{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IC4D45FW37J2SL7PRBGUBOLBMR","short_pith_number":"pith:IC4D45FW","schema_version":"1.0","canonical_sha256":"40b83e74b6dfd3a92fef884d40b961645952282ad5d480d32c13fd4267705987","source":{"kind":"arxiv","id":"2409.08731","version":1},"attestation_state":"computed","paper":{"title":"DFADD: The Diffusion and Flow-Matching Based Audio Deepfake Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haibin Wu, Hung-yi Lee, I-Hsiang Chiu, I-Ming Lin, Jiawei Du, Jyh-Shing Roger Jang, Wenze Ren, Xuanjun Chen, Yu Tsao","submitted_at":"2024-09-13T11:33:34Z","abstract_excerpt":"Mainstream zero-shot TTS production systems like Voicebox and Seed-TTS achieve human parity speech by leveraging Flow-matching and Diffusion models, respectively. Unfortunately, human-level audio synthesis leads to identity misuse and information security issues. Currently, many antispoofing models have been developed against deepfake audio. However, the efficacy of current state-of-the-art anti-spoofing models in countering audio synthesized by diffusion and flowmatching based TTS systems remains unknown. In this paper, we proposed the Diffusion and Flow-matching based Audio Deepfake (DFADD) "},"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":"2409.08731","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-13T11:33:34Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"a708301145eed66b298ddbf288e5d77b0848dba90879da609fbc62aa959bfd7e","abstract_canon_sha256":"acdc60c6a8155f09eba9743332c985b3d2b5470f86136d05523f654b69b091b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:46.361579Z","signature_b64":"inCxmr44QGPADuRtd+k0JYrJ1VdOL88Rltnjq67nc1fcb4T5uPGAlgKGn45g1hKgy4cJ6w1FbVwC55vC1tvYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40b83e74b6dfd3a92fef884d40b961645952282ad5d480d32c13fd4267705987","last_reissued_at":"2026-07-05T09:06:46.361126Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:46.361126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DFADD: The Diffusion and Flow-Matching Based Audio Deepfake Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haibin Wu, Hung-yi Lee, I-Hsiang Chiu, I-Ming Lin, Jiawei Du, Jyh-Shing Roger Jang, Wenze Ren, Xuanjun Chen, Yu Tsao","submitted_at":"2024-09-13T11:33:34Z","abstract_excerpt":"Mainstream zero-shot TTS production systems like Voicebox and Seed-TTS achieve human parity speech by leveraging Flow-matching and Diffusion models, respectively. Unfortunately, human-level audio synthesis leads to identity misuse and information security issues. Currently, many antispoofing models have been developed against deepfake audio. However, the efficacy of current state-of-the-art anti-spoofing models in countering audio synthesized by diffusion and flowmatching based TTS systems remains unknown. In this paper, we proposed the Diffusion and Flow-matching based Audio Deepfake (DFADD) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08731","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/2409.08731/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":"2409.08731","created_at":"2026-07-05T09:06:46.361183+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.08731v1","created_at":"2026-07-05T09:06:46.361183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08731","created_at":"2026-07-05T09:06:46.361183+00:00"},{"alias_kind":"pith_short_12","alias_value":"IC4D45FW37J2","created_at":"2026-07-05T09:06:46.361183+00:00"},{"alias_kind":"pith_short_16","alias_value":"IC4D45FW37J2SL7P","created_at":"2026-07-05T09:06:46.361183+00:00"},{"alias_kind":"pith_short_8","alias_value":"IC4D45FW","created_at":"2026-07-05T09:06:46.361183+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.21463","citing_title":"SpeechFake: A Large-Scale Multilingual Speech Deepfake Dataset Incorporating Cutting-Edge Generation Methods","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IC4D45FW37J2SL7PRBGUBOLBMR","json":"https://pith.science/pith/IC4D45FW37J2SL7PRBGUBOLBMR.json","graph_json":"https://pith.science/api/pith-number/IC4D45FW37J2SL7PRBGUBOLBMR/graph.json","events_json":"https://pith.science/api/pith-number/IC4D45FW37J2SL7PRBGUBOLBMR/events.json","paper":"https://pith.science/paper/IC4D45FW"},"agent_actions":{"view_html":"https://pith.science/pith/IC4D45FW37J2SL7PRBGUBOLBMR","download_json":"https://pith.science/pith/IC4D45FW37J2SL7PRBGUBOLBMR.json","view_paper":"https://pith.science/paper/IC4D45FW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.08731&json=true","fetch_graph":"https://pith.science/api/pith-number/IC4D45FW37J2SL7PRBGUBOLBMR/graph.json","fetch_events":"https://pith.science/api/pith-number/IC4D45FW37J2SL7PRBGUBOLBMR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IC4D45FW37J2SL7PRBGUBOLBMR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IC4D45FW37J2SL7PRBGUBOLBMR/action/storage_attestation","attest_author":"https://pith.science/pith/IC4D45FW37J2SL7PRBGUBOLBMR/action/author_attestation","sign_citation":"https://pith.science/pith/IC4D45FW37J2SL7PRBGUBOLBMR/action/citation_signature","submit_replication":"https://pith.science/pith/IC4D45FW37J2SL7PRBGUBOLBMR/action/replication_record"}},"created_at":"2026-07-05T09:06:46.361183+00:00","updated_at":"2026-07-05T09:06:46.361183+00:00"}