{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZYSCEQKERN7PUEKIHT7DXO6CI6","short_pith_number":"pith:ZYSCEQKE","schema_version":"1.0","canonical_sha256":"ce242241448b7efa11483cfe3bbbc24789657ba877d2ef820225520b8e26d65c","source":{"kind":"arxiv","id":"2311.00500","version":2},"attestation_state":"computed","paper":{"title":"Intriguing Properties of Data Attribution on Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Chao Du, Jing Jiang, Min Lin, Tianyu Pang, Xiaosen Zheng","submitted_at":"2023-11-01T13:00:46Z","abstract_excerpt":"Data attribution seeks to trace model outputs back to training data. With the recent development of diffusion models, data attribution has become a desired module to properly assign valuations for high-quality or copyrighted training samples, ensuring that data contributors are fairly compensated or credited. Several theoretically motivated methods have been proposed to implement data attribution, in an effort to improve the trade-off between computational scalability and effectiveness. In this work, we conduct extensive experiments and ablation studies on attributing diffusion models, specifi"},"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":"2311.00500","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T13:00:46Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"18bfd6c54c8a85a388b9cda4589c19cd46cada35d95fb52fc2dcb68e6b035bc5","abstract_canon_sha256":"a439a1c444967abe786d2d2c0e5e11f27f96bd856a2748689fc11a17b49b7f32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:18.453464Z","signature_b64":"2QAhAeahnRfYYkDS2Zpip7+Bza59KdO+M0Sbp8Jk9vZLHTIiPjvlCdCpvmbiacrkvIJi755m6fur55KZ6NVyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce242241448b7efa11483cfe3bbbc24789657ba877d2ef820225520b8e26d65c","last_reissued_at":"2026-07-05T07:56:18.452972Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:18.452972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Intriguing Properties of Data Attribution on Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Chao Du, Jing Jiang, Min Lin, Tianyu Pang, Xiaosen Zheng","submitted_at":"2023-11-01T13:00:46Z","abstract_excerpt":"Data attribution seeks to trace model outputs back to training data. With the recent development of diffusion models, data attribution has become a desired module to properly assign valuations for high-quality or copyrighted training samples, ensuring that data contributors are fairly compensated or credited. Several theoretically motivated methods have been proposed to implement data attribution, in an effort to improve the trade-off between computational scalability and effectiveness. In this work, we conduct extensive experiments and ablation studies on attributing diffusion models, specifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00500","kind":"arxiv","version":2},"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/2311.00500/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":"2311.00500","created_at":"2026-07-05T07:56:18.453037+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.00500v2","created_at":"2026-07-05T07:56:18.453037+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00500","created_at":"2026-07-05T07:56:18.453037+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZYSCEQKERN7P","created_at":"2026-07-05T07:56:18.453037+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZYSCEQKERN7PUEKI","created_at":"2026-07-05T07:56:18.453037+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZYSCEQKE","created_at":"2026-07-05T07:56:18.453037+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15520","citing_title":"On the Fragility of Data Attribution When Learning Is Distributed","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZYSCEQKERN7PUEKIHT7DXO6CI6","json":"https://pith.science/pith/ZYSCEQKERN7PUEKIHT7DXO6CI6.json","graph_json":"https://pith.science/api/pith-number/ZYSCEQKERN7PUEKIHT7DXO6CI6/graph.json","events_json":"https://pith.science/api/pith-number/ZYSCEQKERN7PUEKIHT7DXO6CI6/events.json","paper":"https://pith.science/paper/ZYSCEQKE"},"agent_actions":{"view_html":"https://pith.science/pith/ZYSCEQKERN7PUEKIHT7DXO6CI6","download_json":"https://pith.science/pith/ZYSCEQKERN7PUEKIHT7DXO6CI6.json","view_paper":"https://pith.science/paper/ZYSCEQKE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.00500&json=true","fetch_graph":"https://pith.science/api/pith-number/ZYSCEQKERN7PUEKIHT7DXO6CI6/graph.json","fetch_events":"https://pith.science/api/pith-number/ZYSCEQKERN7PUEKIHT7DXO6CI6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZYSCEQKERN7PUEKIHT7DXO6CI6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZYSCEQKERN7PUEKIHT7DXO6CI6/action/storage_attestation","attest_author":"https://pith.science/pith/ZYSCEQKERN7PUEKIHT7DXO6CI6/action/author_attestation","sign_citation":"https://pith.science/pith/ZYSCEQKERN7PUEKIHT7DXO6CI6/action/citation_signature","submit_replication":"https://pith.science/pith/ZYSCEQKERN7PUEKIHT7DXO6CI6/action/replication_record"}},"created_at":"2026-07-05T07:56:18.453037+00:00","updated_at":"2026-07-05T07:56:18.453037+00:00"}