{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4KFQMDMT3GV64GHKLNWERNLNHR","short_pith_number":"pith:4KFQMDMT","schema_version":"1.0","canonical_sha256":"e28b060d93d9abee18ea5b6c48b56d3c4b866d321d4de3f34ba232985afd3dba","source":{"kind":"arxiv","id":"2303.10721","version":1},"attestation_state":"computed","paper":{"title":"Right the docs: Characterising voice dataset documentation practices used in machine learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","cs.SD","eess.AS"],"primary_cat":"cs.HC","authors_text":"Elizabeth T. Williams, Kathy Reid","submitted_at":"2023-03-19T17:32:07Z","abstract_excerpt":"Voice-enabled technology is quickly becoming ubiquitous, and is constituted from machine learning (ML)-enabled components such as speech recognition and voice activity detection. However, these systems don't yet work well for everyone. They exhibit bias - the systematic and unfair discrimination against individuals or cohorts of individuals in favour of others (Friedman & Nissembaum, 1996) - across axes such as age, gender and accent.\n  ML is reliant on large datasets for training. Dataset documentation is designed to give ML Practitioners (MLPs) a better understanding of a dataset's character"},"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":"2303.10721","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2023-03-19T17:32:07Z","cross_cats_sorted":["cs.CY","cs.SD","eess.AS"],"title_canon_sha256":"7c4d829d1a3eebe24474536448bbbe88d59a522655e58dfe2d4ceb32946ba1c4","abstract_canon_sha256":"4a085ca782cd657752c4a0a1c6d34abcd8260af852fef213135d2c5f3b50a0b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:35.928238Z","signature_b64":"8LgXg8OpK4Sd79DrE0pZET/pUqQDXfKCtLc6Of8IfbXULFo/C7eY8vDpb9x3aj2PmKOqY9SQBDPShXX/YW2mBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e28b060d93d9abee18ea5b6c48b56d3c4b866d321d4de3f34ba232985afd3dba","last_reissued_at":"2026-07-05T05:52:35.927885Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:35.927885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Right the docs: Characterising voice dataset documentation practices used in machine learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","cs.SD","eess.AS"],"primary_cat":"cs.HC","authors_text":"Elizabeth T. Williams, Kathy Reid","submitted_at":"2023-03-19T17:32:07Z","abstract_excerpt":"Voice-enabled technology is quickly becoming ubiquitous, and is constituted from machine learning (ML)-enabled components such as speech recognition and voice activity detection. However, these systems don't yet work well for everyone. They exhibit bias - the systematic and unfair discrimination against individuals or cohorts of individuals in favour of others (Friedman & Nissembaum, 1996) - across axes such as age, gender and accent.\n  ML is reliant on large datasets for training. Dataset documentation is designed to give ML Practitioners (MLPs) a better understanding of a dataset's character"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.10721","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/2303.10721/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":"2303.10721","created_at":"2026-07-05T05:52:35.927934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.10721v1","created_at":"2026-07-05T05:52:35.927934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.10721","created_at":"2026-07-05T05:52:35.927934+00:00"},{"alias_kind":"pith_short_12","alias_value":"4KFQMDMT3GV6","created_at":"2026-07-05T05:52:35.927934+00:00"},{"alias_kind":"pith_short_16","alias_value":"4KFQMDMT3GV64GHK","created_at":"2026-07-05T05:52:35.927934+00:00"},{"alias_kind":"pith_short_8","alias_value":"4KFQMDMT","created_at":"2026-07-05T05:52:35.927934+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/4KFQMDMT3GV64GHKLNWERNLNHR","json":"https://pith.science/pith/4KFQMDMT3GV64GHKLNWERNLNHR.json","graph_json":"https://pith.science/api/pith-number/4KFQMDMT3GV64GHKLNWERNLNHR/graph.json","events_json":"https://pith.science/api/pith-number/4KFQMDMT3GV64GHKLNWERNLNHR/events.json","paper":"https://pith.science/paper/4KFQMDMT"},"agent_actions":{"view_html":"https://pith.science/pith/4KFQMDMT3GV64GHKLNWERNLNHR","download_json":"https://pith.science/pith/4KFQMDMT3GV64GHKLNWERNLNHR.json","view_paper":"https://pith.science/paper/4KFQMDMT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.10721&json=true","fetch_graph":"https://pith.science/api/pith-number/4KFQMDMT3GV64GHKLNWERNLNHR/graph.json","fetch_events":"https://pith.science/api/pith-number/4KFQMDMT3GV64GHKLNWERNLNHR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4KFQMDMT3GV64GHKLNWERNLNHR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4KFQMDMT3GV64GHKLNWERNLNHR/action/storage_attestation","attest_author":"https://pith.science/pith/4KFQMDMT3GV64GHKLNWERNLNHR/action/author_attestation","sign_citation":"https://pith.science/pith/4KFQMDMT3GV64GHKLNWERNLNHR/action/citation_signature","submit_replication":"https://pith.science/pith/4KFQMDMT3GV64GHKLNWERNLNHR/action/replication_record"}},"created_at":"2026-07-05T05:52:35.927934+00:00","updated_at":"2026-07-05T05:52:35.927934+00:00"}