{"as_of":"2026-08-08T16:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c1ccc991298ab7c6c4b2c8b34e91991bdf69034ed7361615ce9f04c5b3c186c0","coverage":[{"denominator":80,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":80,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-14T14:47:58.592181Z","state":"measured"},{"denominator":80,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":80,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.09891/citation-record","integrity":"/paper/2607.09891/integrity","json":"/paper/2607.09891/citation-record.json","paper":"/paper/2607.09891"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Warning: Humans cannot reliably detect speech deepfakes,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:df29944a467ae82b415cba6b10e4aac9e2d6dbd2abbb6d7ead6f7919af3d5d3b","observation_id":"500e5d23-640d-4d47-bdaa-1039c798acc7","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Audio deepfake detection using deep learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:f6a973754a1909f1c4bab32b5c274025694f3e74a4faaa32624c9af877cab6a4","observation_id":"97245bb3-fcfb-496f-a82d-7fda31a29bce","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"A comprehensive survey of deepfake generation and detection techniques in audio-visual media,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:9cfacb09c694225e285c832359054b0f54ed826b4eb0c6c1abc4ed8a93a05695","observation_id":"164ed5dd-068d-4779-ac97-0091eb21954f","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.14970","last_updated":"2023-08-29T01:50:01Z","snapshot_observed_at":"2026-07-06T16:11:31.948429Z","submitted_at":"2023-08-29T01:50:01Z","title":"Audio Deepfake Detection: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.14970","snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Audio deepfake detection: A survey,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"cited_paper":"/paper/2308.14970","citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:7309f0fc94b2bf549b2f1b537a0255660772a2ec0cefc304195b3c08466242e1","observation_id":"8e6c06dd-aa76-408a-aad9-d99c1b4d9be8","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Vulnerabilities of audio-based biometric authentication systems against deepfake speech synthesis,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:0fb4a5a29752aefdab77c7ce5591bd5b2ed3295034fc3a9ce3cb72851f09ff60","observation_id":"a29b8516-b507-4410-a095-856dabe45eec","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Audio deepfake detection: What has been achieved and what lies ahead,","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:75acf0a6c7e6a126357a99238be2d9c30c92cc23d18067d2df595c8d2450a959","observation_id":"320195a0-9e01-4a7a-a1df-c24ab9c33ad5","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.08739","last_updated":"2024-08-16T13:37:20Z","snapshot_observed_at":"2026-07-06T19:01:32.237848Z","submitted_at":"2024-08-16T13:37:20Z","title":"ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.08739","snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"ASVspoof 5: Crowdsourced speech data, deepfakes, and adversarial attacks at scale,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"cited_paper":"/paper/2408.08739","citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:bcdfaa8a1c3682548cdd72567073276e363e2122dcb637ea78891c9a772c43b5","observation_id":"e1faa814-c3c4-4601-9a0b-25d7e0f3e3ba","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"End-to-end anti-spoofing with RawNet2,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:cc7c5f93601d81bcb5955602ba074b49ea35d651bf4f9a888320b2fb1507bea0","observation_id":"b6b77ab7-9f35-4c9e-be70-c30297a4c804","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"AASIST: Audio anti-spoofing using integrated spectro-temporal graph attention networks,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:5d624509c40f2de8eefab690085290c2621234d5af1b0da7e93db2aefcbc7ae3","observation_id":"bb4fa149-b063-43b0-9c38-f73ad086d184","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Bias in data-driven artificial intelligence systems: An introductory survey,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:ed0bd9a493fea7002daf9655c2b6b61a1458449e9b5cbb883903343db233f131","observation_id":"56234ba1-da39-4deb-b9db-4d83c8d8d758","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Fair voice biometrics: Impact of demographic imbalance on group fairness in speaker recogni- tion,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:f66fbf46e1f487308f5642e85b8507b023e351beb56b1c1aba3feb0b60ca5890","observation_id":"4bf8d3ad-2984-42d0-b5d9-4a0a7c765235","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.12734","last_updated":"2023-08-24T12:26:15Z","snapshot_observed_at":"2026-07-06T16:09:55.775643Z","submitted_at":"2023-08-24T12:26:15Z","title":"Real-time Detection of AI-Generated Speech for DeepFake Voice Conversion","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.12734","snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Real-time detection of AI-generated