{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004352431,0.0006577693,0.0005207426,0.007760543,0.001816963,0.002902396,0.001184324,0.00121073,0.007295716],"category_scores_gemma":[0.01630493,0.0006376219,0.0007704441,0.006224692,0.001620161,0.004176296,0.001915098,0.001276989,0.003829063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007075432,"about_ca_system_score_gemma":0.0018139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003281021,"about_ca_topic_score_gemma":0.006762746,"domain_scores_codex":[0.995995,0.001702306,0.0004133555,0.0008608227,0.0008954427,0.0001329815],"domain_scores_gemma":[0.9926662,0.00399135,0.0007898815,0.001009509,0.001372469,0.0001706262],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002187889,0.0001493909,0.01564845,0.0003483112,0.0001097114,0.0002607581,0.003579481,0.001308966,0.008837441,0.06878839,0.0222056,0.8785447],"study_design_scores_gemma":[0.0002654582,0.0003008242,0.04299284,0.000605257,0.000346235,0.00492447,0.01028706,0.1652566,0.03793709,0.2317212,0.5045703,0.000792629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009025994,0.0002961565,0.9794244,0.0009872072,0.0001629433,0.0003246649,0.001563785,0.001216937,0.006997911],"genre_scores_gemma":[0.03900772,0.0001783003,0.9534016,0.0001546241,0.00008612517,0.0004787626,0.0009909576,0.0001246098,0.005577285],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007760543,"threshold_uncertainty_score":0.02440661,"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."}}