{"id":"W1987169263","doi":"10.1002/tl.38","title":"Using Student Outcomes to Evaluate Teaching: A Cautious Exploration","year":2001,"lang":"en","type":"article","venue":"New Directions for Teaching and Learning","topic":"Teacher Education and Leadership Studies","field":"Social Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Mathematics education; Teaching method; Psychology; Higher education; Pedagogy; Medical education; Medicine; 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"],"consensus_categories":[],"category_scores_codex":[0.002838403,0.0001301658,0.0001698505,0.0001943786,0.00485745,0.0002136195,0.00008830059,0.0000600387,0.00002428091],"category_scores_gemma":[0.00272738,0.0001294378,0.00007158609,0.0001512519,0.00005487182,0.0002972398,0.00002401107,0.0006450326,0.00001062662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002073064,"about_ca_system_score_gemma":0.0001056892,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009775843,"about_ca_topic_score_gemma":0.002256391,"domain_scores_codex":[0.9979592,0.001024853,0.0001842546,0.0002736359,0.000247105,0.0003109659],"domain_scores_gemma":[0.9991726,0.0004184303,0.00007923402,0.00009077651,0.0000550037,0.000184015],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001080709,0.00009588971,0.06592689,0.000004568393,0.00005626401,3.616737e-7,0.7735007,0.001418032,0.00008262248,0.003021608,0.001292632,0.1545896],"study_design_scores_gemma":[0.000295329,0.00005768089,0.01369747,0.00002764203,0.00005815318,0.000002147388,0.424426,0.0003172111,0.000001415102,0.0002183204,0.5607218,0.000176807],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8815997,0.0003203876,0.04863257,0.05546856,0.001104178,0.0006177995,7.55264e-7,0.0005515,0.01170452],"genre_scores_gemma":[0.9637519,0.00003162722,0.008465515,0.0003642185,0.0005736483,0.00005277995,0.000003054997,0.0000197029,0.02673759],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5594292,"threshold_uncertainty_score":0.9968181,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2412671041432465,"score_gpt":0.4862596402215878,"score_spread":0.2449925360783413,"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."}}