{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KLI7Q5N7RBNP642PH2ART4CXRB","short_pith_number":"pith:KLI7Q5N7","schema_version":"1.0","canonical_sha256":"52d1f875bf885aff734f3e8119f0578841f2ee5d0b5d24bf8624aee17906a499","source":{"kind":"arxiv","id":"2306.09345","version":2},"attestation_state":"computed","paper":{"title":"Evaluating Data Attribution for Text-to-Image Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexei A. Efros, Jun-Yan Zhu, Richard Zhang, Sheng-Yu Wang","submitted_at":"2023-06-15T17:59:51Z","abstract_excerpt":"While large text-to-image models are able to synthesize \"novel\" images, these images are necessarily a reflection of the training data. The problem of data attribution in such models -- which of the images in the training set are most responsible for the appearance of a given generated image -- is a difficult yet important one. As an initial step toward this problem, we evaluate attribution through \"customization\" methods, which tune an existing large-scale model toward a given exemplar object or style. Our key insight is that this allows us to efficiently create synthetic images that are comp"},"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":"2306.09345","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-15T17:59:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9e0ac3175ee33f28ac04587270e1bae498a39809ed2ce8f395b5d00fb86aa2a4","abstract_canon_sha256":"669ab6046ac47b0f9d4fa39dd8686183d3141e04edeac69483a8015e71f3ce9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:00.761730Z","signature_b64":"x2cThORvVcnpSyoyL/gUocPRB2H6eeq8g/YuiOj2dlfw7Fb69Dk91QofwVImE40xTHBEi3hptvg6WbFxjeMrAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52d1f875bf885aff734f3e8119f0578841f2ee5d0b5d24bf8624aee17906a499","last_reissued_at":"2026-07-05T06:39:00.761379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:00.761379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Data Attribution for Text-to-Image Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexei A. Efros, Jun-Yan Zhu, Richard Zhang, Sheng-Yu Wang","submitted_at":"2023-06-15T17:59:51Z","abstract_excerpt":"While large text-to-image models are able to synthesize \"novel\" images, these images are necessarily a reflection of the training data. The problem of data attribution in such models -- which of the images in the training set are most responsible for the appearance of a given generated image -- is a difficult yet important one. As an initial step toward this problem, we evaluate attribution through \"customization\" methods, which tune an existing large-scale model toward a given exemplar object or style. Our key insight is that this allows us to efficiently create synthetic images that are comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09345","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/2306.09345/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":"2306.09345","created_at":"2026-07-05T06:39:00.761435+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.09345v2","created_at":"2026-07-05T06:39:00.761435+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09345","created_at":"2026-07-05T06:39:00.761435+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLI7Q5N7RBNP","created_at":"2026-07-05T06:39:00.761435+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLI7Q5N7RBNP642P","created_at":"2026-07-05T06:39:00.761435+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLI7Q5N7","created_at":"2026-07-05T06:39:00.761435+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19313","citing_title":"Concept Reachability in Diffusion Models: Beyond Dataset Constraints","ref_index":2017,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KLI7Q5N7RBNP642PH2ART4CXRB","json":"https://pith.science/pith/KLI7Q5N7RBNP642PH2ART4CXRB.json","graph_json":"https://pith.science/api/pith-number/KLI7Q5N7RBNP642PH2ART4CXRB/graph.json","events_json":"https://pith.science/api/pith-number/KLI7Q5N7RBNP642PH2ART4CXRB/events.json","paper":"https://pith.science/paper/KLI7Q5N7"},"agent_actions":{"view_html":"https://pith.science/pith/KLI7Q5N7RBNP642PH2ART4CXRB","download_json":"https://pith.science/pith/KLI7Q5N7RBNP642PH2ART4CXRB.json","view_paper":"https://pith.science/paper/KLI7Q5N7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.09345&json=true","fetch_graph":"https://pith.science/api/pith-number/KLI7Q5N7RBNP642PH2ART4CXRB/graph.json","fetch_events":"https://pith.science/api/pith-number/KLI7Q5N7RBNP642PH2ART4CXRB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLI7Q5N7RBNP642PH2ART4CXRB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLI7Q5N7RBNP642PH2ART4CXRB/action/storage_attestation","attest_author":"https://pith.science/pith/KLI7Q5N7RBNP642PH2ART4CXRB/action/author_attestation","sign_citation":"https://pith.science/pith/KLI7Q5N7RBNP642PH2ART4CXRB/action/citation_signature","submit_replication":"https://pith.science/pith/KLI7Q5N7RBNP642PH2ART4CXRB/action/replication_record"}},"created_at":"2026-07-05T06:39:00.761435+00:00","updated_at":"2026-07-05T06:39:00.761435+00:00"}