{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YZHQRTXG4P7IJ7QYQ3GEOHBGLA","short_pith_number":"pith:YZHQRTXG","schema_version":"1.0","canonical_sha256":"c64f08cee6e3fe84fe1886cc471c26581b98e7b2dc830498cf022ad62c44474a","source":{"kind":"arxiv","id":"2509.09873","version":1},"attestation_state":"computed","paper":{"title":"From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Ahmed E. Hassan, Bram Adams, Gopi Krishnan Rajbahadur, Hao Li, James Jewitt","submitted_at":"2025-09-11T21:46:20Z","abstract_excerpt":"Hidden license conflicts in the open-source AI ecosystem pose serious legal and ethical risks, exposing organizations to potential litigation and users to undisclosed risk. However, the field lacks a data-driven understanding of how frequently these conflicts occur, where they originate, and which communities are most affected. We present the first end-to-end audit of licenses for datasets and models on Hugging Face, as well as their downstream integration into open-source software applications, covering 364 thousand datasets, 1.6 million models, and 140 thousand GitHub projects. Our empirical"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2509.09873","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-09-11T21:46:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9a99f944040cef5aab56850c59d481893d40a5a6f8b9733e63e0cd71873041da","abstract_canon_sha256":"f29619c267222d3eaa9a24bf4722ce37c8f595d1ebdd3df780aa1b7394428848"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:51.093049Z","signature_b64":"T1pc9ywsDK36Jsz9BswOYgWSQdOq7mlLManoaxVDLFKXqV5A1m3Pk5N1AyfpPToeIToRHt7X0Xpgaelq7iKMBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c64f08cee6e3fe84fe1886cc471c26581b98e7b2dc830498cf022ad62c44474a","last_reissued_at":"2026-07-05T12:09:51.092513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:51.092513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Ahmed E. Hassan, Bram Adams, Gopi Krishnan Rajbahadur, Hao Li, James Jewitt","submitted_at":"2025-09-11T21:46:20Z","abstract_excerpt":"Hidden license conflicts in the open-source AI ecosystem pose serious legal and ethical risks, exposing organizations to potential litigation and users to undisclosed risk. However, the field lacks a data-driven understanding of how frequently these conflicts occur, where they originate, and which communities are most affected. We present the first end-to-end audit of licenses for datasets and models on Hugging Face, as well as their downstream integration into open-source software applications, covering 364 thousand datasets, 1.6 million models, and 140 thousand GitHub projects. Our empirical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09873","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.09873/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2509.09873","created_at":"2026-07-05T12:09:51.092578+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.09873v1","created_at":"2026-07-05T12:09:51.092578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09873","created_at":"2026-07-05T12:09:51.092578+00:00"},{"alias_kind":"pith_short_12","alias_value":"YZHQRTXG4P7I","created_at":"2026-07-05T12:09:51.092578+00:00"},{"alias_kind":"pith_short_16","alias_value":"YZHQRTXG4P7IJ7QY","created_at":"2026-07-05T12:09:51.092578+00:00"},{"alias_kind":"pith_short_8","alias_value":"YZHQRTXG","created_at":"2026-07-05T12:09:51.092578+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.21787","citing_title":"Towards Imputation of Pre-Trained Language Model Metadata using Semantic Fingerprinting","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.24383","citing_title":"A governance horizon for ethical-use constraints in open-weight AI models","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YZHQRTXG4P7IJ7QYQ3GEOHBGLA","json":"https://pith.science/pith/YZHQRTXG4P7IJ7QYQ3GEOHBGLA.json","graph_json":"https://pith.science/api/pith-number/YZHQRTXG4P7IJ7QYQ3GEOHBGLA/graph.json","events_json":"https://pith.science/api/pith-number/YZHQRTXG4P7IJ7QYQ3GEOHBGLA/events.json","paper":"https://pith.science/paper/YZHQRTXG"},"agent_actions":{"view_html":"https://pith.science/pith/YZHQRTXG4P7IJ7QYQ3GEOHBGLA","download_json":"https://pith.science/pith/YZHQRTXG4P7IJ7QYQ3GEOHBGLA.json","view_paper":"https://pith.science/paper/YZHQRTXG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.09873&json=true","fetch_graph":"https://pith.science/api/pith-number/YZHQRTXG4P7IJ7QYQ3GEOHBGLA/graph.json","fetch_events":"https://pith.science/api/pith-number/YZHQRTXG4P7IJ7QYQ3GEOHBGLA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YZHQRTXG4P7IJ7QYQ3GEOHBGLA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YZHQRTXG4P7IJ7QYQ3GEOHBGLA/action/storage_attestation","attest_author":"https://pith.science/pith/YZHQRTXG4P7IJ7QYQ3GEOHBGLA/action/author_attestation","sign_citation":"https://pith.science/pith/YZHQRTXG4P7IJ7QYQ3GEOHBGLA/action/citation_signature","submit_replication":"https://pith.science/pith/YZHQRTXG4P7IJ7QYQ3GEOHBGLA/action/replication_record"}},"created_at":"2026-07-05T12:09:51.092578+00:00","updated_at":"2026-07-05T12:09:51.092578+00:00"}