{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DJGYFBNF7HXVQN4SZLPEWJFZ3P","short_pith_number":"pith:DJGYFBNF","schema_version":"1.0","canonical_sha256":"1a4d8285a5f9ef583792cade4b24b9dbff7752d39a15bce80edeb5eacacff988","source":{"kind":"arxiv","id":"2408.01532","version":2},"attestation_state":"computed","paper":{"title":"Contextual Cross-Modal Attention for Audio-Visual Deepfake Detection and Localization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ajita Rattani, Vinaya Sree Katamneni","submitted_at":"2024-08-02T18:45:01Z","abstract_excerpt":"In the digital age, the emergence of deepfakes and synthetic media presents a significant threat to societal and political integrity. Deepfakes based on multi-modal manipulation, such as audio-visual, are more realistic and pose a greater threat. Current multi-modal deepfake detectors are often based on the attention-based fusion of heterogeneous data streams from multiple modalities. However, the heterogeneous nature of the data (such as audio and visual signals) creates a distributional modality gap and poses a significant challenge in effective fusion and hence multi-modal deepfake detectio"},"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":"2408.01532","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-02T18:45:01Z","cross_cats_sorted":["cs.AI","cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"b9e877a4db8f4c07df49ef4958133e2f4127141d20d03fea9bc8b535ce092ef5","abstract_canon_sha256":"c69d148337d958b74946e1a32bd40a45f10ffe449f2863559f221e37a50e3f39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:56.193107Z","signature_b64":"nqvi2wJR2bXV+fFeW3He2cYQ/MOenncNylp4FN8cVdnvPGVYzWnET2kZjHB6yZPMh7ZMjlX/Be9E2Eblvtv0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a4d8285a5f9ef583792cade4b24b9dbff7752d39a15bce80edeb5eacacff988","last_reissued_at":"2026-07-05T08:52:56.192688Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:56.192688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contextual Cross-Modal Attention for Audio-Visual Deepfake Detection and Localization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ajita Rattani, Vinaya Sree Katamneni","submitted_at":"2024-08-02T18:45:01Z","abstract_excerpt":"In the digital age, the emergence of deepfakes and synthetic media presents a significant threat to societal and political integrity. Deepfakes based on multi-modal manipulation, such as audio-visual, are more realistic and pose a greater threat. Current multi-modal deepfake detectors are often based on the attention-based fusion of heterogeneous data streams from multiple modalities. However, the heterogeneous nature of the data (such as audio and visual signals) creates a distributional modality gap and poses a significant challenge in effective fusion and hence multi-modal deepfake detectio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01532","kind":"arxiv","version":2},"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/2408.01532/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":"2408.01532","created_at":"2026-07-05T08:52:56.192750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.01532v2","created_at":"2026-07-05T08:52:56.192750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01532","created_at":"2026-07-05T08:52:56.192750+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJGYFBNF7HXV","created_at":"2026-07-05T08:52:56.192750+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJGYFBNF7HXVQN4S","created_at":"2026-07-05T08:52:56.192750+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJGYFBNF","created_at":"2026-07-05T08:52:56.192750+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17573","citing_title":"Deepfake Detection in Social Media: A Temporal Artifact Analysis Using 3D Convolutional Neural Networks","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DJGYFBNF7HXVQN4SZLPEWJFZ3P","json":"https://pith.science/pith/DJGYFBNF7HXVQN4SZLPEWJFZ3P.json","graph_json":"https://pith.science/api/pith-number/DJGYFBNF7HXVQN4SZLPEWJFZ3P/graph.json","events_json":"https://pith.science/api/pith-number/DJGYFBNF7HXVQN4SZLPEWJFZ3P/events.json","paper":"https://pith.science/paper/DJGYFBNF"},"agent_actions":{"view_html":"https://pith.science/pith/DJGYFBNF7HXVQN4SZLPEWJFZ3P","download_json":"https://pith.science/pith/DJGYFBNF7HXVQN4SZLPEWJFZ3P.json","view_paper":"https://pith.science/paper/DJGYFBNF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.01532&json=true","fetch_graph":"https://pith.science/api/pith-number/DJGYFBNF7HXVQN4SZLPEWJFZ3P/graph.json","fetch_events":"https://pith.science/api/pith-number/DJGYFBNF7HXVQN4SZLPEWJFZ3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJGYFBNF7HXVQN4SZLPEWJFZ3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJGYFBNF7HXVQN4SZLPEWJFZ3P/action/storage_attestation","attest_author":"https://pith.science/pith/DJGYFBNF7HXVQN4SZLPEWJFZ3P/action/author_attestation","sign_citation":"https://pith.science/pith/DJGYFBNF7HXVQN4SZLPEWJFZ3P/action/citation_signature","submit_replication":"https://pith.science/pith/DJGYFBNF7HXVQN4SZLPEWJFZ3P/action/replication_record"}},"created_at":"2026-07-05T08:52:56.192750+00:00","updated_at":"2026-07-05T08:52:56.192750+00:00"}