{
 "id": "CAMeL-Lab/BAREC-10M",
 "owner": "CAMeL-Lab",
 "name": "BAREC-10M",
 "downloads": 47,
 "likes": 0,
 "last_modified": "2026-06-08T15:50:37.000Z",
 "stated_licence": "cc-by-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@inproceedings{elmadani-etal-2026-large,\n  title = {A Large and Balanced Multi-Domain Arabic Corpus Annotated for Morphology, Syntax, and Readability},\n  author = {Elmadani, Khalid N. and Wizani, Adel Mahmoud and Thomure, Hanada Taha and Habash, Nizar},\n  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference (LREC 2026)},\n  month = {May},\n  year = {2026},\n  pages = {11761--11775},\n  address = {Palma, Mallorca, Spain},\n  publisher = {European Language Resources Association (ELRA)},\n  editor = {Piperidis, Stelios and Bel, Núria and van den Heuvel, Henk and Ide, Nancy and Krek, Simon and Toral, Antonio},\n  doi = {10.63317/45f2o6t8piyi}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "1c60f0a9305d5840754e03b7ad12644170a8803f",
 "stated_evidence": "https://huggingface.co/datasets/CAMeL-Lab/BAREC-10M/blob/1c60f0a9305d5840754e03b7ad12644170a8803f/README.md",
 "file_evidence": "https://huggingface.co/datasets/CAMeL-Lab/BAREC-10M/tree/1c60f0a9305d5840754e03b7ad12644170a8803f",
 "card_nc": false
}