speech for deepfake voice conversion,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"cited_paper":"/paper/2308.12734","citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:a6b89ae97f474baaf778ee8231e47a5b21a041e948416e21bac925d42864e8ef","observation_id":"4707b01c-377a-4af6-902e-307d88362123","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Gender fairness in audio deepfake detection: Performance and disparity analysis,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:e2e53bcaad0a864bbde66ba8353a77c63a0c83d66fed19ee9ca7b940f47b00c2","observation_id":"bd25dc13-567a-4457-bcee-b405b065c7db","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Fairness without demographics in repeated loss minimization,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:f25fb28f258a3b829152f4173290ccebe46afcc727c4146e7770f0d37fab581e","observation_id":"e1cfe465-de47-4d8a-bd38-7f67e9e34bb1","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"AFSS: Artifact-focused self-synthesis for mitigat- ing bias in audio deepfake detection,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:96ff834c1878fc1a6e6f00186f390d64478642ec7d0c49cf22e5b5afa65a22a7","observation_id":"578d2c61-9225-4ca5-a778-f9a40eaf7c31","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"GBDF: Gender balanced deepfake dataset towards fair deepfake detection,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:a86730794363be3fa74ca1d2fbb4699f90bf755841dde80b5513ae980ddc36e0","observation_id":"bf4dde60-f1e4-405a-937a-6190c490623b","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"A survey on bias and fairness in machine learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:e5e6b5747ab283cc04930db4e64e7ec7b2b0bb3ec7e03786bdf4e0caa8fb5819","observation_id":"94a2b0a1-497b-40f0-a103-847da1791cb2","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Improving fairness in deepfake detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:6b25fde5b4eaee0f0b4ae59714ace1d1d726c588899568487c8e1d48c24e4401","observation_id":"e6351f4d-1f6e-400a-80c1-c8dd36ac651f","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Preserving fairness generalization in deepfake detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:6f667bb11cf517c0bcc7062e98920bd2d98e39930a7b7f111b921b85361dbf67","observation_id":"c7d62e4f-33a5-4da1-8e09-15686bbf16bb","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"FairSSD: Understanding bias in synthetic speech detectors,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:0cd9ce2044c59bb969fd26bf2a5927b1bf946d98011fbf25900ab51113b9680d","observation_id":"724b10d1-e7bc-47c5-9d28-87e4b8fbe71a","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Equality of opportunity in supervised learning,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:92ee6c913d97b00184ad72e5400dad4e9cc9cf5aeef8d88e4229a1d98d75f51e","observation_id":"5766938f-019b-4e4d-9ecd-e9c26572eb06","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Fair prediction with disparate impact: A study of bias in recidivism prediction instruments,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:91bc292ac95a72d4830e6bb0b8e4da8b4e7c73b28c6cb00446776d7de82ae2c7","observation_id":"276050b4-d39d-4689-b183-545b64c19b7f","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Phonetic analysis of real and synthetic speech using HuBERT embeddings: Perspectives for deepfake detection,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:fbf143dd6ea8b0f70d4d2a90fd39a11eb470c7461fa5223c2a547ce8d8944b1c","observation_id":"19d3b187-b1ea-49a9-a58c-52f940637ba3","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Towards trustworthy audio deepfake detection: A systematic framework for diagnosing and mitigating gender bias,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:0c3d5c86525e74eb109a4020e123bb376576a185166a9799053333f5ae6acc0d","observation_id":"b378a403-35e3-4e6d-a029-27639ac92806","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"PhonemeDF: A synthetic speech dataset for audio deepfake detection and naturalness evaluation,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:08141a9819c8633cfaf478244c9b9008806d51baa108c940264750a093dde8ea","observation_id":"6ff8a8e8-2de7-4ea2-ade8-eb26f255bb33","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Investigating the impact of speech enhancement on audio deepfake detection in noisy environments,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:340812c4be45a5b94090aa080cd34b21f3bde93157d13fdbe4674aadc6ddadcb","observation_id":"1fc3ecfd-e067-408b-b294-3ea28890d035","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.00558","last_updated":"2021-05-02T21:55:04Z","snapshot_observed_at":"2026-07-06T11:05:35.329698Z","submitted_at":"2021-05-02T21:55:04Z","title":"An Examination of Fairness of AI Models for Deepfake Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.00558","snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"An examination of fairness of AI models for deepfake