{"id":"W2743358023","doi":"10.18260/1-2--28731","title":"PANEL: Gender bias in student evaluations of teaching","year":2018,"lang":"en","type":"article","venue":"","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Set (abstract data type); Gender bias; Promotion (chess); Affect (linguistics); Class (philosophy); Psychology; Gender gap; Institution; Medical education; Social psychology; Computer science; Medicine; Demographic economics; Political science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008374527,0.0003497856,0.0003512768,0.001057918,0.002177899,0.001425199,0.0007611437,0.001998788,0.0349732],"category_scores_gemma":[0.01965965,0.000203087,0.0004413358,0.001064065,0.000534209,0.0009617726,0.001752609,0.001605042,0.007284472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00121781,"about_ca_system_score_gemma":0.0007406842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003316581,"about_ca_topic_score_gemma":0.005863334,"domain_scores_codex":[0.9974446,0.0008275673,0.0001757485,0.0003853941,0.000919927,0.0002466992],"domain_scores_gemma":[0.9742597,0.01056296,0.001355058,0.002096987,0.01033319,0.00139218],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0009234175,0.0002204597,0.04193566,0.0003714892,0.00007716784,0.0002329072,0.002545047,0.0002194307,0.009236737,0.002685329,0.8578824,0.08367011],"study_design_scores_gemma":[0.0001687732,0.0006966316,0.4016534,0.001769417,0.0001266959,0.0005037797,0.007358222,0.002331473,0.02598191,0.004557216,0.5547148,0.0001376816],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3554295,0.006424559,0.02074295,0.208589,0.03393916,0.00279674,0.03851086,0.001014921,0.3325523],"genre_scores_gemma":[0.7927273,0.002344759,0.005118766,0.03747183,0.006692215,0.001887798,0.01021503,0.0003345589,0.1432077],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9916255,"threshold_uncertainty_score":0.116997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5901902343937442,"score_gpt":0.5874192468082498,"score_spread":0.002770987585494433,"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."}}