{"id":"W2705397363","doi":"10.1080/02602938.2017.1343799","title":"Comparing student, instructor, classroom and institutional data to evaluate a seven-year department-wide science education initiative","year":2017,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Helpfulness; Enthusiasm; Graduation (instrument); Psychology; Medical education; Perception; Class (philosophy); Class size; Higher education; Mathematics education; Medicine; Social psychology; Computer science; 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":[],"consensus_categories":[],"category_scores_codex":[0.01458516,0.000298452,0.0004975164,0.003463776,0.0006277595,0.001185813,0.0007804116,0.0005234161,0.0009860703],"category_scores_gemma":[0.03780109,0.0001720955,0.0005967637,0.002778858,0.000467703,0.0009979188,0.001450513,0.0007782396,0.0003140362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001116541,"about_ca_system_score_gemma":0.001101797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002919924,"about_ca_topic_score_gemma":0.007628412,"domain_scores_codex":[0.9891339,0.004601044,0.0009858941,0.0007496543,0.004026756,0.0005027803],"domain_scores_gemma":[0.9291316,0.03390191,0.01005639,0.004543383,0.018225,0.004141723],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007688439,0.002317126,0.9590907,0.0001171591,0.0001895083,0.00005300112,0.003272949,0.0003901128,0.001764959,0.000141251,0.0005275604,0.0313669],"study_design_scores_gemma":[0.00004979512,0.003178701,0.988644,0.00002443648,0.00006499713,0.00004650951,0.002943577,0.0008271185,0.002471204,0.00004434038,0.001683199,0.0000220497],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9984003,0.00003190025,0.0003703086,0.00001649496,0.000005311033,0.00009458361,0.0003838473,0.00001584569,0.0006814463],"genre_scores_gemma":[0.9956053,0.00002510568,0.001592179,0.00003181162,0.000008206742,0.0002576605,0.002106697,0.0000124535,0.0003606687],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01458516,"threshold_uncertainty_score":0.07713467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4177558026403005,"score_gpt":0.5790085889658491,"score_spread":0.1612527863255485,"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."}}