{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NYMVHH5BWQOIBW6DXEQXJOKY45","short_pith_number":"pith:NYMVHH5B","schema_version":"1.0","canonical_sha256":"6e19539fa1b41c80dbc3b92174b958e7748e0e7fb12acf14525e722fa8858e50","source":{"kind":"arxiv","id":"2502.16368","version":3},"attestation_state":"computed","paper":{"title":"Concept Corrector: Erase concepts on the fly for text-to-image diffusion models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Peng, Jing Dong, Tieniu Tan, Wei Wang, Xiaochuan Jin, Yueming Lyu, Zheling Meng","submitted_at":"2025-02-22T21:53:43Z","abstract_excerpt":"Text-to-image diffusion models have demonstrated the underlying risk of generating various unwanted content, such as sexual elements. To address this issue, the task of concept erasure has been introduced, aiming to erase any undesired concepts that the models can generate. Previous methods, whether training-based or training-free, have primarily focused on the input side, i.e., texts. However, they often suffer from incomplete erasure due to limitations in the generalization from limited prompts to diverse image content. In this paper, motivated by the notion that concept erasure on the outpu"},"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":"2502.16368","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-22T21:53:43Z","cross_cats_sorted":[],"title_canon_sha256":"6e25f4ff2645ea32f76bc1708e9db5e544ef2fcccccf80d1f0816fddf044329e","abstract_canon_sha256":"f3fd196ac03cd949512b9106a9896546f08732d47d3a615877465ec39ef380e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:27.670017Z","signature_b64":"CfdUL10GhKHZ1EeNQe3Ww1YlAiPcZ+1kjbwZx8iuYkekw96kXLoqR5qloSWIvGRarM6p55l5JVYT/WMlSAQICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e19539fa1b41c80dbc3b92174b958e7748e0e7fb12acf14525e722fa8858e50","last_reissued_at":"2026-07-05T11:14:27.669543Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:27.669543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Concept Corrector: Erase concepts on the fly for text-to-image diffusion models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Peng, Jing Dong, Tieniu Tan, Wei Wang, Xiaochuan Jin, Yueming Lyu, Zheling Meng","submitted_at":"2025-02-22T21:53:43Z","abstract_excerpt":"Text-to-image diffusion models have demonstrated the underlying risk of generating various unwanted content, such as sexual elements. To address this issue, the task of concept erasure has been introduced, aiming to erase any undesired concepts that the models can generate. Previous methods, whether training-based or training-free, have primarily focused on the input side, i.e., texts. However, they often suffer from incomplete erasure due to limitations in the generalization from limited prompts to diverse image content. In this paper, motivated by the notion that concept erasure on the outpu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16368","kind":"arxiv","version":3},"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/2502.16368/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":"2502.16368","created_at":"2026-07-05T11:14:27.669599+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.16368v3","created_at":"2026-07-05T11:14:27.669599+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16368","created_at":"2026-07-05T11:14:27.669599+00:00"},{"alias_kind":"pith_short_12","alias_value":"NYMVHH5BWQOI","created_at":"2026-07-05T11:14:27.669599+00:00"},{"alias_kind":"pith_short_16","alias_value":"NYMVHH5BWQOIBW6D","created_at":"2026-07-05T11:14:27.669599+00:00"},{"alias_kind":"pith_short_8","alias_value":"NYMVHH5B","created_at":"2026-07-05T11:14:27.669599+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15829","citing_title":"Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NYMVHH5BWQOIBW6DXEQXJOKY45","json":"https://pith.science/pith/NYMVHH5BWQOIBW6DXEQXJOKY45.json","graph_json":"https://pith.science/api/pith-number/NYMVHH5BWQOIBW6DXEQXJOKY45/graph.json","events_json":"https://pith.science/api/pith-number/NYMVHH5BWQOIBW6DXEQXJOKY45/events.json","paper":"https://pith.science/paper/NYMVHH5B"},"agent_actions":{"view_html":"https://pith.science/pith/NYMVHH5BWQOIBW6DXEQXJOKY45","download_json":"https://pith.science/pith/NYMVHH5BWQOIBW6DXEQXJOKY45.json","view_paper":"https://pith.science/paper/NYMVHH5B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.16368&json=true","fetch_graph":"https://pith.science/api/pith-number/NYMVHH5BWQOIBW6DXEQXJOKY45/graph.json","fetch_events":"https://pith.science/api/pith-number/NYMVHH5BWQOIBW6DXEQXJOKY45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NYMVHH5BWQOIBW6DXEQXJOKY45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NYMVHH5BWQOIBW6DXEQXJOKY45/action/storage_attestation","attest_author":"https://pith.science/pith/NYMVHH5BWQOIBW6DXEQXJOKY45/action/author_attestation","sign_citation":"https://pith.science/pith/NYMVHH5BWQOIBW6DXEQXJOKY45/action/citation_signature","submit_replication":"https://pith.science/pith/NYMVHH5BWQOIBW6DXEQXJOKY45/action/replication_record"}},"created_at":"2026-07-05T11:14:27.669599+00:00","updated_at":"2026-07-05T11:14:27.669599+00:00"}