{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:X5GKEMXAV4ITZOSQV7U7B6KXBM","short_pith_number":"pith:X5GKEMXA","schema_version":"1.0","canonical_sha256":"bf4ca232e0af113cba50afe9f0f9570b0ed433f1734f851435eff40abb7295a9","source":{"kind":"arxiv","id":"2310.02234","version":2},"attestation_state":"computed","paper":{"title":"MIS-AVoiDD: Modality Invariant and Specific Representation for Audio-Visual Deepfake Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ajita Rattani, Vinaya Sree Katamneni","submitted_at":"2023-10-03T17:43:24Z","abstract_excerpt":"Deepfakes are synthetic media generated using deep generative algorithms and have posed a severe societal and political threat. Apart from facial manipulation and synthetic voice, recently, a novel kind of deepfakes has emerged with either audio or visual modalities manipulated. In this regard, a new generation of multimodal audio-visual deepfake detectors is being investigated to collectively focus on audio and visual data for multimodal manipulation detection. Existing multimodal (audio-visual) deepfake detectors are often based on the fusion of the audio and visual streams from the video. E"},"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":"2310.02234","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-03T17:43:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1662fabbe62b82742e65a3bbd1d259f9a2113cdb9dcb420551626ec6884d4e1f","abstract_canon_sha256":"db601ac1143e40e634d48bd4d99404273c9f9edf72820e1efcaa15868340d62f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:45.695011Z","signature_b64":"+sn3pl9OImL8WGKcXuflE929TyazRfILl9cKr+2Qx26Vm+wwR+QX54zJnLrgb0Y/AlANY1VeJwHCzpcEKzYqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf4ca232e0af113cba50afe9f0f9570b0ed433f1734f851435eff40abb7295a9","last_reissued_at":"2026-07-05T07:00:45.694518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:45.694518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIS-AVoiDD: Modality Invariant and Specific Representation for Audio-Visual Deepfake Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ajita Rattani, Vinaya Sree Katamneni","submitted_at":"2023-10-03T17:43:24Z","abstract_excerpt":"Deepfakes are synthetic media generated using deep generative algorithms and have posed a severe societal and political threat. Apart from facial manipulation and synthetic voice, recently, a novel kind of deepfakes has emerged with either audio or visual modalities manipulated. In this regard, a new generation of multimodal audio-visual deepfake detectors is being investigated to collectively focus on audio and visual data for multimodal manipulation detection. Existing multimodal (audio-visual) deepfake detectors are often based on the fusion of the audio and visual streams from the video. E"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02234","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/2310.02234/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":"2310.02234","created_at":"2026-07-05T07:00:45.694575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.02234v2","created_at":"2026-07-05T07:00:45.694575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02234","created_at":"2026-07-05T07:00:45.694575+00:00"},{"alias_kind":"pith_short_12","alias_value":"X5GKEMXAV4IT","created_at":"2026-07-05T07:00:45.694575+00:00"},{"alias_kind":"pith_short_16","alias_value":"X5GKEMXAV4ITZOSQ","created_at":"2026-07-05T07:00:45.694575+00:00"},{"alias_kind":"pith_short_8","alias_value":"X5GKEMXA","created_at":"2026-07-05T07:00:45.694575+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.13205","citing_title":"Poison Once, Control Anywhere: Clean-Text Visual Backdoors in VLM-based Mobile Agents","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X5GKEMXAV4ITZOSQV7U7B6KXBM","json":"https://pith.science/pith/X5GKEMXAV4ITZOSQV7U7B6KXBM.json","graph_json":"https://pith.science/api/pith-number/X5GKEMXAV4ITZOSQV7U7B6KXBM/graph.json","events_json":"https://pith.science/api/pith-number/X5GKEMXAV4ITZOSQV7U7B6KXBM/events.json","paper":"https://pith.science/paper/X5GKEMXA"},"agent_actions":{"view_html":"https://pith.science/pith/X5GKEMXAV4ITZOSQV7U7B6KXBM","download_json":"https://pith.science/pith/X5GKEMXAV4ITZOSQV7U7B6KXBM.json","view_paper":"https://pith.science/paper/X5GKEMXA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.02234&json=true","fetch_graph":"https://pith.science/api/pith-number/X5GKEMXAV4ITZOSQV7U7B6KXBM/graph.json","fetch_events":"https://pith.science/api/pith-number/X5GKEMXAV4ITZOSQV7U7B6KXBM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X5GKEMXAV4ITZOSQV7U7B6KXBM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X5GKEMXAV4ITZOSQV7U7B6KXBM/action/storage_attestation","attest_author":"https://pith.science/pith/X5GKEMXAV4ITZOSQV7U7B6KXBM/action/author_attestation","sign_citation":"https://pith.science/pith/X5GKEMXAV4ITZOSQV7U7B6KXBM/action/citation_signature","submit_replication":"https://pith.science/pith/X5GKEMXAV4ITZOSQV7U7B6KXBM/action/replication_record"}},"created_at":"2026-07-05T07:00:45.694575+00:00","updated_at":"2026-07-05T07:00:45.694575+00:00"}