{
 "id": "tasksource/curlie-domains",
 "owner": "tasksource",
 "name": "curlie-domains",
 "downloads": 95,
 "likes": 0,
 "last_modified": "2026-10-21T13:51:37.000Z",
 "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": "@dataset{weiss_baumann_2026_curlie,\n  author    = {Weiß, Thomas and Baumann, Timo},\n  title     = {Curlie Domain-Level Multi-Label Content Classification Benchmark},\n  year      = {2026},\n  publisher = {Zenodo},\n  doi       = {10.5281/zenodo.19943663},\n  url       = {https://zenodo.org/records/19943663},\n}\n\n@inproceedings{lugeon2022homepage2vec,\n  title     = {Homepage2Vec: Language-Agnostic Website Embedding and Classification},\n  author    = {Lugeon, Sylvain and Piccardi, Tiziano and West, Robert},\n  booktitle = {Proceedings of the International AAAI Conference on Web and Social Media},\n  volume    = {16},\n  pages     = {1285--1291},\n  year      = {2022},\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "a2f5176ea155c61be3a0a277a90aabe0dc4b1a9b",
 "stated_evidence": "https://huggingface.co/datasets/tasksource/curlie-domains/blob/a2f5176ea155c61be3a0a277a90aabe0dc4b1a9b/README.md",
 "file_evidence": "https://huggingface.co/datasets/tasksource/curlie-domains/tree/a2f5176ea155c61be3a0a277a90aabe0dc4b1a9b",
 "card_nc": false
}