{
 "id": "taln-ls2n/CASIMIR",
 "owner": "taln-ls2n",
 "name": "CASIMIR",
 "downloads": 305,
 "likes": 1,
 "last_modified": "2025-10-21T17:17:34.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@inproceedings{jourdan-etal-2024-casimir,\n    title = \"{CASIMIR}: A Corpus of Scientific Articles Enhanced with Multiple Author-Integrated Revisions\",\n    author = \"Jourdan, L{\\'e}ane  and\n      Boudin, Florian  and\n      Hernandez, Nicolas  and\n      Dufour, Richard\",\n    editor = \"Calzolari, Nicoletta  and\n      Kan, Min-Yen  and\n      Hoste, Veronique  and\n      Lenci, Alessandro  and\n      Sakti, Sakriani  and\n      Xue, Nianwen\",\n    booktitle = \"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)\",\n    month = may,\n    year = \"2024\",\n    address = \"Torino, Italia\",\n    publisher = \"ELRA and ICCL\",\n    url = \"https://aclanthology.org/2024.lrec-main.257/\",\n    pages = \"2883--2892\",\n    abstract = \"Writing a scientific article is a challenging task as it is a highly codified and specific genre, consequently proficiency in written communication is essential for effectively conveying research findings and ideas. In this article, we propose an original textual resource on the revision step of the writing process of scientific articles. This new dataset, called CASIMIR, contains the multiple revised versions of 15,646 scientific articles from OpenReview, along with their peer reviews. Pairs of consecutive versions of an article are aligned at sentence-level while keeping paragraph location information as metadata for supporting future revision studies at the discourse level. Each pair of revi",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "e6134f9fabce709425e3c43d7b677a2f5a7d81e4",
 "stated_evidence": "https://huggingface.co/datasets/taln-ls2n/CASIMIR/blob/e6134f9fabce709425e3c43d7b677a2f5a7d81e4/README.md",
 "file_evidence": "https://huggingface.co/datasets/taln-ls2n/CASIMIR/tree/e6134f9fabce709425e3c43d7b677a2f5a7d81e4",
 "card_nc": false
}