{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VYT255VHMQBLFI4FAMBTI3Z2HY","short_pith_number":"pith:VYT255VH","schema_version":"1.0","canonical_sha256":"ae27aef6a76402b2a3850303346f3a3e07659d45b32a6566158b4385f1a8d167","source":{"kind":"arxiv","id":"2204.03083","version":3},"attestation_state":"computed","paper":{"title":"Audio-Visual Person-of-Interest DeepFake Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Alessandro Pianese, Davide Cozzolino, Luisa Verdoliva, Matthias Nie{\\ss}ner","submitted_at":"2022-04-06T20:51:40Z","abstract_excerpt":"Face manipulation technology is advancing very rapidly, and new methods are being proposed day by day. The aim of this work is to propose a deepfake detector that can cope with the wide variety of manipulation methods and scenarios encountered in the real world. Our key insight is that each person has specific characteristics that a synthetic generator likely cannot reproduce. Accordingly, we extract audio-visual features which characterize the identity of a person, and use them to create a person-of-interest (POI) deepfake detector. We leverage a contrastive learning paradigm to learn the mov"},"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":"2204.03083","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-06T20:51:40Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"5eabd5c7f2c70a56f12432758656924ac416fb4956d42359f16b832029546070","abstract_canon_sha256":"2645bbc6edf08a6a873830c47e5781369cdb8ca7f32159469ad629b79b0ce768"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:15.536785Z","signature_b64":"eZIohBAoSp1xPPkpPseJJDTL0I7vihWjK9UP0QD2c+pTYHXSv5WHu2AHsLKeJvrLl3SaS8m8wfwtZ3WDvDK5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae27aef6a76402b2a3850303346f3a3e07659d45b32a6566158b4385f1a8d167","last_reissued_at":"2026-07-05T06:11:15.536394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:15.536394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-Visual Person-of-Interest DeepFake Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Alessandro Pianese, Davide Cozzolino, Luisa Verdoliva, Matthias Nie{\\ss}ner","submitted_at":"2022-04-06T20:51:40Z","abstract_excerpt":"Face manipulation technology is advancing very rapidly, and new methods are being proposed day by day. The aim of this work is to propose a deepfake detector that can cope with the wide variety of manipulation methods and scenarios encountered in the real world. Our key insight is that each person has specific characteristics that a synthetic generator likely cannot reproduce. Accordingly, we extract audio-visual features which characterize the identity of a person, and use them to create a person-of-interest (POI) deepfake detector. We leverage a contrastive learning paradigm to learn the mov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03083","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/2204.03083/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":"2204.03083","created_at":"2026-07-05T06:11:15.536454+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.03083v3","created_at":"2026-07-05T06:11:15.536454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03083","created_at":"2026-07-05T06:11:15.536454+00:00"},{"alias_kind":"pith_short_12","alias_value":"VYT255VHMQBL","created_at":"2026-07-05T06:11:15.536454+00:00"},{"alias_kind":"pith_short_16","alias_value":"VYT255VHMQBLFI4F","created_at":"2026-07-05T06:11:15.536454+00:00"},{"alias_kind":"pith_short_8","alias_value":"VYT255VH","created_at":"2026-07-05T06:11:15.536454+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.21489","citing_title":"TRIED: Truly Innovative and Effective AI Detection Benchmark, developed by WITNESS","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VYT255VHMQBLFI4FAMBTI3Z2HY","json":"https://pith.science/pith/VYT255VHMQBLFI4FAMBTI3Z2HY.json","graph_json":"https://pith.science/api/pith-number/VYT255VHMQBLFI4FAMBTI3Z2HY/graph.json","events_json":"https://pith.science/api/pith-number/VYT255VHMQBLFI4FAMBTI3Z2HY/events.json","paper":"https://pith.science/paper/VYT255VH"},"agent_actions":{"view_html":"https://pith.science/pith/VYT255VHMQBLFI4FAMBTI3Z2HY","download_json":"https://pith.science/pith/VYT255VHMQBLFI4FAMBTI3Z2HY.json","view_paper":"https://pith.science/paper/VYT255VH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.03083&json=true","fetch_graph":"https://pith.science/api/pith-number/VYT255VHMQBLFI4FAMBTI3Z2HY/graph.json","fetch_events":"https://pith.science/api/pith-number/VYT255VHMQBLFI4FAMBTI3Z2HY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VYT255VHMQBLFI4FAMBTI3Z2HY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VYT255VHMQBLFI4FAMBTI3Z2HY/action/storage_attestation","attest_author":"https://pith.science/pith/VYT255VHMQBLFI4FAMBTI3Z2HY/action/author_attestation","sign_citation":"https://pith.science/pith/VYT255VHMQBLFI4FAMBTI3Z2HY/action/citation_signature","submit_replication":"https://pith.science/pith/VYT255VHMQBLFI4FAMBTI3Z2HY/action/replication_record"}},"created_at":"2026-07-05T06:11:15.536454+00:00","updated_at":"2026-07-05T06:11:15.536454+00:00"}