{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JWNEWAZJUGPPAPJKCOQZJRMCSA","short_pith_number":"pith:JWNEWAZJ","schema_version":"1.0","canonical_sha256":"4d9a4b0329a19ef03d2a13a194c5829037611784e38a9627c57b8bd1119d17ce","source":{"kind":"arxiv","id":"2505.15233","version":1},"attestation_state":"computed","paper":{"title":"CAD: A General Multimodal Framework for Video Deepfake Detection via Cross-Modal Alignment and Distillation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Caiyong Piao, Hao Li, Li Yuan, Yuhao Luo, Yuxuan Du, Zhendong Wang, Zhiyuan Yan","submitted_at":"2025-05-21T08:11:07Z","abstract_excerpt":"The rapid emergence of multimodal deepfakes (visual and auditory content are manipulated in concert) undermines the reliability of existing detectors that rely solely on modality-specific artifacts or cross-modal inconsistencies. In this work, we first demonstrate that modality-specific forensic traces (e.g., face-swap artifacts or spectral distortions) and modality-shared semantic misalignments (e.g., lip-speech asynchrony) offer complementary evidence, and that neglecting either aspect limits detection performance. Existing approaches either naively fuse modality-specific features without re"},"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":"2505.15233","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T08:11:07Z","cross_cats_sorted":[],"title_canon_sha256":"4581c64ba2b05a17aa1873e1dc022646162a9b8a93a4f3dd7012890a7cb6ff91","abstract_canon_sha256":"c171d8bf572ac7805b4407dec6da77ed9e698bf93d2ad22c72c76e3f1af45d7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:42.409692Z","signature_b64":"cKn4cOBy7CTY4ASlhk8kcljWvBGv1AlHijDb0ReH9b7QExrYe4Azbq4nb2QT7iZTEKCF7puNjt8eg5LFQ8oACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d9a4b0329a19ef03d2a13a194c5829037611784e38a9627c57b8bd1119d17ce","last_reissued_at":"2026-07-05T11:06:42.409196Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:42.409196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAD: A General Multimodal Framework for Video Deepfake Detection via Cross-Modal Alignment and Distillation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Caiyong Piao, Hao Li, Li Yuan, Yuhao Luo, Yuxuan Du, Zhendong Wang, Zhiyuan Yan","submitted_at":"2025-05-21T08:11:07Z","abstract_excerpt":"The rapid emergence of multimodal deepfakes (visual and auditory content are manipulated in concert) undermines the reliability of existing detectors that rely solely on modality-specific artifacts or cross-modal inconsistencies. In this work, we first demonstrate that modality-specific forensic traces (e.g., face-swap artifacts or spectral distortions) and modality-shared semantic misalignments (e.g., lip-speech asynchrony) offer complementary evidence, and that neglecting either aspect limits detection performance. Existing approaches either naively fuse modality-specific features without re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15233","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/2505.15233/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":"2505.15233","created_at":"2026-07-05T11:06:42.409253+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15233v1","created_at":"2026-07-05T11:06:42.409253+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15233","created_at":"2026-07-05T11:06:42.409253+00:00"},{"alias_kind":"pith_short_12","alias_value":"JWNEWAZJUGPP","created_at":"2026-07-05T11:06:42.409253+00:00"},{"alias_kind":"pith_short_16","alias_value":"JWNEWAZJUGPPAPJK","created_at":"2026-07-05T11:06:42.409253+00:00"},{"alias_kind":"pith_short_8","alias_value":"JWNEWAZJ","created_at":"2026-07-05T11:06:42.409253+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17133","citing_title":"CAM-VFD: Cross-Attention Multimodal Video Forgery Detection","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JWNEWAZJUGPPAPJKCOQZJRMCSA","json":"https://pith.science/pith/JWNEWAZJUGPPAPJKCOQZJRMCSA.json","graph_json":"https://pith.science/api/pith-number/JWNEWAZJUGPPAPJKCOQZJRMCSA/graph.json","events_json":"https://pith.science/api/pith-number/JWNEWAZJUGPPAPJKCOQZJRMCSA/events.json","paper":"https://pith.science/paper/JWNEWAZJ"},"agent_actions":{"view_html":"https://pith.science/pith/JWNEWAZJUGPPAPJKCOQZJRMCSA","download_json":"https://pith.science/pith/JWNEWAZJUGPPAPJKCOQZJRMCSA.json","view_paper":"https://pith.science/paper/JWNEWAZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15233&json=true","fetch_graph":"https://pith.science/api/pith-number/JWNEWAZJUGPPAPJKCOQZJRMCSA/graph.json","fetch_events":"https://pith.science/api/pith-number/JWNEWAZJUGPPAPJKCOQZJRMCSA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JWNEWAZJUGPPAPJKCOQZJRMCSA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JWNEWAZJUGPPAPJKCOQZJRMCSA/action/storage_attestation","attest_author":"https://pith.science/pith/JWNEWAZJUGPPAPJKCOQZJRMCSA/action/author_attestation","sign_citation":"https://pith.science/pith/JWNEWAZJUGPPAPJKCOQZJRMCSA/action/citation_signature","submit_replication":"https://pith.science/pith/JWNEWAZJUGPPAPJKCOQZJRMCSA/action/replication_record"}},"created_at":"2026-07-05T11:06:42.409253+00:00","updated_at":"2026-07-05T11:06:42.409253+00:00"}