{
 "id": "bearda/croissantminer",
 "owner": "bearda",
 "name": "croissantminer",
 "downloads": 1246,
 "likes": 1,
 "last_modified": "2026-10-07T09:13:47.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification",
  "text-generation"
 ],
 "citation": "@inproceedings{arda2026croissantminer,\n  title     = {CroissantMiner: Automated Extraction and Validation of Croissant Metadata for ML Datasets},\n  author    = {Arda, Berke and Yavuz, Ahmetcan and Gerry, Paul and Lobentanzer, Sebastian and\n               Sarwar, Nobin and Giner-Miguelez, Joan and Chen, Kongtao and Zhang, Luyao and\n               Sachan, Mrinmaya and Akhtar, Mubashara},\n  booktitle = {Advances in Neural Information Processing Systems (Evaluations and Datasets Track)},\n  year      = {2026}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "90f1c5e4dda12d4472222f80e854fc8496a969bd",
 "stated_evidence": "https://huggingface.co/datasets/bearda/croissantminer/blob/90f1c5e4dda12d4472222f80e854fc8496a969bd/README.md",
 "file_evidence": "https://huggingface.co/datasets/bearda/croissantminer/tree/90f1c5e4dda12d4472222f80e854fc8496a969bd",
 "card_nc": false
}