{
 "id": "mlfoundations/dcvlm_pool_large",
 "owner": "mlfoundations",
 "name": "dcvlm_pool_large",
 "downloads": 81720,
 "likes": 2,
 "last_modified": "2026-10-10T12:42:04.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "image-text-to-text",
  "visual-question-answering"
 ],
 "citation": "@article{farina2026datacomp,\n  title={DataComp-VLM: Improved Open Datasets for Vision-Language Models},\n  author={Farina, Matteo and Udandarao, Vishaal and Nguyen, Thao and Kuzucu, Selim and B{\\\"o}ther, Maximilian and Hochlehnert, Andreas and Ghosh, Adhiraj and Nezhurina, Marianna and Roth, Karsten and Struber, Joschka and others},\n  journal={arXiv preprint arXiv:2606.28551},\n  year={2026}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "c76328c4afd15d3a6333b68a48dabf4f8f0819cc",
 "stated_evidence": "https://huggingface.co/datasets/mlfoundations/dcvlm_pool_large/blob/c76328c4afd15d3a6333b68a48dabf4f8f0819cc/README.md",
 "file_evidence": "https://huggingface.co/datasets/mlfoundations/dcvlm_pool_large/tree/c76328c4afd15d3a6333b68a48dabf4f8f0819cc",
 "card_nc": false
}