{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HRE7NNGGRDDK22J2WAAKC6AORE","short_pith_number":"pith:HRE7NNGG","schema_version":"1.0","canonical_sha256":"3c49f6b4c688c6ad693ab000a1780e893a5431e671858c98c9da4b2d9a7a8fa2","source":{"kind":"arxiv","id":"2401.15975","version":1},"attestation_state":"computed","paper":{"title":"StableIdentity: Inserting Anybody into Anywhere at First Sight","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huchuan Lu, Liqian Ma, Qinghe Wang, Taiqing Li, Xiaomin Li, Xu Jia, Yunzhi Zhuge","submitted_at":"2024-01-29T09:06:15Z","abstract_excerpt":"Recent advances in large pretrained text-to-image models have shown unprecedented capabilities for high-quality human-centric generation, however, customizing face identity is still an intractable problem. Existing methods cannot ensure stable identity preservation and flexible editability, even with several images for each subject during training. In this work, we propose StableIdentity, which allows identity-consistent recontextualization with just one face image. More specifically, we employ a face encoder with an identity prior to encode the input face, and then land the face representatio"},"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":"2401.15975","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T09:06:15Z","cross_cats_sorted":[],"title_canon_sha256":"a519c36249ed900f42d83b308cfc10f05df093a8b05175166174120fcdab718a","abstract_canon_sha256":"dd74046030fa3d92c609dc56e832476046b2249c52f16cf3c42a733644d577aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:42.102098Z","signature_b64":"3mmYF79yo0Qf7uISgYJzTpM/cm0Et7IX7bsChyMRz3oHvUpj4ZNEYT8jQSko3+gVOU3L0aZAJAxIhv/YD45sDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c49f6b4c688c6ad693ab000a1780e893a5431e671858c98c9da4b2d9a7a8fa2","last_reissued_at":"2026-07-05T07:38:42.101570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:42.101570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StableIdentity: Inserting Anybody into Anywhere at First Sight","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huchuan Lu, Liqian Ma, Qinghe Wang, Taiqing Li, Xiaomin Li, Xu Jia, Yunzhi Zhuge","submitted_at":"2024-01-29T09:06:15Z","abstract_excerpt":"Recent advances in large pretrained text-to-image models have shown unprecedented capabilities for high-quality human-centric generation, however, customizing face identity is still an intractable problem. Existing methods cannot ensure stable identity preservation and flexible editability, even with several images for each subject during training. In this work, we propose StableIdentity, which allows identity-consistent recontextualization with just one face image. More specifically, we employ a face encoder with an identity prior to encode the input face, and then land the face representatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.15975","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/2401.15975/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":"2401.15975","created_at":"2026-07-05T07:38:42.101630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.15975v1","created_at":"2026-07-05T07:38:42.101630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.15975","created_at":"2026-07-05T07:38:42.101630+00:00"},{"alias_kind":"pith_short_12","alias_value":"HRE7NNGGRDDK","created_at":"2026-07-05T07:38:42.101630+00:00"},{"alias_kind":"pith_short_16","alias_value":"HRE7NNGGRDDK22J2","created_at":"2026-07-05T07:38:42.101630+00:00"},{"alias_kind":"pith_short_8","alias_value":"HRE7NNGG","created_at":"2026-07-05T07:38:42.101630+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30894","citing_title":"SteerFace: Debiasing Synthetic Face Generation via Adaptive Residue Perturbation","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HRE7NNGGRDDK22J2WAAKC6AORE","json":"https://pith.science/pith/HRE7NNGGRDDK22J2WAAKC6AORE.json","graph_json":"https://pith.science/api/pith-number/HRE7NNGGRDDK22J2WAAKC6AORE/graph.json","events_json":"https://pith.science/api/pith-number/HRE7NNGGRDDK22J2WAAKC6AORE/events.json","paper":"https://pith.science/paper/HRE7NNGG"},"agent_actions":{"view_html":"https://pith.science/pith/HRE7NNGGRDDK22J2WAAKC6AORE","download_json":"https://pith.science/pith/HRE7NNGGRDDK22J2WAAKC6AORE.json","view_paper":"https://pith.science/paper/HRE7NNGG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.15975&json=true","fetch_graph":"https://pith.science/api/pith-number/HRE7NNGGRDDK22J2WAAKC6AORE/graph.json","fetch_events":"https://pith.science/api/pith-number/HRE7NNGGRDDK22J2WAAKC6AORE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HRE7NNGGRDDK22J2WAAKC6AORE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HRE7NNGGRDDK22J2WAAKC6AORE/action/storage_attestation","attest_author":"https://pith.science/pith/HRE7NNGGRDDK22J2WAAKC6AORE/action/author_attestation","sign_citation":"https://pith.science/pith/HRE7NNGGRDDK22J2WAAKC6AORE/action/citation_signature","submit_replication":"https://pith.science/pith/HRE7NNGGRDDK22J2WAAKC6AORE/action/replication_record"}},"created_at":"2026-07-05T07:38:42.101630+00:00","updated_at":"2026-07-05T07:38:42.101630+00:00"}