{"id":"W2345513604","doi":"","title":"Ethnea -- an instance-based ethnicity classifier based on geo-coded author names in a large-scale bibliographic database","year":2016,"lang":"en","type":"article","venue":"","topic":"Names, Identity, and Discrimination Research","field":"Social Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Ethnic group; Computer science; Geocoding; Classifier (UML); Artificial intelligence; Outlier; Natural language processing; Geography; Cartography; Sociology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003904349,0.0001909058,0.0002428977,0.003408084,0.0006056837,0.0002361897,0.0006105692,0.000235673,0.003219939],"category_scores_gemma":[0.001032456,0.0001396875,0.0001385339,0.005240114,0.000613439,0.000900733,0.00006400983,0.0003089646,0.0001005989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001632456,"about_ca_system_score_gemma":0.0006559407,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.008934512,"about_ca_topic_score_gemma":0.2627905,"domain_scores_codex":[0.9956627,0.001125001,0.0003533254,0.0006161267,0.001440424,0.0008023675],"domain_scores_gemma":[0.9980991,0.0004717142,0.00009478382,0.0005876105,0.0003109983,0.0004357392],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006946921,0.004025605,0.8837173,0.0001253938,0.00001605574,0.00007015705,0.00337913,0.00004358663,0.003676088,0.06384798,0.02208359,0.01832042],"study_design_scores_gemma":[0.01115843,0.0005989546,0.8418947,0.0004604324,0.0000480011,2.60804e-7,0.01217746,0.02307089,0.003289248,0.009619546,0.09618783,0.001494241],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8509175,0.0001232298,0.02647856,0.02230413,0.0005665172,0.001212152,0.0003868988,0.0004332906,0.09757774],"genre_scores_gemma":[0.9925664,0.0001339706,0.001051267,0.001472651,0.00009508613,0.00008700463,0.00003758281,0.00002062254,0.004535427],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.253856,"threshold_uncertainty_score":0.9976913,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08743242770217008,"score_gpt":0.3972854283511724,"score_spread":0.3098530006490023,"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."}}