{
 "id": "r-three/farsi_tokenizer_robustness",
 "owner": "r-three",
 "name": "farsi_tokenizer_robustness",
 "downloads": 84,
 "likes": 1,
 "last_modified": "2025-10-29T18:57:12.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "multiple-choice"
 ],
 "citation": "@inproceedings{toksuite2026,\n  title={TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior},\n  author={Altıntaş, Gül Sena and Ehghaghi, Malikeh and Lester, Brian and Liu, Fengyuan and Zhao, Wanru and Ciccone, Marco and Raffel, Colin},\n  booktitle={Preprint.},\n  year={2026},\n  url={TBD}\n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "5174bfe330f12d47596fb2460a4624524a2eb0cd",
 "stated_evidence": "https://huggingface.co/datasets/r-three/farsi_tokenizer_robustness/blob/5174bfe330f12d47596fb2460a4624524a2eb0cd/README.md",
 "file_evidence": "https://huggingface.co/datasets/r-three/farsi_tokenizer_robustness/tree/5174bfe330f12d47596fb2460a4624524a2eb0cd",
 "card_nc": false
}