{"id":"W3110605707","doi":"10.14293/s2199-1006.1.sor-.ppfxxc8.v1","title":"Gender bias in student evaluation of teaching or a mirage?","year":2020,"lang":"en","type":"article","venue":"","topic":"Teacher Professional Development and Motivation","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mount Royal University","funders":"","keywords":"Outlier; Psychology; Gender bias; Statistics; Set (abstract data type); Social psychology; Demography; Mathematics; Computer science; Sociology","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":[0.02079608,0.0003079567,0.0005940886,0.001229772,0.0006767139,0.001695097,0.0006202775,0.0005397612,0.004969672],"category_scores_gemma":[0.1004339,0.0001731418,0.0005203307,0.0009207526,0.001440698,0.001464195,0.001456125,0.000793683,0.001008103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007852038,"about_ca_system_score_gemma":0.0004255408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001840285,"about_ca_topic_score_gemma":0.002295263,"domain_scores_codex":[0.9798746,0.009470226,0.00174485,0.001728498,0.006220883,0.0009610928],"domain_scores_gemma":[0.9323262,0.03349089,0.0163523,0.005496041,0.01041309,0.001921437],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001660901,0.000214915,0.8431392,0.0003902359,0.0003433211,0.0002674831,0.03059004,0.0001227722,0.002885105,0.002307361,0.005446633,0.1126321],"study_design_scores_gemma":[0.00006267222,0.0007171785,0.9631178,0.0002819052,0.00009266187,0.0005196802,0.0213472,0.0007297198,0.002575241,0.002029479,0.008450348,0.00007606088],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9841183,0.0009255481,0.003290629,0.00191406,0.0004368862,0.00008810858,0.0003027351,0.00005742128,0.008866284],"genre_scores_gemma":[0.9981151,0.0001024085,0.0005362924,0.0004152049,0.00007776871,0.00005642626,0.00007924502,0.00001645085,0.0006010614],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9792039,"threshold_uncertainty_score":0.1099815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5104356819139351,"score_gpt":0.4930687479157235,"score_spread":0.01736693399821154,"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."}}