{
 "id": "qvac/GenesisIII",
 "owner": "qvac",
 "name": "GenesisIII",
 "downloads": 4306,
 "likes": 2,
 "last_modified": "2026-09-22T17:28:42.000Z",
 "stated_licence": "cc-by-nc-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@misc{vitabile2026qvacgenesisiii,\n  title         = {QVAC Genesis III: A Large-Scale, High-Quality Open Synthetic STEM Corpus for Efficient Language Model Pre-Training},\n  author        = {Davide Vitabile and Nikhil Ranjan and Akshay Nambiar and Kamal Kumar Gupta and Amril Nazir},\n  year          = {2026},\n  eprint        = {2609.19513},\n  archivePrefix = {arXiv},\n  primaryClass  = {cs.AI},\n  institution   = {Tether Data, S.A. de C.V. d.b.a. Tether AI Research},\n  note          = {Accepted at the Conference on Language Modeling (COLM) 2026},\n  url           = {https://arxiv.org/abs/2609.19513}\n}",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-4.0) is classified as having use restrictions.",
 "revision": "b7a894a7b4e13cbf98e0f8f7b909e90df15a110c",
 "stated_evidence": "https://huggingface.co/datasets/qvac/GenesisIII/blob/b7a894a7b4e13cbf98e0f8f7b909e90df15a110c/README.md",
 "file_evidence": "https://huggingface.co/datasets/qvac/GenesisIII/tree/b7a894a7b4e13cbf98e0f8f7b909e90df15a110c",
 "card_nc": false
}