{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:77P4T6JCNLJIB3PHKTEVOWXONA","short_pith_number":"pith:77P4T6JC","schema_version":"1.0","canonical_sha256":"ffdfc9f9226ad280ede754c9575aee6834a230a524b3a31b914327e63f56f695","source":{"kind":"arxiv","id":"2404.04904","version":2},"attestation_state":"computed","paper":{"title":"Cross-Domain Audio Deepfake Detection: Dataset and Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Daimeng Wei, Hao Yang, Mengxin Ren, Miaomiao Ma, Min Zhang, Yuang Li","submitted_at":"2024-04-07T10:10:15Z","abstract_excerpt":"Audio deepfake detection (ADD) is essential for preventing the misuse of synthetic voices that may infringe on personal rights and privacy. Recent zero-shot text-to-speech (TTS) models pose higher risks as they can clone voices with a single utterance. However, the existing ADD datasets are outdated, leading to suboptimal generalization of detection models. In this paper, we construct a new cross-domain ADD dataset comprising over 300 hours of speech data that is generated by five advanced zero-shot TTS models. To simulate real-world scenarios, we employ diverse attack methods and audio prompt"},"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":"2404.04904","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-04-07T10:10:15Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"5632e61ac52d9cfc1b71f50c2639c270a6be893eed3839fa9f504178ca296e04","abstract_canon_sha256":"785bd05a33771e96a02b2dd01a42f131f2bf50d872f9cfcf86e59e67961deb20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:21.267935Z","signature_b64":"QMF20oM6b1DIIoQlYfXHQmg3FAekyaFUcX5fLSr0j6pJO4vBww3/0NF8kNO/6nRakktBww81KryJAoijCk3kCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffdfc9f9226ad280ede754c9575aee6834a230a524b3a31b914327e63f56f695","last_reissued_at":"2026-07-05T09:09:21.267414Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:21.267414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Domain Audio Deepfake Detection: Dataset and Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Daimeng Wei, Hao Yang, Mengxin Ren, Miaomiao Ma, Min Zhang, Yuang Li","submitted_at":"2024-04-07T10:10:15Z","abstract_excerpt":"Audio deepfake detection (ADD) is essential for preventing the misuse of synthetic voices that may infringe on personal rights and privacy. Recent zero-shot text-to-speech (TTS) models pose higher risks as they can clone voices with a single utterance. However, the existing ADD datasets are outdated, leading to suboptimal generalization of detection models. In this paper, we construct a new cross-domain ADD dataset comprising over 300 hours of speech data that is generated by five advanced zero-shot TTS models. To simulate real-world scenarios, we employ diverse attack methods and audio prompt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04904","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/2404.04904/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":"2404.04904","created_at":"2026-07-05T09:09:21.267479+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.04904v2","created_at":"2026-07-05T09:09:21.267479+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04904","created_at":"2026-07-05T09:09:21.267479+00:00"},{"alias_kind":"pith_short_12","alias_value":"77P4T6JCNLJI","created_at":"2026-07-05T09:09:21.267479+00:00"},{"alias_kind":"pith_short_16","alias_value":"77P4T6JCNLJIB3PH","created_at":"2026-07-05T09:09:21.267479+00:00"},{"alias_kind":"pith_short_8","alias_value":"77P4T6JC","created_at":"2026-07-05T09:09:21.267479+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08038","citing_title":"Exploring the Scale and Diversity of Speech Anti-spoofing Datasets: Experiments and Analysis","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/77P4T6JCNLJIB3PHKTEVOWXONA","json":"https://pith.science/pith/77P4T6JCNLJIB3PHKTEVOWXONA.json","graph_json":"https://pith.science/api/pith-number/77P4T6JCNLJIB3PHKTEVOWXONA/graph.json","events_json":"https://pith.science/api/pith-number/77P4T6JCNLJIB3PHKTEVOWXONA/events.json","paper":"https://pith.science/paper/77P4T6JC"},"agent_actions":{"view_html":"https://pith.science/pith/77P4T6JCNLJIB3PHKTEVOWXONA","download_json":"https://pith.science/pith/77P4T6JCNLJIB3PHKTEVOWXONA.json","view_paper":"https://pith.science/paper/77P4T6JC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.04904&json=true","fetch_graph":"https://pith.science/api/pith-number/77P4T6JCNLJIB3PHKTEVOWXONA/graph.json","fetch_events":"https://pith.science/api/pith-number/77P4T6JCNLJIB3PHKTEVOWXONA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/77P4T6JCNLJIB3PHKTEVOWXONA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/77P4T6JCNLJIB3PHKTEVOWXONA/action/storage_attestation","attest_author":"https://pith.science/pith/77P4T6JCNLJIB3PHKTEVOWXONA/action/author_attestation","sign_citation":"https://pith.science/pith/77P4T6JCNLJIB3PHKTEVOWXONA/action/citation_signature","submit_replication":"https://pith.science/pith/77P4T6JCNLJIB3PHKTEVOWXONA/action/replication_record"}},"created_at":"2026-07-05T09:09:21.267479+00:00","updated_at":"2026-07-05T09:09:21.267479+00:00"}