{
 "id": "hanyuy/prior-shift-diagnostic",
 "owner": "hanyuy",
 "name": "prior-shift-diagnostic",
 "downloads": 346,
 "likes": 0,
 "last_modified": "2026-10-12T01:43:20.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": "mit",
 "licence_files": [
  "LICENSE",
  "LICENSE-DOCS"
 ],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "Archived on Zenodo: [10.5281/zenodo.23304208](https://doi.org/10.5281/zenodo.23304208) (this\nversion; all versions: 10.5281/zenodo.23304207). See `CITATION.cff`. **Everything, data included, is CC BY 4.0** (`LICENSE-DOCS`). The code\n(`code/`, `reproduce.sh`, `verify_data.py`, `test_verify_data.py`) is additionally offered under MIT\n(`LICENSE`); GitHub's sidebar shows only the latter.\n\nSource data: documents from one DCLM shard of `allenai/olmo-mix-1124` (ODC-BY; its DCLM-Baseline\npart is CC BY 4.0). No corpus text is redistributed here, only document indices, SHA-256 hashes,\ntoken counts and per-document loss sums.",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "862587b16c5b17b1ea6047839a11240f3f17aa3b",
 "stated_evidence": "https://huggingface.co/datasets/hanyuy/prior-shift-diagnostic/blob/862587b16c5b17b1ea6047839a11240f3f17aa3b/README.md",
 "file_evidence": "https://huggingface.co/datasets/hanyuy/prior-shift-diagnostic/blob/862587b16c5b17b1ea6047839a11240f3f17aa3b/LICENSE",
 "card_nc": false
}