{"id":"W2092297292","doi":"10.1007/s11251-007-9045-2","title":"Instructors’ perspectives on the utility of student ratings of instruction","year":2007,"lang":"en","type":"article","venue":"Instructional Science","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":101,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Summative assessment; Educational psychology; Psychology; Sample (material); Medical education; Mathematics education; Student engagement; Pedagogy; Formative assessment; Medicine","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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.009281762,0.00008443961,0.0001182976,0.0002198593,0.001059795,0.00004725163,0.0006493166,0.00004942711,0.0004410336],"category_scores_gemma":[0.003444261,0.00006392066,0.00006050958,0.001199134,0.004324762,0.0007847181,0.00007611139,0.0002181383,0.000004684799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001908445,"about_ca_system_score_gemma":0.0005737682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001253835,"about_ca_topic_score_gemma":0.0002726768,"domain_scores_codex":[0.9966584,0.0002257477,0.0003877252,0.0002833405,0.002218169,0.00022664],"domain_scores_gemma":[0.9977502,0.000680753,0.0005345705,0.000233504,0.0007239553,0.00007701505],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00004589383,0.0001122877,0.06027695,0.000004320618,0.00001254456,2.031696e-7,0.03396669,0.00002457038,0.006642248,0.8695354,0.0000314309,0.02934747],"study_design_scores_gemma":[0.0001849716,0.00007175271,0.8952121,0.00002135045,0.000008046633,0.000004579178,0.08875822,0.00005342584,0.007902384,0.006144315,0.00155225,0.00008662491],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9483241,0.00001479417,0.0001286442,0.001462936,0.0007778218,0.0001905274,0.000003130666,0.00002559471,0.04907244],"genre_scores_gemma":[0.9966211,0.00001170479,0.003126984,0.00003256875,0.0001624036,0.000002621209,2.648605e-7,0.000003280419,0.00003908096],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8633911,"threshold_uncertainty_score":0.9983849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1186419514415662,"score_gpt":0.460984290839059,"score_spread":0.3423423393974928,"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."}}