{
 "id": "racineai/VDR_MEGA_MultiDomain_DocRetrieval",
 "owner": "racineai",
 "name": "VDR_MEGA_MultiDomain_DocRetrieval",
 "downloads": 4660,
 "likes": 24,
 "last_modified": "2026-03-17T20:07:55.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "visual-document-retrieval",
  "text-retrieval"
 ],
 "citation": "@misc{appourchaux_brandolini_lemaistre_rochet2025,\n  title        = {Visual Document Retrieval Dataset: A Comprehensive Multilingual Training Resource},\n  author       = {Léo Appourchaux and Noé Brandolini and Paul Lemaistre and André-Louis Rochet},\n  year         = {2025},\n  eprint       = {XXXX.XXXXX},\n  archivePrefix = {arXiv},\n  primaryClass  = {cs.IR},\n  url          = {https://arxiv.org/abs/XXXX.XXXXX}\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "dbcbb1c7ba8e57d9812afa5ee02c5dadf8ae0f71",
 "stated_evidence": "https://huggingface.co/datasets/racineai/VDR_MEGA_MultiDomain_DocRetrieval/blob/dbcbb1c7ba8e57d9812afa5ee02c5dadf8ae0f71/README.md",
 "file_evidence": "https://huggingface.co/datasets/racineai/VDR_MEGA_MultiDomain_DocRetrieval/tree/dbcbb1c7ba8e57d9812afa5ee02c5dadf8ae0f71",
 "card_nc": false
}