detection,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"cited_paper":"/paper/2105.00558","citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:4013b872611ff04029a055bfa8f31d2a57d7b7377650e9e1e21793e6c3101ca3","observation_id":"74a5b503-d539-4f04-b7f4-3a33ee616212","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Analyzing fairness in deepfake detection with massively annotated databases,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:5925742a48dcf1b3b99eadc813e7f09d928e9c57c026062f6dce5b288600da00","observation_id":"beabd784-f88f-4c4c-8c33-7f7cc0270172","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Bias in automated speaker recognition,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:c242bed17e8c14fc5de166a79069077454606ec635e63963199eab64d08572b0","observation_id":"9f2053d5-6ad8-4279-a36e-28e8d1552c64","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.07944","last_updated":"2025-08-11T12:58:37Z","snapshot_observed_at":"2026-08-05T21:47:21.868210Z","submitted_at":"2025-08-11T12:58:37Z","title":"SCDF: A Speaker Characteristics DeepFake Speech Dataset for Bias Analysis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.07944","snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"SCDF: A Speaker Char- acteristics DeepFake Speech Dataset for Bias Analysis,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"cited_paper":"/paper/2508.07944","citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:522bbe4854f6b1a23930e165d492dfb5178c27b67789d2d8f286bce7a04c3c6b","observation_id":"6140bbc3-9585-4538-907e-f5f13063a11b","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:d4196f69b98267d1246269813836a074174889fe74131276ec34fc39521dbf3c","observation_id":"bf2bad8a-eb84-4786-8c1a-c74818bd1705","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Easy, interpretable, effective: openSMILE for voice deepfake detection,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:b5a082c4adfc9d98bb7775e7b5c8ecabcd542fdd5260bd5db2572b3c2fe5915a","observation_id":"f0817f0d-60a7-4c63-921c-bdec0ec869f8","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Natural- Speech: End-to-end text-to-speech synthesis with human-level quality,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:fce15a9b97540c4eabe17862701b8ac5411111d5a5d9750b8915149151558afc","observation_id":"e960aa1b-57e6-4574-b420-9d422aa6bc89","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"ASVspoof: The automatic speaker verification spoofing and countermeasures challenge,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:f6f06bae1617c8a464632ad29653f777bcc6eba3be54ae4fe51dc37365becdde","observation_id":"48ea459f-51b7-415c-bc40-c443c5b5d9a3","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.00537","last_updated":"2021-09-01T16:17:31Z","snapshot_observed_at":"2026-07-06T11:43:28.084184Z","submitted_at":"2021-09-01T16:17:31Z","title":"ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.00537","snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"ASVspoof 2021: Accelerating progress in spoofed and deepfake speech detection,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"cited_paper":"/paper/2109.00537","citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:fdf3311b26ed0e15abbf9f14c304011d6240e295126268b6ef15cd09c0be45cd","observation_id":"9c4aae33-4a1e-4e5d-b086-0ce13e99eb2d","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"ASVspoof 2021: Towards spoofed and deepfake speech detection in the wild,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:8271a576932b9a1b58bd12fa1e16f8879ed28671e2a7e2eb634e3bd20d93d006","observation_id":"b326bcb6-6afd-4fc3-9f66-dd2d4b32cddb","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.09122","last_updated":"2022-03-17T06:56:48Z","snapshot_observed_at":"2026-07-06T12:48:59.296356Z","submitted_at":"2022-03-17T06:56:48Z","title":"To train or not to train adversarially: A study of bias mitigation strategies for speaker recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.09122","snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"To train or not to train adversarially: A study of bias mitigation strategies for speaker recognition,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"cited_paper":"/paper/2203.09122","citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:1ec5cdbc060895fe087f99266361814f7d7233b3faa0b47355de9c937fad840b","observation_id":"dc88e0cf-2c58-41f6-b86e-3a3bbb96811c","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"WavLM: Large-scale self-supervised pre-training for full stack speech processing,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:91e572775b017dbe8cb91625c3d3b0779166e217a7d9e84240c490ac8bb00b5d","observation_id":"de5d25ab-52c5-481f-b1d7-4f14d9d4b3ae","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Controlling the false discovery rate: A practical and powerful approach to multiple testing,","venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:3aa374e1f7e8e73a639706a9f870ef969f12ecccde62722c9209f84c5ec12487","observation_id":"d8f19344-3532-45f3-88f4-273318edaf5d","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"An