{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7Q4GRMAIVQNA2Z6YOMWPSXNV7X","short_pith_number":"pith:7Q4GRMAI","schema_version":"1.0","canonical_sha256":"fc3868b008ac1a0d67d8732cf95db5fdec08c1dbc24a5d1b73e3bec7428c8b14","source":{"kind":"arxiv","id":"2407.21032","version":1},"attestation_state":"computed","paper":{"title":"Safeguard Text-to-Image Diffusion Models with Human Feedback Inversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Balhae Kim, Jinwoo Shin, Juho Lee, Moonseok Choi, Sanghyun Kim, Seohyeon Jung","submitted_at":"2024-07-17T05:21:41Z","abstract_excerpt":"This paper addresses the societal concerns arising from large-scale text-to-image diffusion models for generating potentially harmful or copyrighted content. Existing models rely heavily on internet-crawled data, wherein problematic concepts persist due to incomplete filtration processes. While previous approaches somewhat alleviate the issue, they often rely on text-specified concepts, introducing challenges in accurately capturing nuanced concepts and aligning model knowledge with human understandings. In response, we propose a framework named Human Feedback Inversion (HFI), where human feed"},"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":"2407.21032","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T05:21:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0c23bd6563413b6558fb1105cda82e57cef0c670e0a52ba8b05ef3011ab82a4f","abstract_canon_sha256":"f828ae031529a1bd769f129a0d44e737fee1aec4c2aa7fde8ba205affc1f1921"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:32.230713Z","signature_b64":"Wv7chI0EeiNp76TmN0CcQzEp9o5c03NKUdpMpikVSFYk0+geYPxmlZBi3tgew/mipktl6WraB7BykLSsjn51Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc3868b008ac1a0d67d8732cf95db5fdec08c1dbc24a5d1b73e3bec7428c8b14","last_reissued_at":"2026-07-05T08:50:32.230303Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:32.230303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safeguard Text-to-Image Diffusion Models with Human Feedback Inversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Balhae Kim, Jinwoo Shin, Juho Lee, Moonseok Choi, Sanghyun Kim, Seohyeon Jung","submitted_at":"2024-07-17T05:21:41Z","abstract_excerpt":"This paper addresses the societal concerns arising from large-scale text-to-image diffusion models for generating potentially harmful or copyrighted content. Existing models rely heavily on internet-crawled data, wherein problematic concepts persist due to incomplete filtration processes. While previous approaches somewhat alleviate the issue, they often rely on text-specified concepts, introducing challenges in accurately capturing nuanced concepts and aligning model knowledge with human understandings. In response, we propose a framework named Human Feedback Inversion (HFI), where human feed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21032","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/2407.21032/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":"2407.21032","created_at":"2026-07-05T08:50:32.230369+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.21032v1","created_at":"2026-07-05T08:50:32.230369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21032","created_at":"2026-07-05T08:50:32.230369+00:00"},{"alias_kind":"pith_short_12","alias_value":"7Q4GRMAIVQNA","created_at":"2026-07-05T08:50:32.230369+00:00"},{"alias_kind":"pith_short_16","alias_value":"7Q4GRMAIVQNA2Z6Y","created_at":"2026-07-05T08:50:32.230369+00:00"},{"alias_kind":"pith_short_8","alias_value":"7Q4GRMAI","created_at":"2026-07-05T08:50:32.230369+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.01633","citing_title":"ACE: Anti-Editing Concept Erasure in Text-to-Image Models","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7Q4GRMAIVQNA2Z6YOMWPSXNV7X","json":"https://pith.science/pith/7Q4GRMAIVQNA2Z6YOMWPSXNV7X.json","graph_json":"https://pith.science/api/pith-number/7Q4GRMAIVQNA2Z6YOMWPSXNV7X/graph.json","events_json":"https://pith.science/api/pith-number/7Q4GRMAIVQNA2Z6YOMWPSXNV7X/events.json","paper":"https://pith.science/paper/7Q4GRMAI"},"agent_actions":{"view_html":"https://pith.science/pith/7Q4GRMAIVQNA2Z6YOMWPSXNV7X","download_json":"https://pith.science/pith/7Q4GRMAIVQNA2Z6YOMWPSXNV7X.json","view_paper":"https://pith.science/paper/7Q4GRMAI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.21032&json=true","fetch_graph":"https://pith.science/api/pith-number/7Q4GRMAIVQNA2Z6YOMWPSXNV7X/graph.json","fetch_events":"https://pith.science/api/pith-number/7Q4GRMAIVQNA2Z6YOMWPSXNV7X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7Q4GRMAIVQNA2Z6YOMWPSXNV7X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7Q4GRMAIVQNA2Z6YOMWPSXNV7X/action/storage_attestation","attest_author":"https://pith.science/pith/7Q4GRMAIVQNA2Z6YOMWPSXNV7X/action/author_attestation","sign_citation":"https://pith.science/pith/7Q4GRMAIVQNA2Z6YOMWPSXNV7X/action/citation_signature","submit_replication":"https://pith.science/pith/7Q4GRMAIVQNA2Z6YOMWPSXNV7X/action/replication_record"}},"created_at":"2026-07-05T08:50:32.230369+00:00","updated_at":"2026-07-05T08:50:32.230369+00:00"}