{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3T63CMBXPQCWIUAAJMCIRQXVDQ","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":"3718d6759a6970995abfc0fecb0c6b7bf99b0522fbb09a290d968b9fede67a7f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-07T16:30:40Z","title_canon_sha256":"dbe321e2523398dc460829a5f7997c5ec1c639eff93cb5a2cf5afad90b0a6375"},"schema_version":"1.0","source":{"id":"2112.03807","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.03807","created_at":"2026-07-05T03:39:19Z"},{"alias_kind":"arxiv_version","alias_value":"2112.03807v3","created_at":"2026-07-05T03:39:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03807","created_at":"2026-07-05T03:39:19Z"},{"alias_kind":"pith_short_12","alias_value":"3T63CMBXPQCW","created_at":"2026-07-05T03:39:19Z"},{"alias_kind":"pith_short_16","alias_value":"3T63CMBXPQCWIUAA","created_at":"2026-07-05T03:39:19Z"},{"alias_kind":"pith_short_8","alias_value":"3T63CMBX","created_at":"2026-07-05T03:39:19Z"}],"graph_snapshots":[{"event_id":"sha256:eda175b32881904e84e7c4c9ba24aee299e92ab391ab40e57e5cab7959cb2c25","target":"graph","created_at":"2026-07-05T03:39:19Z","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/2112.03807/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Prasanna Parasurama","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-07T16:30:40Z","title":"raceBERT -- A Transformer-based Model for Predicting Race and Ethnicity from Names"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03807","kind":"arxiv","version":3},"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":"sha256:8f9f06ed987cc42904ecd0c7fb65d3c91a4e0a2bc5b7dc8799593daa8974be52","target":"record","created_at":"2026-07-05T03:39:19Z","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":"3718d6759a6970995abfc0fecb0c6b7bf99b0522fbb09a290d968b9fede67a7f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-07T16:30:40Z","title_canon_sha256":"dbe321e2523398dc460829a5f7997c5ec1c639eff93cb5a2cf5afad90b0a6375"},"schema_version":"1.0","source":{"id":"2112.03807","kind":"arxiv","version":3}},"canonical_sha256":"dcfdb130377c056450004b0488c2f51c065aa3626fd3209f8a02f24cf77dea56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcfdb130377c056450004b0488c2f51c065aa3626fd3209f8a02f24cf77dea56","first_computed_at":"2026-07-05T03:39:19.738989Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:39:19.738989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wvxlhz2l+fFbrb8wcE9MfK/IsJr8bE3U3TxtLNcNhyLKoN9Zb2LY/+W4xKAipJu2OSfATgOHxKohDVLnOSJhAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:39:19.739369Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.03807","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f9f06ed987cc42904ecd0c7fb65d3c91a4e0a2bc5b7dc8799593daa8974be52","sha256:eda175b32881904e84e7c4c9ba24aee299e92ab391ab40e57e5cab7959cb2c25"],"state_sha256":"f8fc610871c2334d10acc930fa78d59bcc54a84f289bc687f6f0d1eada1cb3cf"}