{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01362191,0.0002003535,0.0002162913,0.0005250918,0.002976442,0.001443509,0.001446197,0.00008692776,0.0004978259],"category_scores_gemma":[0.004108587,0.0002267803,0.00002348381,0.0004938287,0.0005588583,0.006167211,0.0005564046,0.000290283,0.00006660615],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002460761,"about_ca_system_score_gemma":0.01963882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002171697,"about_ca_topic_score_gemma":0.002786822,"domain_scores_codex":[0.9942011,0.001225094,0.0005676752,0.0008724444,0.002764853,0.0003688574],"domain_scores_gemma":[0.9962173,0.0003595054,0.0007728167,0.001142102,0.00126001,0.0002483256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001337296,0.0005882845,0.8821089,0.00001299239,0.00002420461,1.416331e-7,0.006563823,0.0002291555,0.0001009342,0.08731863,0.001239613,0.02179993],"study_design_scores_gemma":[0.0006759099,0.00003888743,0.9670017,0.000133687,0.00009881621,5.613076e-7,0.006686409,0.001479652,0.00001106529,0.004942663,0.01868727,0.000243383],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9052697,0.0001016619,0.00009036717,0.02006689,0.004199828,0.001747912,0.000009687499,0.00004482176,0.06846917],"genre_scores_gemma":[0.9865355,0.00005248761,0.01089056,0.0007261343,0.0004842406,0.0004481065,0.0002244331,0.0000147901,0.000623686],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08489279,"threshold_uncertainty_score":0.9995931,"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."}}