{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3NL73BUM2MDHSB7WY4QYKOEC4T","short_pith_number":"pith:3NL73BUM","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"},"canonical_sha256":"db57fd868cd3067907f6c721853882e4e064b7d855a24b33fd347e29972f880f","source":{"kind":"arxiv","id":"2504.21259","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.21259","created_at":"2026-07-05T10:56:21Z"},{"alias_kind":"arxiv_version","alias_value":"2504.21259v1","created_at":"2026-07-05T10:56:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21259","created_at":"2026-07-05T10:56:21Z"},{"alias_kind":"pith_short_12","alias_value":"3NL73BUM2MDH","created_at":"2026-07-05T10:56:21Z"},{"alias_kind":"pith_short_16","alias_value":"3NL73BUM2MDHSB7W","created_at":"2026-07-05T10:56:21Z"},{"alias_kind":"pith_short_8","alias_value":"3NL73BUM","created_at":"2026-07-05T10:56:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3NL73BUM2MDHSB7WY4QYKOEC4T","target":"record","payload":{"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"},"canonical_sha256":"db57fd868cd3067907f6c721853882e4e064b7d855a24b33fd347e29972f880f","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"},"source_kind":"arxiv","source_id":"2504.21259","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:56:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E8BFeVV63sbfTQnQEpyl0mBYLVPbENoO11ehbtWqztKZB8rFv0rix4vbDYyQQkMHA1iPYZBGYi6lIWZOvk4ADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T19:15:42.402443Z"},"content_sha256":"94d68c763e08d4dfa4468391ec8d0f0835fb79cd8375f2a573d57c3a3f7d3698","schema_version":"1.0","event_id":"sha256:94d68c763e08d4dfa4468391ec8d0f0835fb79cd8375f2a573d57c3a3f7d3698"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3NL73BUM2MDHSB7WY4QYKOEC4T","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:56:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x59dHzmS4mp+Kg+Rp+tNjbU/C98mH4N0YedFpW2c3dK/8/5FJYg5FfQWpASxgO3UIXOJn87Oa7iqVCoahnltAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T19:15:42.402971Z"},"content_sha256":"81671f75bf5c5aabb40bb17cf547a22a85340c93f6b0d7a62ee20e0a82114bad","schema_version":"1.0","event_id":"sha256:81671f75bf5c5aabb40bb17cf547a22a85340c93f6b0d7a62ee20e0a82114bad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3NL73BUM2MDHSB7WY4QYKOEC4T/bundle.json","state_url":"https://pith.science/pith/3NL73BUM2MDHSB7WY4QYKOEC4T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3NL73BUM2MDHSB7WY4QYKOEC4T/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T19:15:42Z","links":{"resolver":"https://pith.science/pith/3NL73BUM2MDHSB7WY4QYKOEC4T","bundle":"https://pith.science/pith/3NL73BUM2MDHSB7WY4QYKOEC4T/bundle.json","state":"https://pith.science/pith/3NL73BUM2MDHSB7WY4QYKOEC4T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3NL73BUM2MDHSB7WY4QYKOEC4T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3NL73BUM2MDHSB7WY4QYKOEC4T","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":"6b738b66a96e2bdad3fd414c159aec6549bdb56a6caf08d204569f313c32617f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-04-30T02:20:08Z","title_canon_sha256":"96caf26601ee23f56aa11ee0dac73931da7aae2465eac5febf1a47b524d41129"},"schema_version":"1.0","source":{"id":"2504.21259","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.21259","created_at":"2026-07-05T10:56:21Z"},{"alias_kind":"arxiv_version","alias_value":"2504.21259v1","created_at":"2026-07-05T10:56:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21259","created_at":"2026-07-05T10:56:21Z"},{"alias_kind":"pith_short_12","alias_value":"3NL73BUM2MDH","created_at":"2026-07-05T10:56:21Z"},{"alias_kind":"pith_short_16","alias_value":"3NL73BUM2MDHSB7W","created_at":"2026-07-05T10:56:21Z"},{"alias_kind":"pith_short_8","alias_value":"3NL73BUM","created_at":"2026-07-05T10:56:21Z"}],"graph_snapshots":[{"event_id":"sha256:81671f75bf5c5aabb40bb17cf547a22a85340c93f6b0d7a62ee20e0a82114bad","target":"graph","created_at":"2026-07-05T10:56:21Z","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/2504.21259/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"A. Pastor, S. Chalavadi, T. Leitch","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-04-30T02:20:08Z","title":"LSTM+Geo with xgBoost Filtering: A Novel Approach for Race and Ethnicity Imputation with Reduced Bias"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21259","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":"sha256:94d68c763e08d4dfa4468391ec8d0f0835fb79cd8375f2a573d57c3a3f7d3698","target":"record","created_at":"2026-07-05T10:56:21Z","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":"6b738b66a96e2bdad3fd414c159aec6549bdb56a6caf08d204569f313c32617f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-04-30T02:20:08Z","title_canon_sha256":"96caf26601ee23f56aa11ee0dac73931da7aae2465eac5febf1a47b524d41129"},"schema_version":"1.0","source":{"id":"2504.21259","kind":"arxiv","version":1}},"canonical_sha256":"db57fd868cd3067907f6c721853882e4e064b7d855a24b33fd347e29972f880f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db57fd868cd3067907f6c721853882e4e064b7d855a24b33fd347e29972f880f","first_computed_at":"2026-07-05T10:56:21.003989Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:56:21.003989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IbhUj3ww7P3Rv8g1rZnYDVkeqk/3NvAppiurBJCJmD1ymNpljUZU+ZIiBPe+xm5H0CjnqjTZe/8dNGsf4dLzDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:56:21.004486Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.21259","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94d68c763e08d4dfa4468391ec8d0f0835fb79cd8375f2a573d57c3a3f7d3698","sha256:81671f75bf5c5aabb40bb17cf547a22a85340c93f6b0d7a62ee20e0a82114bad"],"state_sha256":"35ed016ab762090ca4c2cd85e1d6e1e417a1c980dcd4b6049b7fa70e3d001926"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HHBVvUkb2rwKDH+0mO/qUXJqqCv9fg/3Z6VsOJFBVacM3HqhLeBq/seWsitqSr7BQABbMoF6HOUwqwp70wTIAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T19:15:42.408078Z","bundle_sha256":"2222dae690ad455f45b986b388f7ada853443d70fbba50935cb2d062e73c7f39"}}