{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.001748745,0.001331746,0.001285056,0.01583463,0.0009425176,0.002443616,0.001841341,0.0009351493,0.004623407],"category_scores_gemma":[0.006123332,0.0003217048,0.001118774,0.008592205,0.0002963041,0.003691822,0.00205553,0.000982768,0.006242658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009541316,"about_ca_system_score_gemma":0.001685654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005488934,"about_ca_topic_score_gemma":0.0167337,"domain_scores_codex":[0.9979044,0.0002266514,0.0002831649,0.0006515918,0.0007993766,0.0001348057],"domain_scores_gemma":[0.9974744,0.0007251124,0.0004530472,0.0006214992,0.0004951103,0.0002308261],"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":[0.000702859,0.0007947709,0.1192413,0.002305067,0.0007291242,0.0009630913,0.0006344802,0.008363174,0.01035081,0.004936657,0.2056946,0.645284],"study_design_scores_gemma":[0.0002828002,0.0006305043,0.1119483,0.0007799218,0.0006158582,0.004292154,0.002685772,0.4797261,0.03320244,0.02237018,0.3431968,0.0002692686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.2067141,0.006865416,0.1836777,0.002835097,0.001015633,0.001641585,0.4726377,0.0885433,0.03606952],"genre_scores_gemma":[0.2621502,0.001458432,0.3946234,0.0005274275,0.0003621551,0.0006613193,0.3319696,0.0008722129,0.007375216],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9841654,"threshold_uncertainty_score":0.01546687,"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."}}