{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3NL73BUM2MDHSB7WY4QYKOEC4T","short_pith_number":"pith:3NL73BUM","schema_version":"1.0","canonical_sha256":"db57fd868cd3067907f6c721853882e4e064b7d855a24b33fd347e29972f880f","source":{"kind":"arxiv","id":"2504.21259","version":1},"attestation_state":"computed","paper":{"title":"LSTM+Geo with xgBoost Filtering: A Novel Approach for Race and Ethnicity Imputation with Reduced Bias","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CY","authors_text":"A. Pastor, S. Chalavadi, T. Leitch","submitted_at":"2025-04-30T02:20:08Z","abstract_excerpt":"Accurate imputation of race and ethnicity (R&E) is crucial for analyzing disparities and informing policy. Methods like Bayesian Improved Surname Geocoding (BISG) are widely used but exhibit limitations, including systematic misclassification biases linked to socioeconomic status. This paper introduces LSTM+Geo, a novel approach enhancing Long Short-Term Memory (LSTM) networks with census tract geolocation information. Using a large voter dataset, we demonstrate that LSTM+Geo (88.7% accuracy) significantly outperforms standalone LSTM (86.4%) and Bayesian methods like BISG (82.9%) and BIFSG (86"},"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":"2504.21259","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-04-30T02:20:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"96caf26601ee23f56aa11ee0dac73931da7aae2465eac5febf1a47b524d41129","abstract_canon_sha256":"6b738b66a96e2bdad3fd414c159aec6549bdb56a6caf08d204569f313c32617f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:21.004486Z","signature_b64":"IbhUj3ww7P3Rv8g1rZnYDVkeqk/3NvAppiurBJCJmD1ymNpljUZU+ZIiBPe+xm5H0CjnqjTZe/8dNGsf4dLzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db57fd868cd3067907f6c721853882e4e064b7d855a24b33fd347e29972f880f","last_reissued_at":"2026-07-05T10:56:21.003989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:21.003989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LSTM+Geo with xgBoost Filtering: A Novel Approach for Race and Ethnicity Imputation with Reduced Bias","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CY","authors_text":"A. Pastor, S. Chalavadi, T. Leitch","submitted_at":"2025-04-30T02:20:08Z","abstract_excerpt":"Accurate imputation of race and ethnicity (R&E) is crucial for analyzing disparities and informing policy. Methods like Bayesian Improved Surname Geocoding (BISG) are widely used but exhibit limitations, including systematic misclassification biases linked to socioeconomic status. This paper introduces LSTM+Geo, a novel approach enhancing Long Short-Term Memory (LSTM) networks with census tract geolocation information. Using a large voter dataset, we demonstrate that LSTM+Geo (88.7% accuracy) significantly outperforms standalone LSTM (86.4%) and Bayesian methods like BISG (82.9%) and BIFSG (86"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21259","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/2504.21259/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":"2504.21259","created_at":"2026-07-05T10:56:21.004049+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.21259v1","created_at":"2026-07-05T10:56:21.004049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21259","created_at":"2026-07-05T10:56:21.004049+00:00"},{"alias_kind":"pith_short_12","alias_value":"3NL73BUM2MDH","created_at":"2026-07-05T10:56:21.004049+00:00"},{"alias_kind":"pith_short_16","alias_value":"3NL73BUM2MDHSB7W","created_at":"2026-07-05T10:56:21.004049+00:00"},{"alias_kind":"pith_short_8","alias_value":"3NL73BUM","created_at":"2026-07-05T10:56:21.004049+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16946","citing_title":"NY Real Estate Racial Equity Analysis via Applied Machine Learning","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3NL73BUM2MDHSB7WY4QYKOEC4T","json":"https://pith.science/pith/3NL73BUM2MDHSB7WY4QYKOEC4T.json","graph_json":"https://pith.science/api/pith-number/3NL73BUM2MDHSB7WY4QYKOEC4T/graph.json","events_json":"https://pith.science/api/pith-number/3NL73BUM2MDHSB7WY4QYKOEC4T/events.json","paper":"https://pith.science/paper/3NL73BUM"},"agent_actions":{"view_html":"https://pith.science/pith/3NL73BUM2MDHSB7WY4QYKOEC4T","download_json":"https://pith.science/pith/3NL73BUM2MDHSB7WY4QYKOEC4T.json","view_paper":"https://pith.science/paper/3NL73BUM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.21259&json=true","fetch_graph":"https://pith.science/api/pith-number/3NL73BUM2MDHSB7WY4QYKOEC4T/graph.json","fetch_events":"https://pith.science/api/pith-number/3NL73BUM2MDHSB7WY4QYKOEC4T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3NL73BUM2MDHSB7WY4QYKOEC4T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3NL73BUM2MDHSB7WY4QYKOEC4T/action/storage_attestation","attest_author":"https://pith.science/pith/3NL73BUM2MDHSB7WY4QYKOEC4T/action/author_attestation","sign_citation":"https://pith.science/pith/3NL73BUM2MDHSB7WY4QYKOEC4T/action/citation_signature","submit_replication":"https://pith.science/pith/3NL73BUM2MDHSB7WY4QYKOEC4T/action/replication_record"}},"created_at":"2026-07-05T10:56:21.004049+00:00","updated_at":"2026-07-05T10:56:21.004049+00:00"}