{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QOFVIVNCJUDQT2TNPXH2G6A3VP","short_pith_number":"pith:QOFVIVNC","schema_version":"1.0","canonical_sha256":"838b5455a24d0709ea6d7dcfa3781babd21532736a78aacb0df8a912b91a92f3","source":{"kind":"arxiv","id":"2411.00121","version":1},"attestation_state":"computed","paper":{"title":"I Can Hear You: Selective Robust Training for Deepfake Audio Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aroon Sankoh, Chengzhi Mao, Emanuel Mendiola-Ortiz, Junfeng Yang, Wei Hao, William Lin, Zirui Zhang","submitted_at":"2024-10-31T18:21:36Z","abstract_excerpt":"Recent advances in AI-generated voices have intensified the challenge of detecting deepfake audio, posing risks for scams and the spread of disinformation. To tackle this issue, we establish the largest public voice dataset to date, named DeepFakeVox-HQ, comprising 1.3 million samples, including 270,000 high-quality deepfake samples from 14 diverse sources. Despite previously reported high accuracy, existing deepfake voice detectors struggle with our diversely collected dataset, and their detection success rates drop even further under realistic corruptions and adversarial attacks. We conduct "},"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":"2411.00121","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-31T18:21:36Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"42282d18ccd5e6afb8a97279ff10b2b9c8bc5efd1e15ce23afd6dc3f9b3390ce","abstract_canon_sha256":"c5daf650dd672c0e6429f6a7be31b485788b99d0fc1390463d01a0945b801e6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:37.793107Z","signature_b64":"aLb++TRrq535ZjrK10VvOpoLBCsub2bKKhDAJ40SfSpZwjNZfaJRWCJBnFEzp8v4LqgBUrFj+njpgtrPC9gMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"838b5455a24d0709ea6d7dcfa3781babd21532736a78aacb0df8a912b91a92f3","last_reissued_at":"2026-07-05T09:29:37.792604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:37.792604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"I Can Hear You: Selective Robust Training for Deepfake Audio Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aroon Sankoh, Chengzhi Mao, Emanuel Mendiola-Ortiz, Junfeng Yang, Wei Hao, William Lin, Zirui Zhang","submitted_at":"2024-10-31T18:21:36Z","abstract_excerpt":"Recent advances in AI-generated voices have intensified the challenge of detecting deepfake audio, posing risks for scams and the spread of disinformation. To tackle this issue, we establish the largest public voice dataset to date, named DeepFakeVox-HQ, comprising 1.3 million samples, including 270,000 high-quality deepfake samples from 14 diverse sources. Despite previously reported high accuracy, existing deepfake voice detectors struggle with our diversely collected dataset, and their detection success rates drop even further under realistic corruptions and adversarial attacks. We conduct "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00121","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/2411.00121/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":"2411.00121","created_at":"2026-07-05T09:29:37.792671+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00121v1","created_at":"2026-07-05T09:29:37.792671+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00121","created_at":"2026-07-05T09:29:37.792671+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOFVIVNCJUDQ","created_at":"2026-07-05T09:29:37.792671+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOFVIVNCJUDQT2TN","created_at":"2026-07-05T09:29:37.792671+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOFVIVNC","created_at":"2026-07-05T09:29:37.792671+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30366","citing_title":"Escaping the Linearity Trap: Manifold Detours for Black-Box Adversarial Attacks on Singing Audio Deepfake Detection","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QOFVIVNCJUDQT2TNPXH2G6A3VP","json":"https://pith.science/pith/QOFVIVNCJUDQT2TNPXH2G6A3VP.json","graph_json":"https://pith.science/api/pith-number/QOFVIVNCJUDQT2TNPXH2G6A3VP/graph.json","events_json":"https://pith.science/api/pith-number/QOFVIVNCJUDQT2TNPXH2G6A3VP/events.json","paper":"https://pith.science/paper/QOFVIVNC"},"agent_actions":{"view_html":"https://pith.science/pith/QOFVIVNCJUDQT2TNPXH2G6A3VP","download_json":"https://pith.science/pith/QOFVIVNCJUDQT2TNPXH2G6A3VP.json","view_paper":"https://pith.science/paper/QOFVIVNC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00121&json=true","fetch_graph":"https://pith.science/api/pith-number/QOFVIVNCJUDQT2TNPXH2G6A3VP/graph.json","fetch_events":"https://pith.science/api/pith-number/QOFVIVNCJUDQT2TNPXH2G6A3VP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOFVIVNCJUDQT2TNPXH2G6A3VP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOFVIVNCJUDQT2TNPXH2G6A3VP/action/storage_attestation","attest_author":"https://pith.science/pith/QOFVIVNCJUDQT2TNPXH2G6A3VP/action/author_attestation","sign_citation":"https://pith.science/pith/QOFVIVNCJUDQT2TNPXH2G6A3VP/action/citation_signature","submit_replication":"https://pith.science/pith/QOFVIVNCJUDQT2TNPXH2G6A3VP/action/replication_record"}},"created_at":"2026-07-05T09:29:37.792671+00:00","updated_at":"2026-07-05T09:29:37.792671+00:00"}