{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3T63CMBXPQCWIUAAJMCIRQXVDQ","short_pith_number":"pith:3T63CMBX","schema_version":"1.0","canonical_sha256":"dcfdb130377c056450004b0488c2f51c065aa3626fd3209f8a02f24cf77dea56","source":{"kind":"arxiv","id":"2112.03807","version":3},"attestation_state":"computed","paper":{"title":"raceBERT -- A Transformer-based Model for Predicting Race and Ethnicity from Names","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Prasanna Parasurama","submitted_at":"2021-12-07T16:30:40Z","abstract_excerpt":"This paper presents raceBERT -- a transformer-based model for predicting race and ethnicity from character sequences in names, and an accompanying python package. Using a transformer-based model trained on a U.S. Florida voter registration dataset, the model predicts the likelihood of a name belonging to 5 U.S. census race categories (White, Black, Hispanic, Asian & Pacific Islander, American Indian & Alaskan Native). I build on Sood and Laohaprapanon (2018) by replacing their LSTM model with transformer-based models (pre-trained BERT model, and a roBERTa model trained from scratch), and compa"},"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":"2112.03807","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-07T16:30:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dbe321e2523398dc460829a5f7997c5ec1c639eff93cb5a2cf5afad90b0a6375","abstract_canon_sha256":"3718d6759a6970995abfc0fecb0c6b7bf99b0522fbb09a290d968b9fede67a7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:39:19.739369Z","signature_b64":"wvxlhz2l+fFbrb8wcE9MfK/IsJr8bE3U3TxtLNcNhyLKoN9Zb2LY/+W4xKAipJu2OSfATgOHxKohDVLnOSJhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcfdb130377c056450004b0488c2f51c065aa3626fd3209f8a02f24cf77dea56","last_reissued_at":"2026-07-05T03:39:19.738989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:39:19.738989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"raceBERT -- A Transformer-based Model for Predicting Race and Ethnicity from Names","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Prasanna Parasurama","submitted_at":"2021-12-07T16:30:40Z","abstract_excerpt":"This paper presents raceBERT -- a transformer-based model for predicting race and ethnicity from character sequences in names, and an accompanying python package. Using a transformer-based model trained on a U.S. Florida voter registration dataset, the model predicts the likelihood of a name belonging to 5 U.S. census race categories (White, Black, Hispanic, Asian & Pacific Islander, American Indian & Alaskan Native). I build on Sood and Laohaprapanon (2018) by replacing their LSTM model with transformer-based models (pre-trained BERT model, and a roBERTa model trained from scratch), and compa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03807","kind":"arxiv","version":3},"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/2112.03807/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":"2112.03807","created_at":"2026-07-05T03:39:19.739043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.03807v3","created_at":"2026-07-05T03:39:19.739043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03807","created_at":"2026-07-05T03:39:19.739043+00:00"},{"alias_kind":"pith_short_12","alias_value":"3T63CMBXPQCW","created_at":"2026-07-05T03:39:19.739043+00:00"},{"alias_kind":"pith_short_16","alias_value":"3T63CMBXPQCWIUAA","created_at":"2026-07-05T03:39:19.739043+00:00"},{"alias_kind":"pith_short_8","alias_value":"3T63CMBX","created_at":"2026-07-05T03:39:19.739043+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22555","citing_title":"Using Embedding Models to Improve Probabilistic Race Prediction","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10401","citing_title":"NameBERT: Scaling Name-Based Nationality Classification with LLM-Augmented Open Academic Data","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3T63CMBXPQCWIUAAJMCIRQXVDQ","json":"https://pith.science/pith/3T63CMBXPQCWIUAAJMCIRQXVDQ.json","graph_json":"https://pith.science/api/pith-number/3T63CMBXPQCWIUAAJMCIRQXVDQ/graph.json","events_json":"https://pith.science/api/pith-number/3T63CMBXPQCWIUAAJMCIRQXVDQ/events.json","paper":"https://pith.science/paper/3T63CMBX"},"agent_actions":{"view_html":"https://pith.science/pith/3T63CMBXPQCWIUAAJMCIRQXVDQ","download_json":"https://pith.science/pith/3T63CMBXPQCWIUAAJMCIRQXVDQ.json","view_paper":"https://pith.science/paper/3T63CMBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.03807&json=true","fetch_graph":"https://pith.science/api/pith-number/3T63CMBXPQCWIUAAJMCIRQXVDQ/graph.json","fetch_events":"https://pith.science/api/pith-number/3T63CMBXPQCWIUAAJMCIRQXVDQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3T63CMBXPQCWIUAAJMCIRQXVDQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3T63CMBXPQCWIUAAJMCIRQXVDQ/action/storage_attestation","attest_author":"https://pith.science/pith/3T63CMBXPQCWIUAAJMCIRQXVDQ/action/author_attestation","sign_citation":"https://pith.science/pith/3T63CMBXPQCWIUAAJMCIRQXVDQ/action/citation_signature","submit_replication":"https://pith.science/pith/3T63CMBXPQCWIUAAJMCIRQXVDQ/action/replication_record"}},"created_at":"2026-07-05T03:39:19.739043+00:00","updated_at":"2026-07-05T03:39:19.739043+00:00"}