{
 "id": "ashtok897/indic-hplt-v2",
 "owner": "ashtok897",
 "name": "indic-hplt-v2",
 "downloads": 710,
 "likes": 3,
 "last_modified": "2026-06-09T23:26:43.000Z",
 "stated_licence": "cc0-1.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [
  {
   "id": "hplt-project/hplt_monolingual_v3",
   "licence": null,
   "found": false,
   "evidence": "https://huggingface.co/datasets/hplt-project/hplt_monolingual_v3"
  }
 ],
 "gated": false,
 "tasks": [
  "text-generation",
  "fill-mask"
 ],
 "citation": "@dataset{indicHPLTv2_2026,\n  author    = {Mahajan, Ashutosh},\n  title     = {Indic {HPLT} v2: A 34.6M-document Multilingual Corpus for 13 Indic Languages and English},\n  year      = {2026},\n  publisher = {Hugging Face},\n  url       = {https://huggingface.co/datasets/ashtok897/indic-hplt-v2}\n}\n\n@article{oepen2025hplt,\n  title   = {{HPLT} 3.0: Very Large-Scale Multilingual Resources for {LLM} and {MT}},\n  author  = {Oepen, Stephan and others},\n  journal = {arXiv preprint arXiv:2511.01066},\n  year    = {2025}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID for at least one declared source dataset.",
 "revision": "5c4ec3ff627f29aa8e8cf3f2062b9a20ac61330f",
 "stated_evidence": "https://huggingface.co/datasets/ashtok897/indic-hplt-v2/blob/5c4ec3ff627f29aa8e8cf3f2062b9a20ac61330f/README.md",
 "file_evidence": "https://huggingface.co/datasets/ashtok897/indic-hplt-v2/tree/5c4ec3ff627f29aa8e8cf3f2062b9a20ac61330f",
 "card_nc": false
}