{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W3O53F7FOY2NV7V4Y67H6YAWPM","short_pith_number":"pith:W3O53F7F","schema_version":"1.0","canonical_sha256":"b6dddd97e57634dafebcc7be7f60167b0ec80e7214eb56ddf260a586ac448063","source":{"kind":"arxiv","id":"2501.01633","version":1},"attestation_state":"computed","paper":{"title":"ACE: Anti-Editing Concept Erasure in Text-to-Image Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Li, Hang Xu, Renjing Pei, Wangmeng Zuo, Yuxiang Wei, Zihao Wang","submitted_at":"2025-01-03T04:57:27Z","abstract_excerpt":"Recent advance in text-to-image diffusion models have significantly facilitated the generation of high-quality images, but also raising concerns about the illegal creation of harmful content, such as copyrighted images. Existing concept erasure methods achieve superior results in preventing the production of erased concept from prompts, but typically perform poorly in preventing undesired editing. To address this issue, we propose an Anti-Editing Concept Erasure (ACE) method, which not only erases the target concept during generation but also filters out it during editing. Specifically, we pro"},"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":"2501.01633","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-03T04:57:27Z","cross_cats_sorted":[],"title_canon_sha256":"ca9fe120e0a3d8cb8d8f2e41b3b09d723fc289f39c880bc6ff7d0bc6252129e3","abstract_canon_sha256":"8b683f1589de622a3bf0205f8cc0a14704116aa82d551962510b6e7cfe1a9ed0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:27.988971Z","signature_b64":"0Zl8pvSX7WphljDBcV1AA9le2Fz4ydywOpAd5MPkq6KQ2dmB9FUGxaqJIZAhykbA0TwNU7aGHz9pTeilTPZaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6dddd97e57634dafebcc7be7f60167b0ec80e7214eb56ddf260a586ac448063","last_reissued_at":"2026-07-05T09:56:27.988542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:27.988542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ACE: Anti-Editing Concept Erasure in Text-to-Image Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Li, Hang Xu, Renjing Pei, Wangmeng Zuo, Yuxiang Wei, Zihao Wang","submitted_at":"2025-01-03T04:57:27Z","abstract_excerpt":"Recent advance in text-to-image diffusion models have significantly facilitated the generation of high-quality images, but also raising concerns about the illegal creation of harmful content, such as copyrighted images. Existing concept erasure methods achieve superior results in preventing the production of erased concept from prompts, but typically perform poorly in preventing undesired editing. To address this issue, we propose an Anti-Editing Concept Erasure (ACE) method, which not only erases the target concept during generation but also filters out it during editing. Specifically, we pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01633","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/2501.01633/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":"2501.01633","created_at":"2026-07-05T09:56:27.988598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.01633v1","created_at":"2026-07-05T09:56:27.988598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01633","created_at":"2026-07-05T09:56:27.988598+00:00"},{"alias_kind":"pith_short_12","alias_value":"W3O53F7FOY2N","created_at":"2026-07-05T09:56:27.988598+00:00"},{"alias_kind":"pith_short_16","alias_value":"W3O53F7FOY2NV7V4","created_at":"2026-07-05T09:56:27.988598+00:00"},{"alias_kind":"pith_short_8","alias_value":"W3O53F7F","created_at":"2026-07-05T09:56:27.988598+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.12782","citing_title":"Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts","ref_index":87,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W3O53F7FOY2NV7V4Y67H6YAWPM","json":"https://pith.science/pith/W3O53F7FOY2NV7V4Y67H6YAWPM.json","graph_json":"https://pith.science/api/pith-number/W3O53F7FOY2NV7V4Y67H6YAWPM/graph.json","events_json":"https://pith.science/api/pith-number/W3O53F7FOY2NV7V4Y67H6YAWPM/events.json","paper":"https://pith.science/paper/W3O53F7F"},"agent_actions":{"view_html":"https://pith.science/pith/W3O53F7FOY2NV7V4Y67H6YAWPM","download_json":"https://pith.science/pith/W3O53F7FOY2NV7V4Y67H6YAWPM.json","view_paper":"https://pith.science/paper/W3O53F7F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.01633&json=true","fetch_graph":"https://pith.science/api/pith-number/W3O53F7FOY2NV7V4Y67H6YAWPM/graph.json","fetch_events":"https://pith.science/api/pith-number/W3O53F7FOY2NV7V4Y67H6YAWPM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W3O53F7FOY2NV7V4Y67H6YAWPM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W3O53F7FOY2NV7V4Y67H6YAWPM/action/storage_attestation","attest_author":"https://pith.science/pith/W3O53F7FOY2NV7V4Y67H6YAWPM/action/author_attestation","sign_citation":"https://pith.science/pith/W3O53F7FOY2NV7V4Y67H6YAWPM/action/citation_signature","submit_replication":"https://pith.science/pith/W3O53F7FOY2NV7V4Y67H6YAWPM/action/replication_record"}},"created_at":"2026-07-05T09:56:27.988598+00:00","updated_at":"2026-07-05T09:56:27.988598+00:00"}