{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WOMSSB3PV6X5LXRSB7RJJI3TQG","short_pith_number":"pith:WOMSSB3P","schema_version":"1.0","canonical_sha256":"b39929076fafafd5de320fe294a37381a5edf4f2ece7e51d280a2119e6cd28fd","source":{"kind":"arxiv","id":"2304.03858","version":4},"attestation_state":"computed","paper":{"title":"Benchmark Dataset Dynamics, Bias and Privacy Challenges in Voice Biometrics Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CY","authors_text":"Anna Leschanowsky, Carolyn Quinlan, Casandra Rusti, Lauriane Gorce, Michaela Pnacek, Wiebke Hutiri","submitted_at":"2023-04-07T23:05:37Z","abstract_excerpt":"Speaker recognition is a widely used voice-based biometric technology with applications in various industries, including banking, education, recruitment, immigration, law enforcement, healthcare, and well-being. However, while dataset evaluations and audits have improved data practices in face recognition and other computer vision tasks, the data practices in speaker recognition have gone largely unquestioned. Our research aims to address this gap by exploring how dataset usage has evolved over time and what implications this has on bias, fairness and privacy in speaker recognition systems. Pr"},"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":"2304.03858","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2023-04-07T23:05:37Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"2cc354e4d66342aa1a5a88f053a02551927c12e4b89bf547ebca588e02084800","abstract_canon_sha256":"16d05a50933c564b5fe5d95c22430d5cf0060d2570559ded73c52b93741d001b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:20.800529Z","signature_b64":"HH42F6Ej6Bs4G8mh7wY8uPcD0A2r0EPxO6keWKN7KzpPMsaKai9aH8K4SXJSFnI3Dj3peu9QiBgs8aWVYLLmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b39929076fafafd5de320fe294a37381a5edf4f2ece7e51d280a2119e6cd28fd","last_reissued_at":"2026-07-05T06:42:20.800019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:20.800019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmark Dataset Dynamics, Bias and Privacy Challenges in Voice Biometrics Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CY","authors_text":"Anna Leschanowsky, Carolyn Quinlan, Casandra Rusti, Lauriane Gorce, Michaela Pnacek, Wiebke Hutiri","submitted_at":"2023-04-07T23:05:37Z","abstract_excerpt":"Speaker recognition is a widely used voice-based biometric technology with applications in various industries, including banking, education, recruitment, immigration, law enforcement, healthcare, and well-being. However, while dataset evaluations and audits have improved data practices in face recognition and other computer vision tasks, the data practices in speaker recognition have gone largely unquestioned. Our research aims to address this gap by exploring how dataset usage has evolved over time and what implications this has on bias, fairness and privacy in speaker recognition systems. Pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03858","kind":"arxiv","version":4},"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/2304.03858/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":"2304.03858","created_at":"2026-07-05T06:42:20.800079+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.03858v4","created_at":"2026-07-05T06:42:20.800079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03858","created_at":"2026-07-05T06:42:20.800079+00:00"},{"alias_kind":"pith_short_12","alias_value":"WOMSSB3PV6X5","created_at":"2026-07-05T06:42:20.800079+00:00"},{"alias_kind":"pith_short_16","alias_value":"WOMSSB3PV6X5LXRS","created_at":"2026-07-05T06:42:20.800079+00:00"},{"alias_kind":"pith_short_8","alias_value":"WOMSSB3P","created_at":"2026-07-05T06:42:20.800079+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08087","citing_title":"Assessing the Energy and Carbon Emissions of Neural Speaker Verification Model in Training and Inference","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WOMSSB3PV6X5LXRSB7RJJI3TQG","json":"https://pith.science/pith/WOMSSB3PV6X5LXRSB7RJJI3TQG.json","graph_json":"https://pith.science/api/pith-number/WOMSSB3PV6X5LXRSB7RJJI3TQG/graph.json","events_json":"https://pith.science/api/pith-number/WOMSSB3PV6X5LXRSB7RJJI3TQG/events.json","paper":"https://pith.science/paper/WOMSSB3P"},"agent_actions":{"view_html":"https://pith.science/pith/WOMSSB3PV6X5LXRSB7RJJI3TQG","download_json":"https://pith.science/pith/WOMSSB3PV6X5LXRSB7RJJI3TQG.json","view_paper":"https://pith.science/paper/WOMSSB3P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.03858&json=true","fetch_graph":"https://pith.science/api/pith-number/WOMSSB3PV6X5LXRSB7RJJI3TQG/graph.json","fetch_events":"https://pith.science/api/pith-number/WOMSSB3PV6X5LXRSB7RJJI3TQG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WOMSSB3PV6X5LXRSB7RJJI3TQG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WOMSSB3PV6X5LXRSB7RJJI3TQG/action/storage_attestation","attest_author":"https://pith.science/pith/WOMSSB3PV6X5LXRSB7RJJI3TQG/action/author_attestation","sign_citation":"https://pith.science/pith/WOMSSB3PV6X5LXRSB7RJJI3TQG/action/citation_signature","submit_replication":"https://pith.science/pith/WOMSSB3PV6X5LXRSB7RJJI3TQG/action/replication_record"}},"created_at":"2026-07-05T06:42:20.800079+00:00","updated_at":"2026-07-05T06:42:20.800079+00:00"}