{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ABZAN47YFNUD7EAAEGDIWVTBNN","short_pith_number":"pith:ABZAN47Y","schema_version":"1.0","canonical_sha256":"007206f3f82b683f900021868b56616b43c103a1a92f7ab154a08d0c96ed74f0","source":{"kind":"arxiv","id":"2111.09983","version":1},"attestation_state":"computed","paper":{"title":"Towards Measuring Fairness in Speech Recognition: Casual Conversations Dataset Transcriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Alex Xiao, Andres Alvarado, Caner Hazirbas, Chunxi Liu, Leda Sar{\\i}, Mark Chou, Michael Picheny, Pooja Chitkara, Xiaohui Zhang, Yatharth Saraf","submitted_at":"2021-11-18T23:54:05Z","abstract_excerpt":"It is well known that many machine learning systems demonstrate bias towards specific groups of individuals. This problem has been studied extensively in the Facial Recognition area, but much less so in Automatic Speech Recognition (ASR). This paper presents initial Speech Recognition results on \"Casual Conversations\" -- a publicly released 846 hour corpus designed to help researchers evaluate their computer vision and audio models for accuracy across a diverse set of metadata, including age, gender, and skin tone. The entire corpus has been manually transcribed, allowing for detailed ASR eval"},"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":"2111.09983","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-11-18T23:54:05Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"162f6d75d65343c51e5fdeb965e367b2a59492a9ecd9b64e0eecefa9b1f412e0","abstract_canon_sha256":"69220bfd579b28f6201b92aff233aae5f7ccbd1cf4086ed84ea178825664091e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:33:26.328075Z","signature_b64":"/78PL5RZLZq2mY+QE2O5hWNHPk18Shzy007aQ7QmChV0xy9RMElQI55OrDPuFQxIWn8x1wO8o02MjOxNPFKKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"007206f3f82b683f900021868b56616b43c103a1a92f7ab154a08d0c96ed74f0","last_reissued_at":"2026-07-05T03:33:26.327577Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:33:26.327577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Measuring Fairness in Speech Recognition: Casual Conversations Dataset Transcriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Alex Xiao, Andres Alvarado, Caner Hazirbas, Chunxi Liu, Leda Sar{\\i}, Mark Chou, Michael Picheny, Pooja Chitkara, Xiaohui Zhang, Yatharth Saraf","submitted_at":"2021-11-18T23:54:05Z","abstract_excerpt":"It is well known that many machine learning systems demonstrate bias towards specific groups of individuals. This problem has been studied extensively in the Facial Recognition area, but much less so in Automatic Speech Recognition (ASR). This paper presents initial Speech Recognition results on \"Casual Conversations\" -- a publicly released 846 hour corpus designed to help researchers evaluate their computer vision and audio models for accuracy across a diverse set of metadata, including age, gender, and skin tone. The entire corpus has been manually transcribed, allowing for detailed ASR eval"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.09983","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/2111.09983/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":"2111.09983","created_at":"2026-07-05T03:33:26.327639+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.09983v1","created_at":"2026-07-05T03:33:26.327639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.09983","created_at":"2026-07-05T03:33:26.327639+00:00"},{"alias_kind":"pith_short_12","alias_value":"ABZAN47YFNUD","created_at":"2026-07-05T03:33:26.327639+00:00"},{"alias_kind":"pith_short_16","alias_value":"ABZAN47YFNUD7EAA","created_at":"2026-07-05T03:33:26.327639+00:00"},{"alias_kind":"pith_short_8","alias_value":"ABZAN47Y","created_at":"2026-07-05T03:33:26.327639+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21148","citing_title":"\"This Wasn't Made for Me\": Recentering User Experience and Emotional Impact in the Evaluation of ASR Bias","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ABZAN47YFNUD7EAAEGDIWVTBNN","json":"https://pith.science/pith/ABZAN47YFNUD7EAAEGDIWVTBNN.json","graph_json":"https://pith.science/api/pith-number/ABZAN47YFNUD7EAAEGDIWVTBNN/graph.json","events_json":"https://pith.science/api/pith-number/ABZAN47YFNUD7EAAEGDIWVTBNN/events.json","paper":"https://pith.science/paper/ABZAN47Y"},"agent_actions":{"view_html":"https://pith.science/pith/ABZAN47YFNUD7EAAEGDIWVTBNN","download_json":"https://pith.science/pith/ABZAN47YFNUD7EAAEGDIWVTBNN.json","view_paper":"https://pith.science/paper/ABZAN47Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.09983&json=true","fetch_graph":"https://pith.science/api/pith-number/ABZAN47YFNUD7EAAEGDIWVTBNN/graph.json","fetch_events":"https://pith.science/api/pith-number/ABZAN47YFNUD7EAAEGDIWVTBNN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ABZAN47YFNUD7EAAEGDIWVTBNN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ABZAN47YFNUD7EAAEGDIWVTBNN/action/storage_attestation","attest_author":"https://pith.science/pith/ABZAN47YFNUD7EAAEGDIWVTBNN/action/author_attestation","sign_citation":"https://pith.science/pith/ABZAN47YFNUD7EAAEGDIWVTBNN/action/citation_signature","submit_replication":"https://pith.science/pith/ABZAN47YFNUD7EAAEGDIWVTBNN/action/replication_record"}},"created_at":"2026-07-05T03:33:26.327639+00:00","updated_at":"2026-07-05T03:33:26.327639+00:00"}