{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3X4AIT3UZKVHDALWS5OFJFI3ZI","short_pith_number":"pith:3X4AIT3U","schema_version":"1.0","canonical_sha256":"ddf8044f74caaa718176975c54951bca0d82e9b50dd33d9ec37ed477c7b7a6ee","source":{"kind":"arxiv","id":"2406.08112","version":1},"attestation_state":"computed","paper":{"title":"Codecfake: An Initial Dataset for Detecting LLM-based Deepfake Audio","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jianhua Tao, Ruibo Fu, Shuchen Shi, Xiaopeng Wang, Xin Qi, Xuefei Liu, Yi Lu, Yongwei Li, Yuankun Xie, Yukun Liu, Zhengqi Wen, Zhiyong Wang","submitted_at":"2024-06-12T11:47:23Z","abstract_excerpt":"With the proliferation of Large Language Model (LLM) based deepfake audio, there is an urgent need for effective detection methods. Previous deepfake audio generation methods typically involve a multi-step generation process, with the final step using a vocoder to predict the waveform from handcrafted features. However, LLM-based audio is directly generated from discrete neural codecs in an end-to-end generation process, skipping the final step of vocoder processing. This poses a significant challenge for current audio deepfake detection (ADD) models based on vocoder artifacts. To effectively "},"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":"2406.08112","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-12T11:47:23Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"8de5ca6765c354349335345e94033cef315443f5a0b884970b551f69c7c3621e","abstract_canon_sha256":"b69357c3f8929812576b230456ac2d5fc88ce38e660459271708933ae64c93fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:54.759647Z","signature_b64":"p3AHRxJWkYYh0HiieKOE9ny2JFUoS579hTgw1w5CvPgj0UuwospLTTu18XrOB8g2WA/GdJPLPji0XFf1cG5mAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddf8044f74caaa718176975c54951bca0d82e9b50dd33d9ec37ed477c7b7a6ee","last_reissued_at":"2026-07-05T08:30:54.759131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:54.759131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Codecfake: An Initial Dataset for Detecting LLM-based Deepfake Audio","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jianhua Tao, Ruibo Fu, Shuchen Shi, Xiaopeng Wang, Xin Qi, Xuefei Liu, Yi Lu, Yongwei Li, Yuankun Xie, Yukun Liu, Zhengqi Wen, Zhiyong Wang","submitted_at":"2024-06-12T11:47:23Z","abstract_excerpt":"With the proliferation of Large Language Model (LLM) based deepfake audio, there is an urgent need for effective detection methods. Previous deepfake audio generation methods typically involve a multi-step generation process, with the final step using a vocoder to predict the waveform from handcrafted features. However, LLM-based audio is directly generated from discrete neural codecs in an end-to-end generation process, skipping the final step of vocoder processing. This poses a significant challenge for current audio deepfake detection (ADD) models based on vocoder artifacts. To effectively "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08112","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/2406.08112/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":"2406.08112","created_at":"2026-07-05T08:30:54.759190+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08112v1","created_at":"2026-07-05T08:30:54.759190+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08112","created_at":"2026-07-05T08:30:54.759190+00:00"},{"alias_kind":"pith_short_12","alias_value":"3X4AIT3UZKVH","created_at":"2026-07-05T08:30:54.759190+00:00"},{"alias_kind":"pith_short_16","alias_value":"3X4AIT3UZKVHDALW","created_at":"2026-07-05T08:30:54.759190+00:00"},{"alias_kind":"pith_short_8","alias_value":"3X4AIT3U","created_at":"2026-07-05T08:30:54.759190+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19949","citing_title":"Indic-CodecFake meets SATYAM: Towards Detecting Neural Audio Codec Synthesized Speech Deepfakes in Indic Languages","ref_index":163,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3X4AIT3UZKVHDALWS5OFJFI3ZI","json":"https://pith.science/pith/3X4AIT3UZKVHDALWS5OFJFI3ZI.json","graph_json":"https://pith.science/api/pith-number/3X4AIT3UZKVHDALWS5OFJFI3ZI/graph.json","events_json":"https://pith.science/api/pith-number/3X4AIT3UZKVHDALWS5OFJFI3ZI/events.json","paper":"https://pith.science/paper/3X4AIT3U"},"agent_actions":{"view_html":"https://pith.science/pith/3X4AIT3UZKVHDALWS5OFJFI3ZI","download_json":"https://pith.science/pith/3X4AIT3UZKVHDALWS5OFJFI3ZI.json","view_paper":"https://pith.science/paper/3X4AIT3U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08112&json=true","fetch_graph":"https://pith.science/api/pith-number/3X4AIT3UZKVHDALWS5OFJFI3ZI/graph.json","fetch_events":"https://pith.science/api/pith-number/3X4AIT3UZKVHDALWS5OFJFI3ZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3X4AIT3UZKVHDALWS5OFJFI3ZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3X4AIT3UZKVHDALWS5OFJFI3ZI/action/storage_attestation","attest_author":"https://pith.science/pith/3X4AIT3UZKVHDALWS5OFJFI3ZI/action/author_attestation","sign_citation":"https://pith.science/pith/3X4AIT3UZKVHDALWS5OFJFI3ZI/action/citation_signature","submit_replication":"https://pith.science/pith/3X4AIT3UZKVHDALWS5OFJFI3ZI/action/replication_record"}},"created_at":"2026-07-05T08:30:54.759190+00:00","updated_at":"2026-07-05T08:30:54.759190+00:00"}