{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DEMQIFX7D3UDRWIRNJIY353FOD","short_pith_number":"pith:DEMQIFX7","schema_version":"1.0","canonical_sha256":"19190416ff1ee838d9116a518df76570d95a3561bc0fcc030d302ac28aa1cca7","source":{"kind":"arxiv","id":"2405.16762","version":1},"attestation_state":"computed","paper":{"title":"Addressing Discretization-Induced Bias in Demographic Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CY","authors_text":"Aaron Schein, Evan Dong, Nikhil Garg, Yixin Wang","submitted_at":"2024-05-27T02:22:43Z","abstract_excerpt":"Racial and other demographic imputation is necessary for many applications, especially in auditing disparities and outreach targeting in political campaigns. The canonical approach is to construct continuous predictions -- e.g., based on name and geography -- and then to $\\textit{discretize}$ the predictions by selecting the most likely class (argmax). We study how this practice produces $\\textit{discretization bias}$. In particular, we show that argmax labeling, as used by a prominent commercial voter file vendor to impute race/ethnicity, results in a substantial under-count of African-Americ"},"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":"2405.16762","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-05-27T02:22:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e4ef95ad6fea74ad9a8703e5d2aab586245fd2f90d91c4ffe64127cc76b5e74e","abstract_canon_sha256":"852ceca225d4d6d9e460825a6b7adf9b5b4fede3a98d737b4572e60aea4e4f3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:35.093085Z","signature_b64":"hB0QmBGDg64Lu8jfiBbOCcNlYFXMZ2/NNHn0mHxuw4rb/rHvU4ZYOuY/DwBFwdWItvUFVUUos3+I28KsyNRgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19190416ff1ee838d9116a518df76570d95a3561bc0fcc030d302ac28aa1cca7","last_reissued_at":"2026-07-05T08:23:35.092592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:35.092592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Addressing Discretization-Induced Bias in Demographic Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CY","authors_text":"Aaron Schein, Evan Dong, Nikhil Garg, Yixin Wang","submitted_at":"2024-05-27T02:22:43Z","abstract_excerpt":"Racial and other demographic imputation is necessary for many applications, especially in auditing disparities and outreach targeting in political campaigns. The canonical approach is to construct continuous predictions -- e.g., based on name and geography -- and then to $\\textit{discretize}$ the predictions by selecting the most likely class (argmax). We study how this practice produces $\\textit{discretization bias}$. In particular, we show that argmax labeling, as used by a prominent commercial voter file vendor to impute race/ethnicity, results in a substantial under-count of African-Americ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16762","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/2405.16762/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":"2405.16762","created_at":"2026-07-05T08:23:35.092661+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16762v1","created_at":"2026-07-05T08:23:35.092661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16762","created_at":"2026-07-05T08:23:35.092661+00:00"},{"alias_kind":"pith_short_12","alias_value":"DEMQIFX7D3UD","created_at":"2026-07-05T08:23:35.092661+00:00"},{"alias_kind":"pith_short_16","alias_value":"DEMQIFX7D3UDRWIR","created_at":"2026-07-05T08:23:35.092661+00:00"},{"alias_kind":"pith_short_8","alias_value":"DEMQIFX7","created_at":"2026-07-05T08:23:35.092661+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/DEMQIFX7D3UDRWIRNJIY353FOD","json":"https://pith.science/pith/DEMQIFX7D3UDRWIRNJIY353FOD.json","graph_json":"https://pith.science/api/pith-number/DEMQIFX7D3UDRWIRNJIY353FOD/graph.json","events_json":"https://pith.science/api/pith-number/DEMQIFX7D3UDRWIRNJIY353FOD/events.json","paper":"https://pith.science/paper/DEMQIFX7"},"agent_actions":{"view_html":"https://pith.science/pith/DEMQIFX7D3UDRWIRNJIY353FOD","download_json":"https://pith.science/pith/DEMQIFX7D3UDRWIRNJIY353FOD.json","view_paper":"https://pith.science/paper/DEMQIFX7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16762&json=true","fetch_graph":"https://pith.science/api/pith-number/DEMQIFX7D3UDRWIRNJIY353FOD/graph.json","fetch_events":"https://pith.science/api/pith-number/DEMQIFX7D3UDRWIRNJIY353FOD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DEMQIFX7D3UDRWIRNJIY353FOD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DEMQIFX7D3UDRWIRNJIY353FOD/action/storage_attestation","attest_author":"https://pith.science/pith/DEMQIFX7D3UDRWIRNJIY353FOD/action/author_attestation","sign_citation":"https://pith.science/pith/DEMQIFX7D3UDRWIRNJIY353FOD/action/citation_signature","submit_replication":"https://pith.science/pith/DEMQIFX7D3UDRWIRNJIY353FOD/action/replication_record"}},"created_at":"2026-07-05T08:23:35.092661+00:00","updated_at":"2026-07-05T08:23:35.092661+00:00"}