intervention-based framework for shortcut diagnosis in spoofing countermeasures,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:40be6f5851f0e04a004a5258f7773bcd9c7656329dd7e6b107ec9b62229f5c91","observation_id":"2195dba8-a93a-4b69-96a4-0a548fbbf9f1","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Can SSL frontend generalize to all-type audio spoofing?","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:15f70db016dba7aacab669d2074ec6adfd6a8c5f64998fdf04078a2ddb009934","observation_id":"02f615f2-cf63-463a-9849-b2ab225c3d68","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Decoupled weight decay regularization,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:bbc55c32e479c0d0c79684d78a1f68e3b972a7bf6abb42aa073275e18970fc04","observation_id":"881e8326-4971-44d5-979d-29113fb17af2","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Creating non-parametric bootstrap samples using Poisson frequencies,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:528fcf8a0dbcedec0020a2fdc80c2c8e55da42ae44aeabd756436d9e77b6a68f","observation_id":"2944c02e-eb90-4b35-a0d5-5847726a4542","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"The control of the false discovery rate in multiple testing under dependency,","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:0e1a745b8bfc99c29c4994a0e42864710df6995664c75f473a638cc22852effd","observation_id":"62e993a5-53bf-4e76-ad57-e985329a3291","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Efron and R","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:ff7251d04c062b4a3352512a643ff131033deff471984877f73373bb3da8dc1d","observation_id":"4dda6e18-031f-4239-93d7-45f8af273cd7","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Creating new language and voice components for the updated MaryTTS text-to-speech synthesis platform,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:3e02a58543f36cc3e9bd142de0f15fb41125d36ad5fe94af8540009622d2f2ef","observation_id":"b66ccb00-8c55-4a6c-baa6-19e27d59d9bb","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"ZMM-TTS: Zero-shot multilingual and multispeaker speech synthesis conditioned on self-supervised discrete speech representations,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:66575a19116215136716c69c0c58623b2db62fb42491ab57f51128301ba7000c","observation_id":"ffcced3b-cf2d-42d9-804e-a409a60e4ecc","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"YourTTS: Towards zero-shot multi-speaker TTS and zero- shot voice conversion for everyone,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:aba5ee2b481c684edcc8f2cf043c8dcefa549d8e118c73290a6be31167cd489e","observation_id":"a5e333e2-9209-4819-bef3-bae11bb12651","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04904","last_updated":"2024-06-07T12:56:11Z","snapshot_observed_at":"2026-08-06T13:29:11.244845Z","submitted_at":"2024-06-07T12:56:11Z","title":"XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04904","snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"XTTS: A massively multilingual zero-shot text-to-speech model,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"cited_paper":"/paper/2406.04904","citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:d11a194803431cb8736e7cbb5168c4fbab5a9f1f0828652d43aa3f906cf76c8f","observation_id":"598472a0-17c8-4bad-a142-30cdc42e8ed0","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:da1c6600715ddc38913a0f23af17e745bea3a1acef1e6ec87fe2811b074f93ff","observation_id":"4933bd34-6528-43e1-a495-e1681c938d82","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Grad- TTS: A diffusion probabilistic model for text-to-speech,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:4253600eb18d8cd791989e2ddc5b8b4cc810c582954532eb47ae7d2c789bcb15","observation_id":"696d2734-4ef1-4a46-a55f-5ab2955a5524","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04658","last_updated":"2023-02-16T18:48:56Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:56:10Z","title":"BigVGAN: A Universal Neural Vocoder with Large-Scale Training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04658","snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"BigVGAN: A universal neural vocoder with large-scale training,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"cited_paper":"/paper/2206.04658","citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:d27c24c8f3eb06ad7108d5bcc0e222892115c94b8b211aaa7f3d0b9927e368ca","observation_id":"e71e3b9a-8de6-4cc1-99c5-688362adba5b","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Exact prosody cloning in zero-shot multispeaker text-to-speech,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:78498514d00fe5e374bce80983a0d95ef9e0955d5477cec62b52207f8dbec951","observation_id":"55722d7e-133a-438d-bf3f-19224d02d79b","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"FastPitch: Parallel text-to-speech with pitch