{
 "id": "wissamantoun/MegaQuery-680M",
 "owner": "wissamantoun",
 "name": "MegaQuery-680M",
 "downloads": 76,
 "likes": 0,
 "last_modified": "2026-11-01T23:34:02.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-retrieval"
 ],
 "citation": "We release this dataset under **odc-by**. Source documents come from\n[HuggingFaceFW/finepdfs](https://huggingface.co/datasets/HuggingFaceFW/finepdfs). See its dataset card\nfor source attribution and usage information. We build our data-generation recipe\non [Qwen3 Embedding](https://arxiv.org/abs/2506.05176).",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "8b0363f4fd42106dead6f690bec9fca17dc9b067",
 "stated_evidence": "https://huggingface.co/datasets/wissamantoun/MegaQuery-680M/blob/8b0363f4fd42106dead6f690bec9fca17dc9b067/README.md",
 "file_evidence": "https://huggingface.co/datasets/wissamantoun/MegaQuery-680M/tree/8b0363f4fd42106dead6f690bec9fca17dc9b067",
 "card_nc": false
}