{
 "id": "juliannunezb/crisp-v8",
 "owner": "juliannunezb",
 "name": "crisp-v8",
 "downloads": 6,
 "likes": 0,
 "last_modified": "2026-09-16T20:04:05.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "mixed-upstream-licenses",
 "licence_link": "https://huggingface.co/datasets/juliannunezb/crisp-v8#licensing-and-access",
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "manual",
 "tasks": [
  "text-generation"
 ],
 "citation": "@misc{nunez_crisp_v8_2026,\n  author = {Julián Núñez Barrero},\n  title  = {crisp-v8: an 8B-token single-digit-tokenizer pretraining corpus in two nested-sampled phases},\n  year   = {2026},\n  url    = {https://huggingface.co/datasets/juliannunezb/crisp-v8}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "09c6bc2c9ad6c10675c60b7b96e75b0dcb80080c",
 "stated_evidence": "https://huggingface.co/datasets/juliannunezb/crisp-v8/blob/09c6bc2c9ad6c10675c60b7b96e75b0dcb80080c/README.md",
 "file_evidence": "https://huggingface.co/datasets/juliannunezb/crisp-v8/tree/09c6bc2c9ad6c10675c60b7b96e75b0dcb80080c",
 "card_nc": false
}