{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MSTEOYQO54QMISP5LQHEOI3AC2","short_pith_number":"pith:MSTEOYQO","schema_version":"1.0","canonical_sha256":"64a647620eef20c449fd5c0e472360169f64bdf57cdae6843112e2a75d93d179","source":{"kind":"arxiv","id":"2311.15308","version":2},"attestation_state":"computed","paper":{"title":"AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Dhall, Aman Pankaj Adatia, Kalin Stefanov, Munawar Hayat, Shreya Ghosh, Tom Gedeon, Zhixi Cai","submitted_at":"2023-11-26T14:17:51Z","abstract_excerpt":"The detection and localization of highly realistic deepfake audio-visual content are challenging even for the most advanced state-of-the-art methods. While most of the research efforts in this domain are focused on detecting high-quality deepfake images and videos, only a few works address the problem of the localization of small segments of audio-visual manipulations embedded in real videos. In this research, we emulate the process of such content generation and propose the AV-Deepfake1M dataset. The dataset contains content-driven (i) video manipulations, (ii) audio manipulations, and (iii) "},"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":"2311.15308","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-26T14:17:51Z","cross_cats_sorted":[],"title_canon_sha256":"e2347daea8957cf5e3fb6bcf6e90546ad17b5a99bf806c130f60e99d823facc7","abstract_canon_sha256":"9d4b6b7358023ffa412c7d9cdeebf0c10c1b55d0aa9a2f1e8df954f209dbdb2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:49:26.947762Z","signature_b64":"cdQSOteLji+ymXbqyo6lqs0KNQbFev7uHMu2Hm8rDc56zCYsmL9wNyb4QvWcIS2bhL45arRzYbPv7gQ7P5wJDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64a647620eef20c449fd5c0e472360169f64bdf57cdae6843112e2a75d93d179","last_reissued_at":"2026-07-05T08:49:26.947278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:49:26.947278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Dhall, Aman Pankaj Adatia, Kalin Stefanov, Munawar Hayat, Shreya Ghosh, Tom Gedeon, Zhixi Cai","submitted_at":"2023-11-26T14:17:51Z","abstract_excerpt":"The detection and localization of highly realistic deepfake audio-visual content are challenging even for the most advanced state-of-the-art methods. While most of the research efforts in this domain are focused on detecting high-quality deepfake images and videos, only a few works address the problem of the localization of small segments of audio-visual manipulations embedded in real videos. In this research, we emulate the process of such content generation and propose the AV-Deepfake1M dataset. The dataset contains content-driven (i) video manipulations, (ii) audio manipulations, and (iii) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15308","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/2311.15308/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":"2311.15308","created_at":"2026-07-05T08:49:26.947341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.15308v2","created_at":"2026-07-05T08:49:26.947341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15308","created_at":"2026-07-05T08:49:26.947341+00:00"},{"alias_kind":"pith_short_12","alias_value":"MSTEOYQO54QM","created_at":"2026-07-05T08:49:26.947341+00:00"},{"alias_kind":"pith_short_16","alias_value":"MSTEOYQO54QMISP5","created_at":"2026-07-05T08:49:26.947341+00:00"},{"alias_kind":"pith_short_8","alias_value":"MSTEOYQO","created_at":"2026-07-05T08:49:26.947341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.09512","citing_title":"MLAAD: The Multi-Language Audio Anti-Spoofing Dataset","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27557","citing_title":"A General Model for Deepfake Speech Detection: Diverse Bonafide Resources or Diverse AI-Based Generators","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02223","citing_title":"Toward Fine-Grained Speech Inpainting Forensics:A Dataset, Method, and Metric for Multi-Region Tampering Localization","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MSTEOYQO54QMISP5LQHEOI3AC2","json":"https://pith.science/pith/MSTEOYQO54QMISP5LQHEOI3AC2.json","graph_json":"https://pith.science/api/pith-number/MSTEOYQO54QMISP5LQHEOI3AC2/graph.json","events_json":"https://pith.science/api/pith-number/MSTEOYQO54QMISP5LQHEOI3AC2/events.json","paper":"https://pith.science/paper/MSTEOYQO"},"agent_actions":{"view_html":"https://pith.science/pith/MSTEOYQO54QMISP5LQHEOI3AC2","download_json":"https://pith.science/pith/MSTEOYQO54QMISP5LQHEOI3AC2.json","view_paper":"https://pith.science/paper/MSTEOYQO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.15308&json=true","fetch_graph":"https://pith.science/api/pith-number/MSTEOYQO54QMISP5LQHEOI3AC2/graph.json","fetch_events":"https://pith.science/api/pith-number/MSTEOYQO54QMISP5LQHEOI3AC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MSTEOYQO54QMISP5LQHEOI3AC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MSTEOYQO54QMISP5LQHEOI3AC2/action/storage_attestation","attest_author":"https://pith.science/pith/MSTEOYQO54QMISP5LQHEOI3AC2/action/author_attestation","sign_citation":"https://pith.science/pith/MSTEOYQO54QMISP5LQHEOI3AC2/action/citation_signature","submit_replication":"https://pith.science/pith/MSTEOYQO54QMISP5LQHEOI3AC2/action/replication_record"}},"created_at":"2026-07-05T08:49:26.947341+00:00","updated_at":"2026-07-05T08:49:26.947341+00:00"}