{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NAWAIJJZVEYCPMCPZV5SPTKCT7","short_pith_number":"pith:NAWAIJJZ","schema_version":"1.0","canonical_sha256":"682c042539a93027b04fcd7b27cd429fc4e3c7d418e65781399749c340a24131","source":{"kind":"arxiv","id":"2308.14761","version":2},"attestation_state":"computed","paper":{"title":"Unified Concept Editing in Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"David Bau, Hadas Orgad, Joanna Materzy\\'nska, Rohit Gandikota, Yonatan Belinkov","submitted_at":"2023-08-25T17:59:59Z","abstract_excerpt":"Text-to-image models suffer from various safety issues that may limit their suitability for deployment. Previous methods have separately addressed individual issues of bias, copyright, and offensive content in text-to-image models. However, in the real world, all of these issues appear simultaneously in the same model. We present a method that tackles all issues with a single approach. Our method, Unified Concept Editing (UCE), edits the model without training using a closed-form solution, and scales seamlessly to concurrent edits on text-conditional diffusion models. We demonstrate scalable s"},"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":"2308.14761","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-25T17:59:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"06660029ab43a80c0fe2f73b7c9295178aeca5699763db7245bb825f1eee4094","abstract_canon_sha256":"5a18e4ee6ae78edcc80428226649236fab029ef846593d0038dbfec599a2c4c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:51.713597Z","signature_b64":"2JpIlkEtSX713ntA+2B+9UyCh5Jkukuk3xu9c/iuR9ge6aQvFl4CDequi3LIlbaN05EI6VZ4HKXgfVhjfdIZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"682c042539a93027b04fcd7b27cd429fc4e3c7d418e65781399749c340a24131","last_reissued_at":"2026-07-05T09:24:51.713114Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:51.713114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Concept Editing in Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"David Bau, Hadas Orgad, Joanna Materzy\\'nska, Rohit Gandikota, Yonatan Belinkov","submitted_at":"2023-08-25T17:59:59Z","abstract_excerpt":"Text-to-image models suffer from various safety issues that may limit their suitability for deployment. Previous methods have separately addressed individual issues of bias, copyright, and offensive content in text-to-image models. However, in the real world, all of these issues appear simultaneously in the same model. We present a method that tackles all issues with a single approach. Our method, Unified Concept Editing (UCE), edits the model without training using a closed-form solution, and scales seamlessly to concurrent edits on text-conditional diffusion models. We demonstrate scalable s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.14761","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/2308.14761/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":"2308.14761","created_at":"2026-07-05T09:24:51.713175+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.14761v2","created_at":"2026-07-05T09:24:51.713175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.14761","created_at":"2026-07-05T09:24:51.713175+00:00"},{"alias_kind":"pith_short_12","alias_value":"NAWAIJJZVEYC","created_at":"2026-07-05T09:24:51.713175+00:00"},{"alias_kind":"pith_short_16","alias_value":"NAWAIJJZVEYCPMCP","created_at":"2026-07-05T09:24:51.713175+00:00"},{"alias_kind":"pith_short_8","alias_value":"NAWAIJJZ","created_at":"2026-07-05T09:24:51.713175+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16363","citing_title":"CSF: Black-box Fingerprinting via Compositional Semantics for Text-to-Image Models","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NAWAIJJZVEYCPMCPZV5SPTKCT7","json":"https://pith.science/pith/NAWAIJJZVEYCPMCPZV5SPTKCT7.json","graph_json":"https://pith.science/api/pith-number/NAWAIJJZVEYCPMCPZV5SPTKCT7/graph.json","events_json":"https://pith.science/api/pith-number/NAWAIJJZVEYCPMCPZV5SPTKCT7/events.json","paper":"https://pith.science/paper/NAWAIJJZ"},"agent_actions":{"view_html":"https://pith.science/pith/NAWAIJJZVEYCPMCPZV5SPTKCT7","download_json":"https://pith.science/pith/NAWAIJJZVEYCPMCPZV5SPTKCT7.json","view_paper":"https://pith.science/paper/NAWAIJJZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.14761&json=true","fetch_graph":"https://pith.science/api/pith-number/NAWAIJJZVEYCPMCPZV5SPTKCT7/graph.json","fetch_events":"https://pith.science/api/pith-number/NAWAIJJZVEYCPMCPZV5SPTKCT7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NAWAIJJZVEYCPMCPZV5SPTKCT7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NAWAIJJZVEYCPMCPZV5SPTKCT7/action/storage_attestation","attest_author":"https://pith.science/pith/NAWAIJJZVEYCPMCPZV5SPTKCT7/action/author_attestation","sign_citation":"https://pith.science/pith/NAWAIJJZVEYCPMCPZV5SPTKCT7/action/citation_signature","submit_replication":"https://pith.science/pith/NAWAIJJZVEYCPMCPZV5SPTKCT7/action/replication_record"}},"created_at":"2026-07-05T09:24:51.713175+00:00","updated_at":"2026-07-05T09:24:51.713175+00:00"}