{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RMIO2TUCG6XA2FKUV4Q2MQ3V3E","short_pith_number":"pith:RMIO2TUC","schema_version":"1.0","canonical_sha256":"8b10ed4e8237ae0d1554af21a64375d935ff8626916394959fd356386a06fbd7","source":{"kind":"arxiv","id":"2203.01318","version":3},"attestation_state":"computed","paper":{"title":"Protecting Celebrities from DeepFake with Identity Consistency Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Dong Chen, Dongdong Chen, Fang Wen, Jianmin Bao, Nenghai Yu, Ting Zhang, Weiming Zhang, Xiaoyi Dong","submitted_at":"2022-03-02T18:59:58Z","abstract_excerpt":"In this work we propose Identity Consistency Transformer, a novel face forgery detection method that focuses on high-level semantics, specifically identity information, and detecting a suspect face by finding identity inconsistency in inner and outer face regions. The Identity Consistency Transformer incorporates a consistency loss for identity consistency determination. We show that Identity Consistency Transformer exhibits superior generalization ability not only across different datasets but also across various types of image degradation forms found in real-world applications including deep"},"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":"2203.01318","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-02T18:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"7fb1c63b14de91af9b763a8c2d37ae5781cdb864ad96bcb11b9f01e6f916584b","abstract_canon_sha256":"0d3af1eeeab431394c511204cd4f6c187c96a0ef3d3d4d069023d9c1fb9a4647"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:30.728957Z","signature_b64":"w+Z9FNFp513fghIYiFh63YDfW8MZBhWGUN2guN6cutYmvl904RDavuoz5jkFCaWnPsr1iCMBMhEKS8WK6zRpDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b10ed4e8237ae0d1554af21a64375d935ff8626916394959fd356386a06fbd7","last_reissued_at":"2026-07-05T04:11:30.728561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:30.728561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Protecting Celebrities from DeepFake with Identity Consistency Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Dong Chen, Dongdong Chen, Fang Wen, Jianmin Bao, Nenghai Yu, Ting Zhang, Weiming Zhang, Xiaoyi Dong","submitted_at":"2022-03-02T18:59:58Z","abstract_excerpt":"In this work we propose Identity Consistency Transformer, a novel face forgery detection method that focuses on high-level semantics, specifically identity information, and detecting a suspect face by finding identity inconsistency in inner and outer face regions. The Identity Consistency Transformer incorporates a consistency loss for identity consistency determination. We show that Identity Consistency Transformer exhibits superior generalization ability not only across different datasets but also across various types of image degradation forms found in real-world applications including deep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.01318","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/2203.01318/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":"2203.01318","created_at":"2026-07-05T04:11:30.728616+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.01318v3","created_at":"2026-07-05T04:11:30.728616+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.01318","created_at":"2026-07-05T04:11:30.728616+00:00"},{"alias_kind":"pith_short_12","alias_value":"RMIO2TUCG6XA","created_at":"2026-07-05T04:11:30.728616+00:00"},{"alias_kind":"pith_short_16","alias_value":"RMIO2TUCG6XA2FKU","created_at":"2026-07-05T04:11:30.728616+00:00"},{"alias_kind":"pith_short_8","alias_value":"RMIO2TUC","created_at":"2026-07-05T04:11:30.728616+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23189","citing_title":"Trident: Detecting Face Forgeries with Adversarial Triplet Learning","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RMIO2TUCG6XA2FKUV4Q2MQ3V3E","json":"https://pith.science/pith/RMIO2TUCG6XA2FKUV4Q2MQ3V3E.json","graph_json":"https://pith.science/api/pith-number/RMIO2TUCG6XA2FKUV4Q2MQ3V3E/graph.json","events_json":"https://pith.science/api/pith-number/RMIO2TUCG6XA2FKUV4Q2MQ3V3E/events.json","paper":"https://pith.science/paper/RMIO2TUC"},"agent_actions":{"view_html":"https://pith.science/pith/RMIO2TUCG6XA2FKUV4Q2MQ3V3E","download_json":"https://pith.science/pith/RMIO2TUCG6XA2FKUV4Q2MQ3V3E.json","view_paper":"https://pith.science/paper/RMIO2TUC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.01318&json=true","fetch_graph":"https://pith.science/api/pith-number/RMIO2TUCG6XA2FKUV4Q2MQ3V3E/graph.json","fetch_events":"https://pith.science/api/pith-number/RMIO2TUCG6XA2FKUV4Q2MQ3V3E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RMIO2TUCG6XA2FKUV4Q2MQ3V3E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RMIO2TUCG6XA2FKUV4Q2MQ3V3E/action/storage_attestation","attest_author":"https://pith.science/pith/RMIO2TUCG6XA2FKUV4Q2MQ3V3E/action/author_attestation","sign_citation":"https://pith.science/pith/RMIO2TUCG6XA2FKUV4Q2MQ3V3E/action/citation_signature","submit_replication":"https://pith.science/pith/RMIO2TUCG6XA2FKUV4Q2MQ3V3E/action/replication_record"}},"created_at":"2026-07-05T04:11:30.728616+00:00","updated_at":"2026-07-05T04:11:30.728616+00:00"}