prediction,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:59a241bd136318c528771c6654fb03fa20d021a3b36dbf89d27a366dca33a7fa","observation_id":"963ad5dd-2e68-4467-988b-c4663b0bee64","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:63d71e5fa82cb985cd9874315eeb7f95700906185930b50a537ab4e0272aff9e","observation_id":"f432cba7-ddda-4927-af22-bfa7231ad499","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Low-resource multilingual and zero- shot multispeaker TTS,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:aa7659b9e9121f35c2c8a24e5497f1255cd4e33fe7238c30ba004046178cf5ed","observation_id":"6e148a87-2b1f-4159-9772-7bd22a6b8bfc","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.13821","last_updated":"2022-08-04T10:25:40Z","snapshot_observed_at":"2026-08-07T17:24:03.888611Z","submitted_at":"2021-09-28T15:48:22Z","title":"Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.13821","snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Diffusion-based voice conversion with fast maximum likelihood sam- pling scheme,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"cited_paper":"/paper/2109.13821","citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:3962b88e13c1df20fce414e4002e00bc53cf44418b1524018f264b2691eb3979","observation_id":"e7b1ade3-0c46-4c20-95d6-f9752b32c64f","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"HiFi-GAN: Generative adversarial net- works for efficient and high-fidelity speech synthesis,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:501df419f3d5d57fb266c46ebdc12f51b3bea790a66b51e0e7197a269f1e21b1","observation_id":"24b6a1b7-2b96-4467-8af8-1cb998e91ee8","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Natural TTS synthesis by conditioning WaveNet on mel spectrogram predictions,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:386345e8ce84a92c3710f7d3bd88e7fb06ec22e6e102789a074ca01b62b1d798","observation_id":"19b9363f-7e2a-4602-a373-90ee30f2e6b6","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.10394","last_updated":"2021-07-23T01:08:09Z","snapshot_observed_at":"2026-07-06T11:31:23.057674Z","submitted_at":"2021-07-21T23:44:17Z","title":"StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.10394","snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"StarGANv2-VC: A diverse, unsu- pervised, non-parallel framework for natural-sounding voice conversion,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"cited_paper":"/paper/2107.10394","citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:ff6265b66a1952fd51c94943561d88f5b1405e67db26dd0441c5fc95dbe3f0c2","observation_id":"e6e9c61e-998a-493d-bb7b-fdbbd34c7b87","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"V oice conversion using speech-to-speech neuro-style transfer,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:5caa163f0898733c1a133d5735ce028170654ea67a7a290a925efc130eaeaf0e","observation_id":"b0e8ec5d-c38e-4b13-b24a-ac0ef6eeef64","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Self-supervised speech representation learning: A review,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:d5456cab2daf99cd39e869f5a9ec2247305feff33cecd850a388525c65b949c1","observation_id":"bfbd7a63-2dcf-4fa8-b925-a74ee6e780ba","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Toward noise-aware audio deepfake detection: Survey, SNR-benchmarks, and practical recipes,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:2e7be1904ee12d21f1c5e32eee5c30a9aaeb5128d90348522ef841fae87db6b5","observation_id":"0840c4c5-62a1-49aa-a2ab-8ffc2bf37e1e","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"C3-DINO: Joint contrastive and non-contrastive self-supervised learning for speaker verification,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:55c6d11b61c5a1a5a67cc1d2af44320633ba677f6a80dd5a1d38d2935b2d3a7a","observation_id":"3e966358-5b5f-45ed-a45e-260d84dbbd7b","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Context and transcripts improve detection of deepfake audios of public figures,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:e0e534987c7494071a15a7b56eca3c2b5fb48fb345b65fcbfd3d2cd83d0fad9d","observation_id":"21193bf5-0242-451d-96ca-2c4060cd8187","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Fine-tuning self-supervised learning models for end-to-end pronunciation scoring,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:38746bfe8c2c5136eb62d8a0f6bc2575d79324348d41e5cbae4fc8b5cc6b247f","observation_id":"b839c8db-ed75-4964-b6f2-4077e1d1027a","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Using optimal f-measure and random resampling in gene ontology enrichment calculations,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:94fb57cd6bc4ee36148ef354d492760896810fe56c9938c7f6889ca6109224de","observation_id":"708f5ecf-8359-4ded-8112-23cff57438e9","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Modified FDR controlling proce- dure for multi-stage analyses,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:802d9b512f33cd92cc7c4bedaa72ed10e7186a152dd987b6366216b8d15acc3a","observation_id":"87154a5c-95b1-441c-b09a-3e9de05ca0fd","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Cyclostationarity analysis as a complement to self-supervised representations for speech deepfake