{
 "id": "CLS-Lab/narradolma",
 "owner": "CLS-Lab",
 "name": "narradolma",
 "downloads": 344,
 "likes": 1,
 "last_modified": "2026-09-09T05:32:39.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@misc{johnson2026narrative,\n  title         = {Characterizing Narrative Content in Web-scale LLM Pretraining Data},\n  author        = {Johnson, Teagan and Ash, Elliott and Piper, Andrew and Antoniak, Maria},\n  year          = {2026},\n  eprint        = {2606.19468},\n  archivePrefix = {arXiv},\n  primaryClass  = {cs.CL},\n  url           = {https://arxiv.org/abs/2606.19468}\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "d7954cf580ecf1d6e80800567e99c92923fbb7f5",
 "stated_evidence": "https://huggingface.co/datasets/CLS-Lab/narradolma/blob/d7954cf580ecf1d6e80800567e99c92923fbb7f5/README.md",
 "file_evidence": "https://huggingface.co/datasets/CLS-Lab/narradolma/tree/d7954cf580ecf1d6e80800567e99c92923fbb7f5",
 "card_nc": false
}