{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TMOSOO6HM7ERKRHJNA6H63MHKA","short_pith_number":"pith:TMOSOO6H","schema_version":"1.0","canonical_sha256":"9b1d273bc767c91544e9683c7f6d87500ac8744a1820ca16f7d167b46893e395","source":{"kind":"arxiv","id":"2404.13892","version":2},"attestation_state":"computed","paper":{"title":"Retrieval-Augmented Audio Deepfake Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Botao Zhao, Jianzong Wang, Jing Xiao, Junqing Peng, Xiaoyang Qu, Yayun He, Zuheng Kang","submitted_at":"2024-04-22T05:46:40Z","abstract_excerpt":"With recent advances in speech synthesis including text-to-speech (TTS) and voice conversion (VC) systems enabling the generation of ultra-realistic audio deepfakes, there is growing concern about their potential misuse. However, most deepfake (DF) detection methods rely solely on the fuzzy knowledge learned by a single model, resulting in performance bottlenecks and transparency issues. Inspired by retrieval-augmented generation (RAG), we propose a retrieval-augmented detection (RAD) framework that augments test samples with similar retrieved samples for enhanced detection. We also extend the"},"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":"2404.13892","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-04-22T05:46:40Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"75687cf5e1b042f093040ac1b0efab057641ed38e5635fc06987d3e4a4c4006f","abstract_canon_sha256":"b2e865b2fcc7df71adb08790639250cd53d21679281772e946d8a8445e07796b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:04.781232Z","signature_b64":"WYMcNcME9ZPPydkAs6y9pxWhffeYbgvljMalX288RZ9RiadAxj1vfxgEPExb4sr9LxLvxmW13KYr8mGEYzBeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b1d273bc767c91544e9683c7f6d87500ac8744a1820ca16f7d167b46893e395","last_reissued_at":"2026-07-05T08:11:04.780727Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:04.780727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval-Augmented Audio Deepfake Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Botao Zhao, Jianzong Wang, Jing Xiao, Junqing Peng, Xiaoyang Qu, Yayun He, Zuheng Kang","submitted_at":"2024-04-22T05:46:40Z","abstract_excerpt":"With recent advances in speech synthesis including text-to-speech (TTS) and voice conversion (VC) systems enabling the generation of ultra-realistic audio deepfakes, there is growing concern about their potential misuse. However, most deepfake (DF) detection methods rely solely on the fuzzy knowledge learned by a single model, resulting in performance bottlenecks and transparency issues. Inspired by retrieval-augmented generation (RAG), we propose a retrieval-augmented detection (RAD) framework that augments test samples with similar retrieved samples for enhanced detection. We also extend the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13892","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/2404.13892/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":"2404.13892","created_at":"2026-07-05T08:11:04.780783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.13892v2","created_at":"2026-07-05T08:11:04.780783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13892","created_at":"2026-07-05T08:11:04.780783+00:00"},{"alias_kind":"pith_short_12","alias_value":"TMOSOO6HM7ER","created_at":"2026-07-05T08:11:04.780783+00:00"},{"alias_kind":"pith_short_16","alias_value":"TMOSOO6HM7ERKRHJ","created_at":"2026-07-05T08:11:04.780783+00:00"},{"alias_kind":"pith_short_8","alias_value":"TMOSOO6H","created_at":"2026-07-05T08:11:04.780783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TMOSOO6HM7ERKRHJNA6H63MHKA","json":"https://pith.science/pith/TMOSOO6HM7ERKRHJNA6H63MHKA.json","graph_json":"https://pith.science/api/pith-number/TMOSOO6HM7ERKRHJNA6H63MHKA/graph.json","events_json":"https://pith.science/api/pith-number/TMOSOO6HM7ERKRHJNA6H63MHKA/events.json","paper":"https://pith.science/paper/TMOSOO6H"},"agent_actions":{"view_html":"https://pith.science/pith/TMOSOO6HM7ERKRHJNA6H63MHKA","download_json":"https://pith.science/pith/TMOSOO6HM7ERKRHJNA6H63MHKA.json","view_paper":"https://pith.science/paper/TMOSOO6H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.13892&json=true","fetch_graph":"https://pith.science/api/pith-number/TMOSOO6HM7ERKRHJNA6H63MHKA/graph.json","fetch_events":"https://pith.science/api/pith-number/TMOSOO6HM7ERKRHJNA6H63MHKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TMOSOO6HM7ERKRHJNA6H63MHKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TMOSOO6HM7ERKRHJNA6H63MHKA/action/storage_attestation","attest_author":"https://pith.science/pith/TMOSOO6HM7ERKRHJNA6H63MHKA/action/author_attestation","sign_citation":"https://pith.science/pith/TMOSOO6HM7ERKRHJNA6H63MHKA/action/citation_signature","submit_replication":"https://pith.science/pith/TMOSOO6HM7ERKRHJNA6H63MHKA/action/replication_record"}},"created_at":"2026-07-05T08:11:04.780783+00:00","updated_at":"2026-07-05T08:11:04.780783+00:00"}