{
 "id": "bethgelab/dataconcept_128M",
 "owner": "bethgelab",
 "name": "dataconcept_128M",
 "downloads": 9102,
 "likes": 6,
 "last_modified": "2026-08-25T18:09:48.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "zero-shot-classification"
 ],
 "citation": "@inproceedings{ghosh2026concept,\n  title={Concept-aware batch sampling improves language-image pretraining},\n  author={Ghosh, Adhiraj and Udandarao, Vishaal and Nguyen, Thao and Farina, Matteo and Cherti, Mehdi and Jitsev, Jenia and Oh, Sewoong and Ricci, Elisa and Schmidt, Ludwig and Bethge, Matthias},\n  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},\n  pages={3056--3068},\n  year={2026}\n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "2f0b9209849b18041118150c4c81f47b345080d0",
 "stated_evidence": "https://huggingface.co/datasets/bethgelab/dataconcept_128M/blob/2f0b9209849b18041118150c4c81f47b345080d0/README.md",
 "file_evidence": "https://huggingface.co/datasets/bethgelab/dataconcept_128M/tree/2f0b9209849b18041118150c4c81f47b345080d0",
 "card_nc": false
}