detection,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:9f7a0684e070dfa75d65d9e5bdca14572d0f44f78df33c80ce611bfaccea4171","observation_id":"fce8bcef-eebe-4620-b540-60c50826209f","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Training-free cross- lingual dysarthria severity assessment via phonological subspace analysis in self-supervised speech representations,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:1e3f3d8a897166eb2c265a8c170552cfafa4a22007813094c1375acee877336b","observation_id":"e06aba63-311a-46e9-b06a-7f19b18c29ef","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Bootstrap confidence regions for the intensity of a Poisson point process,","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:5747d78e0b8576baab7345829acd712882c1d72f92bf615818536188eb442e44","observation_id":"2932c63c-ecc5-40eb-954d-5f204883f7f7","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"PyTorch: An imperative style, high- performance deep learning library,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:6e7b23c14599899f66ded03fa05ec1d204408c8fd8210a1365de31b9bb07606b","observation_id":"d3bdd6d1-2856-47d9-b328-afa624d7dbea","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Fairness through awareness,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:307fe12a2ffb7bb6e5ed6a5e8ec92967d99664e9eb2875f64df262ee8fdaf8b3","observation_id":"159b92fa-3cb8-4b55-88b3-4855081c08d7","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.03079","last_updated":"2026-05-04T18:49:29Z","snapshot_observed_at":"2026-07-31T18:16:20.911637Z","submitted_at":"2026-05-04T18:49:29Z","title":"Phoneme-Level Deepfake Detection Across Emotional Conditions Using Self-Supervised Embeddings","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.03079","snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Phoneme-Level Deep- fake Detection Across Emotional Conditions Using Self-Supervised Em- beddings,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"cited_paper":"/paper/2605.03079","citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:09921e218870ca79e072ae618747b78b2fab45140d997a65d838dfd6825f8789","observation_id":"ee125d76-89b7-4f11-9198-d16c2a1ad946","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"A review on fairness in machine learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:1ed782bbad6be69e8b8ae330bd557ef73c8a4f45a10601401c3882bca22a971f","observation_id":"62356cb7-8ed5-4db1-9604-80a7dbda200d","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Fairness definitions explained,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:08ed6b701f686b1a4b5ed3ff8ba0481d457a5bacbb8796bd60d54c14a88e05cb","observation_id":"542fcb57-3546-41d1-b60b-f0062bc4486c","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Measuring algorithmic fairness,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:12dde61558efa653bdc3fac67a3db30c19fd5d6b080eaa28769fb32f0c8a83a3","observation_id":"079a216e-b869-4b07-92f4-d76824fd3444","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Bias preservation in machine learning: The legality of fairness metrics under EU non-discrimination law,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:3e4a8f86b272f8ed8d8ab3b1653ccc10005ad0f0ba8b7512196d2e1d51cefaaa","observation_id":"3994676e-5610-420e-81e4-c81491ea2866","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.05501","last_updated":"2021-11-10T02:45:18Z","snapshot_observed_at":"2026-07-06T12:07:05.919117Z","submitted_at":"2021-11-10T02:45:18Z","title":"Inclusive Speaker Verification with Adaptive thresholding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.05501","snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"Inclusive speaker verification with adaptive thresholding,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"cited_paper":"/paper/2111.05501","citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:21cffe02c15acdaac3053f489baed0aa4c8d118983b49e356c20388c6da371ec","observation_id":"35f7cc17-e27f-42ad-bbe6-f0045dd5947f","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T14:47:58.592181Z","title":"On fairness and calibration,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-07-14T14:47:58.592181Z"},"links":{"citing_paper":"/paper/2607.09891"},"observation_digest":"sha256:197f0df7c02ec7a15978f4ad2f0421e8c6300043850161dad6b65b503c4a1595","observation_id":"36a2e6a9-a767-4e1a-87eb-db955ca2430a","resolution":{"observed_at":"2026-07-14T14:47:58.592181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.09891","last_updated":"2026-07-10T18:29:24Z","latest_version":1,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-07T18:22:58.421177Z","submitted_at":"2026-07-10T18:29:24Z","title":"What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection"},"reference_resolution":{"displayed":80,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":80,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":80},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 80 of 80 outbound references and 0 inbound Pith citation observations for arXiv:2607.09891."}