{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3ZO2RVA2QE2A646YGMGIXJLUEQ","short_pith_number":"pith:3ZO2RVA2","schema_version":"1.0","canonical_sha256":"de5da8d41a81340f73d8330c8ba57424100f7f88187b107c45d06dafb7a42d43","source":{"kind":"arxiv","id":"2307.10854","version":1},"attestation_state":"computed","paper":{"title":"BlendFace: Re-designing Identity Encoders for Face-Swapping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaede Shiohara, Takafumi Taketomi, Xingchao Yang","submitted_at":"2023-07-20T13:17:30Z","abstract_excerpt":"The great advancements of generative adversarial networks and face recognition models in computer vision have made it possible to swap identities on images from single sources. Although a lot of studies seems to have proposed almost satisfactory solutions, we notice previous methods still suffer from an identity-attribute entanglement that causes undesired attributes swapping because widely used identity encoders, eg, ArcFace, have some crucial attribute biases owing to their pretraining on face recognition tasks. To address this issue, we design BlendFace, a novel identity encoder for face-sw"},"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":"2307.10854","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-20T13:17:30Z","cross_cats_sorted":[],"title_canon_sha256":"3c608457578ed2bc72abe7162d3ff604a02810c37b490678a026df07131f5158","abstract_canon_sha256":"b059069c2940fdb4d7a220c71e4b3de99978fc291f76771a469d9d0c44527f7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:12.490710Z","signature_b64":"htLjGJAuTlPTK7oNYsqsq8UF0TXtYrRmFy5gD8AEzRp1njFEJWHNPVvjsM3s1oONyvGBcc3DlJEvFCV6lD39BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de5da8d41a81340f73d8330c8ba57424100f7f88187b107c45d06dafb7a42d43","last_reissued_at":"2026-07-05T06:33:12.490299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:12.490299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BlendFace: Re-designing Identity Encoders for Face-Swapping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaede Shiohara, Takafumi Taketomi, Xingchao Yang","submitted_at":"2023-07-20T13:17:30Z","abstract_excerpt":"The great advancements of generative adversarial networks and face recognition models in computer vision have made it possible to swap identities on images from single sources. Although a lot of studies seems to have proposed almost satisfactory solutions, we notice previous methods still suffer from an identity-attribute entanglement that causes undesired attributes swapping because widely used identity encoders, eg, ArcFace, have some crucial attribute biases owing to their pretraining on face recognition tasks. To address this issue, we design BlendFace, a novel identity encoder for face-sw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.10854","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/2307.10854/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":"2307.10854","created_at":"2026-07-05T06:33:12.490368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.10854v1","created_at":"2026-07-05T06:33:12.490368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.10854","created_at":"2026-07-05T06:33:12.490368+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZO2RVA2QE2A","created_at":"2026-07-05T06:33:12.490368+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZO2RVA2QE2A646Y","created_at":"2026-07-05T06:33:12.490368+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZO2RVA2","created_at":"2026-07-05T06:33:12.490368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.16704","citing_title":"DFCon: Attention-Driven Supervised Contrastive Learning for Robust Deepfake Detection","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ZO2RVA2QE2A646YGMGIXJLUEQ","json":"https://pith.science/pith/3ZO2RVA2QE2A646YGMGIXJLUEQ.json","graph_json":"https://pith.science/api/pith-number/3ZO2RVA2QE2A646YGMGIXJLUEQ/graph.json","events_json":"https://pith.science/api/pith-number/3ZO2RVA2QE2A646YGMGIXJLUEQ/events.json","paper":"https://pith.science/paper/3ZO2RVA2"},"agent_actions":{"view_html":"https://pith.science/pith/3ZO2RVA2QE2A646YGMGIXJLUEQ","download_json":"https://pith.science/pith/3ZO2RVA2QE2A646YGMGIXJLUEQ.json","view_paper":"https://pith.science/paper/3ZO2RVA2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.10854&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZO2RVA2QE2A646YGMGIXJLUEQ/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZO2RVA2QE2A646YGMGIXJLUEQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZO2RVA2QE2A646YGMGIXJLUEQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZO2RVA2QE2A646YGMGIXJLUEQ/action/storage_attestation","attest_author":"https://pith.science/pith/3ZO2RVA2QE2A646YGMGIXJLUEQ/action/author_attestation","sign_citation":"https://pith.science/pith/3ZO2RVA2QE2A646YGMGIXJLUEQ/action/citation_signature","submit_replication":"https://pith.science/pith/3ZO2RVA2QE2A646YGMGIXJLUEQ/action/replication_record"}},"created_at":"2026-07-05T06:33:12.490368+00:00","updated_at":"2026-07-05T06:33:12.490368+00:00"}