{
 "id": "strifero/attribution-groundtruth",
 "owner": "strifero",
 "name": "attribution-groundtruth",
 "downloads": 55,
 "likes": 0,
 "last_modified": "2026-10-27T00:47:39.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "A benchmark for methods that claim to tell you which training data taught a model something. Two small models were trained from scratch on the same ordered 5B-token stream, differing only in which half of 528 fictional facts their planted documents stated. Because we planted the documents, we know the right answer; because we have the twin that never saw each fact, we can measure what each document actually did.\n\n- Models: [tda-124m-A](https://huggingface.co/strifero/tda-124m-A) and [tda-124m-B](https://huggingface.co/strifero/tda-124m-B), with checkpoints every 0.5B tokens\n- Report: [Paper trail](https://trifero.ai/research/paper-trail/)\n- Code (stream builder, training, every method, scoring): [https://github.com/strifero/attribution-groundtruth](https://github.com/strifero/attribution-groundtruth)\n\nAll planted content is fictional. The base training text is not redistributed here; `stream/` holds the exact recipe and order to rebuild it, with a hash of every window to check the rebuild.",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "02fc811a6ea7f49dbab0a5ed6995d46689762a61",
 "stated_evidence": "https://huggingface.co/datasets/strifero/attribution-groundtruth/blob/02fc811a6ea7f49dbab0a5ed6995d46689762a61/README.md",
 "file_evidence": "https://huggingface.co/datasets/strifero/attribution-groundtruth/tree/02fc811a6ea7f49dbab0a5ed6995d46689762a61",
 "card_nc": false
}