{
 "id": "VidaForge/VidaForge-3M",
 "owner": "VidaForge",
 "name": "VidaForge-3M",
 "downloads": 1861,
 "likes": 14,
 "last_modified": "2026-09-13T11:27:13.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-to-video",
  "video-text-to-text",
  "video-classification"
 ],
 "citation": "@misc{ma2026vidaforge,\n    title        = {VidaForge: Building a Video Foundation Model Pretraining Data Pipeline from Scratch in an Academic Lab},\n    author       = {Ma, Yan and Su, Jiadi and Hu, Zhulin and Chern, Ethan and Zhang, Linhao and Mi, TianTian and Liu, Pengfei},\n    year         = {2026},\n    howpublished = {\\url{https://yanmaaaaaa.notion.site/vidaforge}},\n    note         = {Blog and open-source project}\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "7f36ccb3252b597607df734f87db5647f45746ca",
 "stated_evidence": "https://huggingface.co/datasets/VidaForge/VidaForge-3M/blob/7f36ccb3252b597607df734f87db5647f45746ca/README.md",
 "file_evidence": "https://huggingface.co/datasets/VidaForge/VidaForge-3M/tree/7f36ccb3252b597607df734f87db5647f45746ca",
 "card_nc": false
}