{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OGJMVTWR4O6RV2JJRDCJ6KONNT","short_pith_number":"pith:OGJMVTWR","schema_version":"1.0","canonical_sha256":"7192caced1e3bd1ae92988c49f29cd6ccae5278fc5b663919b430b4dc9dec914","source":{"kind":"arxiv","id":"2505.11109","version":1},"attestation_state":"computed","paper":{"title":"MAVOS-DD: Multilingual Audio-Video Open-Set Deepfake Detection Benchmark","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Florinel-Alin Croitoru, Marius Popescu, Mubarak Shah, Radu Tudor Ionescu, Vlad Hondru","submitted_at":"2025-05-16T10:42:30Z","abstract_excerpt":"We present the first large-scale open-set benchmark for multilingual audio-video deepfake detection. Our dataset comprises over 250 hours of real and fake videos across eight languages, with 60% of data being generated. For each language, the fake videos are generated with seven distinct deepfake generation models, selected based on the quality of the generated content. We organize the training, validation and test splits such that only a subset of the chosen generative models and languages are available during training, thus creating several challenging open-set evaluation setups. We perform "},"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":"2505.11109","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-16T10:42:30Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"a8da647896d628f81737adc9ecc55bb2bb7fd5913a5f206ecdbe8225f470151d","abstract_canon_sha256":"cec6524835d8719644c95fabf370e84d9a0a22fb552cfbf4a8446cc0ff41f980"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:10.996535Z","signature_b64":"3kT4erj1yLcHgrytw+FuQ3HkDKD9WKSUiZfgeFohJBOYCfWS6CtongNTVikbj+CXKmMR8C7ey8k1IFQOFGqrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7192caced1e3bd1ae92988c49f29cd6ccae5278fc5b663919b430b4dc9dec914","last_reissued_at":"2026-07-05T11:04:10.996021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:10.996021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAVOS-DD: Multilingual Audio-Video Open-Set Deepfake Detection Benchmark","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Florinel-Alin Croitoru, Marius Popescu, Mubarak Shah, Radu Tudor Ionescu, Vlad Hondru","submitted_at":"2025-05-16T10:42:30Z","abstract_excerpt":"We present the first large-scale open-set benchmark for multilingual audio-video deepfake detection. Our dataset comprises over 250 hours of real and fake videos across eight languages, with 60% of data being generated. For each language, the fake videos are generated with seven distinct deepfake generation models, selected based on the quality of the generated content. We organize the training, validation and test splits such that only a subset of the chosen generative models and languages are available during training, thus creating several challenging open-set evaluation setups. We perform "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11109","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/2505.11109/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":"2505.11109","created_at":"2026-07-05T11:04:10.996085+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11109v1","created_at":"2026-07-05T11:04:10.996085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11109","created_at":"2026-07-05T11:04:10.996085+00:00"},{"alias_kind":"pith_short_12","alias_value":"OGJMVTWR4O6R","created_at":"2026-07-05T11:04:10.996085+00:00"},{"alias_kind":"pith_short_16","alias_value":"OGJMVTWR4O6RV2JJ","created_at":"2026-07-05T11:04:10.996085+00:00"},{"alias_kind":"pith_short_8","alias_value":"OGJMVTWR","created_at":"2026-07-05T11:04:10.996085+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01638","citing_title":"Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06912","citing_title":"Advancing Reliable Synthetic Video Detection: Insights from the SAFE Challenge","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OGJMVTWR4O6RV2JJRDCJ6KONNT","json":"https://pith.science/pith/OGJMVTWR4O6RV2JJRDCJ6KONNT.json","graph_json":"https://pith.science/api/pith-number/OGJMVTWR4O6RV2JJRDCJ6KONNT/graph.json","events_json":"https://pith.science/api/pith-number/OGJMVTWR4O6RV2JJRDCJ6KONNT/events.json","paper":"https://pith.science/paper/OGJMVTWR"},"agent_actions":{"view_html":"https://pith.science/pith/OGJMVTWR4O6RV2JJRDCJ6KONNT","download_json":"https://pith.science/pith/OGJMVTWR4O6RV2JJRDCJ6KONNT.json","view_paper":"https://pith.science/paper/OGJMVTWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11109&json=true","fetch_graph":"https://pith.science/api/pith-number/OGJMVTWR4O6RV2JJRDCJ6KONNT/graph.json","fetch_events":"https://pith.science/api/pith-number/OGJMVTWR4O6RV2JJRDCJ6KONNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OGJMVTWR4O6RV2JJRDCJ6KONNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OGJMVTWR4O6RV2JJRDCJ6KONNT/action/storage_attestation","attest_author":"https://pith.science/pith/OGJMVTWR4O6RV2JJRDCJ6KONNT/action/author_attestation","sign_citation":"https://pith.science/pith/OGJMVTWR4O6RV2JJRDCJ6KONNT/action/citation_signature","submit_replication":"https://pith.science/pith/OGJMVTWR4O6RV2JJRDCJ6KONNT/action/replication_record"}},"created_at":"2026-07-05T11:04:10.996085+00:00","updated_at":"2026-07-05T11:04:10.996085+00:00"}