{
 "id": "dataseek/ptbr-academic",
 "owner": "dataseek",
 "name": "ptbr-academic",
 "downloads": 37,
 "likes": 0,
 "last_modified": "2026-05-12T16:15:33.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@misc{magtina350m_pretrain_2026,\n  title  = {MagTina350m pretrain corpus — PT-BR Academic Corpus (CAPES theses + SciELO abstracts/books)},\n  author = {Frasson, Ricardo and {Dataseek Team}},\n  year   = 2026,\n  publisher = {Hugging Face},\n  url    = {https://huggingface.co/datasets/dataseek/ptbr-academic}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "0e8a57c2e2ef6730836db7cb0d0b684928f361f6",
 "stated_evidence": "https://huggingface.co/datasets/dataseek/ptbr-academic/blob/0e8a57c2e2ef6730836db7cb0d0b684928f361f6/README.md",
 "file_evidence": "https://huggingface.co/datasets/dataseek/ptbr-academic/tree/0e8a57c2e2ef6730836db7cb0d0b684928f361f6",
 "card_nc": false
}