{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3YKSPEVYZ7THNYGFC6LLTTBT7U","short_pith_number":"pith:3YKSPEVY","schema_version":"1.0","canonical_sha256":"de152792b8cfe676e0c51796b9cc33fd0edd60439ef38c51aa1af7fa9711a42a","source":{"kind":"arxiv","id":"2501.08137","version":4},"attestation_state":"computed","paper":{"title":"Audio-Visual Deepfake Detection With Local Temporal Inconsistencies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Djamila Aouada, Enjie Ghorbel, Marcella Astrid","submitted_at":"2025-01-14T14:15:10Z","abstract_excerpt":"This paper proposes an audio-visual deepfake detection approach that aims to capture fine-grained temporal inconsistencies between audio and visual modalities. To achieve this, both architectural and data synthesis strategies are introduced. From an architectural perspective, a temporal distance map, coupled with an attention mechanism, is designed to capture these inconsistencies while minimizing the impact of irrelevant temporal subsequences. Moreover, we explore novel pseudo-fake generation techniques to synthesize local inconsistencies. Our approach is evaluated against state-of-the-art me"},"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":"2501.08137","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T14:15:10Z","cross_cats_sorted":["cs.CR","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"36d6b32cd52e4cc02181af937360c642ecf9d35789c77e141d960ba9702b0305","abstract_canon_sha256":"466505783f241f5a89fb45d3522592f202dda32a765207499bf286fc36387822"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:30.140186Z","signature_b64":"GtG05niut5NTfoSMkHu/E2jSTUEFxgzUtajHKjZrKLpmNw2XuEFCNIV+55KtolFi6Zal1+/YLrz5XIWplXQcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de152792b8cfe676e0c51796b9cc33fd0edd60439ef38c51aa1af7fa9711a42a","last_reissued_at":"2026-07-05T10:30:30.139568Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:30.139568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-Visual Deepfake Detection With Local Temporal Inconsistencies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Djamila Aouada, Enjie Ghorbel, Marcella Astrid","submitted_at":"2025-01-14T14:15:10Z","abstract_excerpt":"This paper proposes an audio-visual deepfake detection approach that aims to capture fine-grained temporal inconsistencies between audio and visual modalities. To achieve this, both architectural and data synthesis strategies are introduced. From an architectural perspective, a temporal distance map, coupled with an attention mechanism, is designed to capture these inconsistencies while minimizing the impact of irrelevant temporal subsequences. Moreover, we explore novel pseudo-fake generation techniques to synthesize local inconsistencies. Our approach is evaluated against state-of-the-art me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08137","kind":"arxiv","version":4},"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/2501.08137/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":"2501.08137","created_at":"2026-07-05T10:30:30.139650+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.08137v4","created_at":"2026-07-05T10:30:30.139650+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08137","created_at":"2026-07-05T10:30:30.139650+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YKSPEVYZ7TH","created_at":"2026-07-05T10:30:30.139650+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YKSPEVYZ7THNYGF","created_at":"2026-07-05T10:30:30.139650+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YKSPEVY","created_at":"2026-07-05T10:30:30.139650+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.08137","citing_title":"Audio-Visual Deepfake Detection With Local Temporal Inconsistencies","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3YKSPEVYZ7THNYGFC6LLTTBT7U","json":"https://pith.science/pith/3YKSPEVYZ7THNYGFC6LLTTBT7U.json","graph_json":"https://pith.science/api/pith-number/3YKSPEVYZ7THNYGFC6LLTTBT7U/graph.json","events_json":"https://pith.science/api/pith-number/3YKSPEVYZ7THNYGFC6LLTTBT7U/events.json","paper":"https://pith.science/paper/3YKSPEVY"},"agent_actions":{"view_html":"https://pith.science/pith/3YKSPEVYZ7THNYGFC6LLTTBT7U","download_json":"https://pith.science/pith/3YKSPEVYZ7THNYGFC6LLTTBT7U.json","view_paper":"https://pith.science/paper/3YKSPEVY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.08137&json=true","fetch_graph":"https://pith.science/api/pith-number/3YKSPEVYZ7THNYGFC6LLTTBT7U/graph.json","fetch_events":"https://pith.science/api/pith-number/3YKSPEVYZ7THNYGFC6LLTTBT7U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YKSPEVYZ7THNYGFC6LLTTBT7U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YKSPEVYZ7THNYGFC6LLTTBT7U/action/storage_attestation","attest_author":"https://pith.science/pith/3YKSPEVYZ7THNYGFC6LLTTBT7U/action/author_attestation","sign_citation":"https://pith.science/pith/3YKSPEVYZ7THNYGFC6LLTTBT7U/action/citation_signature","submit_replication":"https://pith.science/pith/3YKSPEVYZ7THNYGFC6LLTTBT7U/action/replication_record"}},"created_at":"2026-07-05T10:30:30.139650+00:00","updated_at":"2026-07-05T10:30:30.139650+00:00"}