{
 "id": "soberania/jabuticaba",
 "owner": "soberania",
 "name": "jabuticaba",
 "downloads": 10,
 "likes": 21,
 "last_modified": "2025-08-05T18:49:15.000Z",
 "stated_licence": "cc-by-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "manual",
 "tasks": [
  "text-generation",
  "fill-mask"
 ],
 "citation": "@article{Amadeus_Cruz Castaneda_Homeli da Silva_Scotti_2025,\n    title={Jabuticaba: The largest commercial corpus for LLMs in Portuguese},\n    url={https://preprints.scielo.org/index.php/scielo/preprint/view/12696},\n    DOI={10.1590/SciELOPreprints.12696},\n    journal={SciELO Preprints},\n    author={Amadeus, Marcellus and Cruz Castaneda, William Alberto and Homeli da Silva, José Roberto and Scotti, Rodrigo},\n    year={2025},\n    month={ago.}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "847fcaea609b482308f38ddfaa1148bc81ee05f9",
 "stated_evidence": "https://huggingface.co/datasets/soberania/jabuticaba/blob/847fcaea609b482308f38ddfaa1148bc81ee05f9/README.md",
 "file_evidence": "https://huggingface.co/datasets/soberania/jabuticaba/tree/847fcaea609b482308f38ddfaa1148bc81ee05f9",
 "card_nc": false
}