{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HYDZ4M2NZC52G4HJ76G2W2J7QD","short_pith_number":"pith:HYDZ4M2N","schema_version":"1.0","canonical_sha256":"3e079e334dc8bba370e9ff8dab693f80e54f1b10614539c9f78f7735093e5d80","source":{"kind":"arxiv","id":"2507.20579","version":1},"attestation_state":"computed","paper":{"title":"AV-Deepfake1M++: A Large-Scale Audio-Visual Deepfake Benchmark with Real-World Perturbations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Dhall, Akanksha Chuchra, Kartik Kuckreja, Muhammad Haris Khan, Shreya Ghosh, Tom Gedeon, Usman Tariq, Zhixi Cai","submitted_at":"2025-07-28T07:27:42Z","abstract_excerpt":"The rapid surge of text-to-speech and face-voice reenactment models makes video fabrication easier and highly realistic. To encounter this problem, we require datasets that rich in type of generation methods and perturbation strategy which is usually common for online videos. To this end, we propose AV-Deepfake1M++, an extension of the AV-Deepfake1M having 2 million video clips with diversified manipulation strategy and audio-visual perturbation. This paper includes the description of data generation strategies along with benchmarking of AV-Deepfake1M++ using state-of-the-art methods. We belie"},"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":"2507.20579","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-28T07:27:42Z","cross_cats_sorted":[],"title_canon_sha256":"f2ced3f19bd18580df8d53dc319947e1ef6112c9f728143ffdc5dde906b888c4","abstract_canon_sha256":"9f7a1febf3bc1a95c8d44cc374b3785c029f6401f1f3e6c43807091db61c152c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:21.943072Z","signature_b64":"DV8N+twfpHZ1HkTGXFWXTrPSHy7T7ThZn8NruRuTH3QgcfTOv6ir98G8AO1fbq09YY0zehTMNQOMp94Kv4IJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e079e334dc8bba370e9ff8dab693f80e54f1b10614539c9f78f7735093e5d80","last_reissued_at":"2026-07-05T11:44:21.942587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:21.942587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AV-Deepfake1M++: A Large-Scale Audio-Visual Deepfake Benchmark with Real-World Perturbations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Dhall, Akanksha Chuchra, Kartik Kuckreja, Muhammad Haris Khan, Shreya Ghosh, Tom Gedeon, Usman Tariq, Zhixi Cai","submitted_at":"2025-07-28T07:27:42Z","abstract_excerpt":"The rapid surge of text-to-speech and face-voice reenactment models makes video fabrication easier and highly realistic. To encounter this problem, we require datasets that rich in type of generation methods and perturbation strategy which is usually common for online videos. To this end, we propose AV-Deepfake1M++, an extension of the AV-Deepfake1M having 2 million video clips with diversified manipulation strategy and audio-visual perturbation. This paper includes the description of data generation strategies along with benchmarking of AV-Deepfake1M++ using state-of-the-art methods. We belie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20579","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/2507.20579/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":"2507.20579","created_at":"2026-07-05T11:44:21.942644+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.20579v1","created_at":"2026-07-05T11:44:21.942644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20579","created_at":"2026-07-05T11:44:21.942644+00:00"},{"alias_kind":"pith_short_12","alias_value":"HYDZ4M2NZC52","created_at":"2026-07-05T11:44:21.942644+00:00"},{"alias_kind":"pith_short_16","alias_value":"HYDZ4M2NZC52G4HJ","created_at":"2026-07-05T11:44:21.942644+00:00"},{"alias_kind":"pith_short_8","alias_value":"HYDZ4M2N","created_at":"2026-07-05T11:44:21.942644+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07337","citing_title":"KLASSify to Verify: Audio-Visual Deepfake Detection Using SSL-based Audio and Handcrafted Visual Features","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HYDZ4M2NZC52G4HJ76G2W2J7QD","json":"https://pith.science/pith/HYDZ4M2NZC52G4HJ76G2W2J7QD.json","graph_json":"https://pith.science/api/pith-number/HYDZ4M2NZC52G4HJ76G2W2J7QD/graph.json","events_json":"https://pith.science/api/pith-number/HYDZ4M2NZC52G4HJ76G2W2J7QD/events.json","paper":"https://pith.science/paper/HYDZ4M2N"},"agent_actions":{"view_html":"https://pith.science/pith/HYDZ4M2NZC52G4HJ76G2W2J7QD","download_json":"https://pith.science/pith/HYDZ4M2NZC52G4HJ76G2W2J7QD.json","view_paper":"https://pith.science/paper/HYDZ4M2N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.20579&json=true","fetch_graph":"https://pith.science/api/pith-number/HYDZ4M2NZC52G4HJ76G2W2J7QD/graph.json","fetch_events":"https://pith.science/api/pith-number/HYDZ4M2NZC52G4HJ76G2W2J7QD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HYDZ4M2NZC52G4HJ76G2W2J7QD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HYDZ4M2NZC52G4HJ76G2W2J7QD/action/storage_attestation","attest_author":"https://pith.science/pith/HYDZ4M2NZC52G4HJ76G2W2J7QD/action/author_attestation","sign_citation":"https://pith.science/pith/HYDZ4M2NZC52G4HJ76G2W2J7QD/action/citation_signature","submit_replication":"https://pith.science/pith/HYDZ4M2NZC52G4HJ76G2W2J7QD/action/replication_record"}},"created_at":"2026-07-05T11:44:21.942644+00:00","updated_at":"2026-07-05T11:44:21.942644+00:00"}