{"id":"W2160128373","doi":"10.1093/pan/mpu038","title":"What's in a Name? A Method for Extracting Information about Ethnicity from Names","year":2015,"lang":"en","type":"article","venue":"Political Analysis","topic":"Names, Identity, and Discrimination Research","field":"Social Sciences","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; Harvard University; National Science Foundation","keywords":"Ethnic group; Geocoding; Context (archaeology); Identity (music); Linkage (software); Ethnic composition; Group (periodic table); Computer science; Linguistics; Genealogy; Geography; Sociology; History; Anthropology; Cartography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002492795,0.00007400619,0.000238817,0.0004356036,0.0002051961,0.0006253138,0.0002046055,0.0001077161,0.0002697221],"category_scores_gemma":[0.007011032,0.00007116021,0.0001894735,0.0009446801,0.0001352386,0.001926959,0.00004833443,0.0001404678,0.00004218473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002965031,"about_ca_system_score_gemma":0.0002602933,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1062086,"about_ca_topic_score_gemma":0.04479311,"domain_scores_codex":[0.9979283,0.0004356622,0.0003310225,0.0001629852,0.0006569957,0.0004850428],"domain_scores_gemma":[0.9979414,0.0010372,0.00007505184,0.0001294052,0.000446357,0.0003705619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005716046,0.0002274716,0.1080869,0.00003989193,0.0003297193,0.000003352865,0.03621436,0.0001511952,0.000008269179,0.8175375,0.0008180166,0.03652617],"study_design_scores_gemma":[0.001389331,0.00005487779,0.1308644,0.0000436671,0.001121726,2.699708e-7,0.254767,0.07796028,0.0001261533,0.5040151,0.02915523,0.0005019326],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4298301,0.0009755181,0.4294404,0.05353296,0.0007167258,0.001016587,0.0001573138,0.0001878198,0.08414265],"genre_scores_gemma":[0.9926814,0.00003678809,0.005954633,0.0004940347,0.0001762209,0.00004747663,0.00005847108,0.000003534591,0.0005474491],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5628513,"threshold_uncertainty_score":0.9726369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1094670874781619,"score_gpt":0.4752007986900707,"score_spread":0.3657337112119088,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}