{"id":"W1887917947","doi":"10.47678/cjhe.v35i2.183500","title":"The Utility of Student Ratings of Instruction for Students, Faculty, and Administrators: A \"Consequential Validity\" Study","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Higher Education","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":81,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Psychology; Higher education; Medical education; Quality (philosophy); Merit pay; Mathematics education; Medicine; Incentive; Political science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003180215,0.00005891063,0.0001256845,0.0001011227,0.000444814,0.000123401,0.000275377,0.00003873372,0.0000766037],"category_scores_gemma":[0.0005387327,0.00004881268,0.00004618747,0.0001072124,0.0002028318,0.0003707021,0.000008054753,0.00010598,3.691484e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001752276,"about_ca_system_score_gemma":0.00379987,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.009901532,"about_ca_topic_score_gemma":0.0659494,"domain_scores_codex":[0.998435,0.0004546995,0.0004638518,0.00008192131,0.0004468834,0.0001176313],"domain_scores_gemma":[0.9980097,0.0002385351,0.0008402576,0.00009274229,0.0006539854,0.0001647489],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005422783,0.000425043,0.9243668,0.00001956915,0.0001288015,3.872426e-7,0.04459154,0.000003810886,0.00005333179,0.00600837,0.00898292,0.01536515],"study_design_scores_gemma":[0.0005272594,0.000315511,0.8145131,0.00002823247,0.0001249897,0.000003512304,0.03521271,0.000001335984,0.0001229509,0.0007979854,0.1482909,0.00006146445],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9907474,0.000376071,0.00001204088,0.007121343,0.001048696,0.0003805922,0.000006999864,0.00000192367,0.0003049358],"genre_scores_gemma":[0.9984832,0.00001488972,0.0004962748,0.00004518142,0.0003854725,0.00000854568,0.000001501575,0.000004043276,0.0005608647],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.139308,"threshold_uncertainty_score":0.9966916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1943694772100051,"score_gpt":0.52518544487511,"score_spread":0.3308159676651049,"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."}}