{"id":"W2831165","doi":"10.55016/ojs/ajer.v55i4.55342","title":"The Consequential Validity of Student Ratings: What do Instructors Really Think?","year":2010,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Psychology; Strengths and weaknesses; Applied psychology; Accountability; Medical education; Sample (material); Perception; Social psychology; Higher education; Medicine","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":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02160283,0.00007335619,0.0001433874,0.0001836539,0.001454498,0.0007228601,0.001121677,0.00008539335,0.004752058],"category_scores_gemma":[0.1022299,0.00005213204,0.000101825,0.0003278923,0.001151662,0.001390233,0.00009418355,0.001151031,0.00005478975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000147094,"about_ca_system_score_gemma":0.005525396,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004528853,"about_ca_topic_score_gemma":0.01882707,"domain_scores_codex":[0.9935238,0.002668835,0.0006276137,0.0001307304,0.002758949,0.0002900788],"domain_scores_gemma":[0.9278778,0.06831647,0.0007714833,0.0002387717,0.002597756,0.0001977476],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000158855,0.000652384,0.2062445,0.00001839975,0.0002070395,7.635997e-7,0.07862072,0.00001745935,0.004133798,0.6767577,0.02562389,0.007564494],"study_design_scores_gemma":[0.001182754,0.0006651625,0.3275737,0.0003739597,0.0001288259,0.0000869968,0.1777246,0.00001919038,0.001401772,0.06077432,0.4297108,0.0003578559],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.876415,0.0002792014,7.300212e-7,0.0990467,0.002254093,0.0001670721,5.609203e-7,5.737463e-7,0.02183605],"genre_scores_gemma":[0.9914168,0.001216781,0.0004761797,0.00007292037,0.001111926,0.000005276633,0.000001296167,0.00000813331,0.005690704],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6159834,"threshold_uncertainty_score":0.9998454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2472252017628741,"score_gpt":0.5587972615610401,"score_spread":0.311572059798166,"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."}}