{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DEMQIFX7D3UDRWIRNJIY353FOD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"852ceca225d4d6d9e460825a6b7adf9b5b4fede3a98d737b4572e60aea4e4f3d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-05-27T02:22:43Z","title_canon_sha256":"e4ef95ad6fea74ad9a8703e5d2aab586245fd2f90d91c4ffe64127cc76b5e74e"},"schema_version":"1.0","source":{"id":"2405.16762","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16762","created_at":"2026-07-05T08:23:35Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16762v1","created_at":"2026-07-05T08:23:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16762","created_at":"2026-07-05T08:23:35Z"},{"alias_kind":"pith_short_12","alias_value":"DEMQIFX7D3UD","created_at":"2026-07-05T08:23:35Z"},{"alias_kind":"pith_short_16","alias_value":"DEMQIFX7D3UDRWIR","created_at":"2026-07-05T08:23:35Z"},{"alias_kind":"pith_short_8","alias_value":"DEMQIFX7","created_at":"2026-07-05T08:23:35Z"}],"graph_snapshots":[{"event_id":"sha256:f199611386c87b8406df31b070ff5d67a3a044dc8a8cf2e2abaa0839bf20bcbf","target":"graph","created_at":"2026-07-05T08:23:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.16762/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aaron Schein, Evan Dong, Nikhil Garg, Yixin Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-05-27T02:22:43Z","title":"Addressing Discretization-Induced Bias in Demographic Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16762","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c67f51ff7cd8afcf48ed1b5e46d9ad8b0082306e5e133428b2db4227cacc0345","target":"record","created_at":"2026-07-05T08:23:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"852ceca225d4d6d9e460825a6b7adf9b5b4fede3a98d737b4572e60aea4e4f3d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-05-27T02:22:43Z","title_canon_sha256":"e4ef95ad6fea74ad9a8703e5d2aab586245fd2f90d91c4ffe64127cc76b5e74e"},"schema_version":"1.0","source":{"id":"2405.16762","kind":"arxiv","version":1}},"canonical_sha256":"19190416ff1ee838d9116a518df76570d95a3561bc0fcc030d302ac28aa1cca7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19190416ff1ee838d9116a518df76570d95a3561bc0fcc030d302ac28aa1cca7","first_computed_at":"2026-07-05T08:23:35.092592Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:35.092592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hB0QmBGDg64Lu8jfiBbOCcNlYFXMZ2/NNHn0mHxuw4rb/rHvU4ZYOuY/DwBFwdWItvUFVUUos3+I28KsyNRgDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:35.093085Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16762","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c67f51ff7cd8afcf48ed1b5e46d9ad8b0082306e5e133428b2db4227cacc0345","sha256:f199611386c87b8406df31b070ff5d67a3a044dc8a8cf2e2abaa0839bf20bcbf"],"state_sha256":"cd71e21107cc120286ba691c64ec2c40fef9eb7ae9b80798d64f89f2fd8ca186"}