect",
 "owner": "AnnaWegmann",
 "name": "Dialect",
 "downloads": 117,
 "likes": 0,
 "last_modified": "2025-07-16T08:37:50.000Z",
 "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": "037dc01640cbc3127c008bd9252d2e76b8d2b4dc",
 "stated_evidence": "https://huggingface.co/datasets/AnnaWegmann/Dialect/blob/037dc01640cbc3127c008bd9252d2e76b8d2b4dc/README.md",
 "file_evidence": "https://huggingface.co/datasets/AnnaWegmann/Dialect/tree/037dc01640cbc3127c008bd9252d2e76b8d2b4dc",
 "card_nc": false
}