{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SD4ZKGDQVEU6TBULQLZJ7SCYTJ","short_pith_number":"pith:SD4ZKGDQ","schema_version":"1.0","canonical_sha256":"90f9951870a929e9868b82f29fc8589a64c352d7a1502cd81f367ad5b7d931cb","source":{"kind":"arxiv","id":"2207.07776","version":1},"attestation_state":"computed","paper":{"title":"Adversarial Reweighting for Speaker Verification Fairness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Andreas Stolcke, Chelsea J.-T. Ju, Jasha Droppo, Minho Jin, Yi-Chieh Liu, Zeya Chen","submitted_at":"2022-07-15T22:50:31Z","abstract_excerpt":"We address performance fairness for speaker verification using the adversarial reweighting (ARW) method. ARW is reformulated for speaker verification with metric learning, and shown to improve results across different subgroups of gender and nationality, without requiring annotation of subgroups in the training data. An adversarial network learns a weight for each training sample in the batch so that the main learner is forced to focus on poorly performing instances. Using a min-max optimization algorithm, this method improves overall speaker verification fairness. We present three different A"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2207.07776","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-07-15T22:50:31Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"0974265f802be6c644e70cd00cd6032f81e7ca2680f32274c3031a6d12709b64","abstract_canon_sha256":"c16d6909cbe141b6e8b121b9b4ae806262a89fc0043499e8a8cf0cfb83cb57b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:37.964804Z","signature_b64":"3vhbx7aQpa5BpOQNI+H73gtgwseOGCH9YPFtz4M46k/5qqqREwtYf4I4Xilu2rZ2X2j8jL0sAwBvJn4Vpo2rDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90f9951870a929e9868b82f29fc8589a64c352d7a1502cd81f367ad5b7d931cb","last_reissued_at":"2026-07-05T07:42:37.964307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:37.964307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Reweighting for Speaker Verification Fairness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Andreas Stolcke, Chelsea J.-T. Ju, Jasha Droppo, Minho Jin, Yi-Chieh Liu, Zeya Chen","submitted_at":"2022-07-15T22:50:31Z","abstract_excerpt":"We address performance fairness for speaker verification using the adversarial reweighting (ARW) method. ARW is reformulated for speaker verification with metric learning, and shown to improve results across different subgroups of gender and nationality, without requiring annotation of subgroups in the training data. An adversarial network learns a weight for each training sample in the batch so that the main learner is forced to focus on poorly performing instances. Using a min-max optimization algorithm, this method improves overall speaker verification fairness. We present three different A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.07776","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2207.07776/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2207.07776","created_at":"2026-07-05T07:42:37.964369+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.07776v1","created_at":"2026-07-05T07:42:37.964369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.07776","created_at":"2026-07-05T07:42:37.964369+00:00"},{"alias_kind":"pith_short_12","alias_value":"SD4ZKGDQVEU6","created_at":"2026-07-05T07:42:37.964369+00:00"},{"alias_kind":"pith_short_16","alias_value":"SD4ZKGDQVEU6TBUL","created_at":"2026-07-05T07:42:37.964369+00:00"},{"alias_kind":"pith_short_8","alias_value":"SD4ZKGDQ","created_at":"2026-07-05T07:42:37.964369+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SD4ZKGDQVEU6TBULQLZJ7SCYTJ","json":"https://pith.science/pith/SD4ZKGDQVEU6TBULQLZJ7SCYTJ.json","graph_json":"https://pith.science/api/pith-number/SD4ZKGDQVEU6TBULQLZJ7SCYTJ/graph.json","events_json":"https://pith.science/api/pith-number/SD4ZKGDQVEU6TBULQLZJ7SCYTJ/events.json","paper":"https://pith.science/paper/SD4ZKGDQ"},"agent_actions":{"view_html":"https://pith.science/pith/SD4ZKGDQVEU6TBULQLZJ7SCYTJ","download_json":"https://pith.science/pith/SD4ZKGDQVEU6TBULQLZJ7SCYTJ.json","view_paper":"https://pith.science/paper/SD4ZKGDQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.07776&json=true","fetch_graph":"https://pith.science/api/pith-number/SD4ZKGDQVEU6TBULQLZJ7SCYTJ/graph.json","fetch_events":"https://pith.science/api/pith-number/SD4ZKGDQVEU6TBULQLZJ7SCYTJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SD4ZKGDQVEU6TBULQLZJ7SCYTJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SD4ZKGDQVEU6TBULQLZJ7SCYTJ/action/storage_attestation","attest_author":"https://pith.science/pith/SD4ZKGDQVEU6TBULQLZJ7SCYTJ/action/author_attestation","sign_citation":"https://pith.science/pith/SD4ZKGDQVEU6TBULQLZJ7SCYTJ/action/citation_signature","submit_replication":"https://pith.science/pith/SD4ZKGDQVEU6TBULQLZJ7SCYTJ/action/replication_record"}},"created_at":"2026-07-05T07:42:37.964369+00:00","updated_at":"2026-07-05T07:42:37.964369+00:00"}