{
 "id": "alegendaryfish/CodonTranslator-data",
 "owner": "alegendaryfish",
 "name": "CodonTranslator-data",
 "downloads": 1009,
 "likes": 1,
 "last_modified": "2026-04-08T01:44:23.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": "cc-by-4.0",
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "This release redistributes processed training data and derived embeddings for reproducibility of the CodonTranslator experiments. See the audit files in `_work/` for construction details and final verification outputs.\n\nThe raw MMseqs working database is not included because it is large, machine-specific intermediate state. The released `_work/` files are the reproducibility artifacts needed to audit and reconstruct the clustering and split decisions.",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "370c4e1d84ea044854053350fb02f2f891106542",
 "stated_evidence": "https://huggingface.co/datasets/alegendaryfish/CodonTranslator-data/blob/370c4e1d84ea044854053350fb02f2f891106542/README.md",
 "file_evidence": "https://huggingface.co/datasets/alegendaryfish/CodonTranslator-data/blob/370c4e1d84ea044854053350fb02f2f891106542/LICENSE",
 "card_nc": false
}