{"id":"W39064896","doi":"10.55016/ojs/ajer.v55i1.55272","title":"Peer Observation Reports and Student Evaluations of Teaching: Who Are the Experts?","year":2009,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Psychology; Mathematics education; Educational research; Peer evaluation; Higher education; Pedagogy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02092521,0.000263935,0.0004988018,0.001711896,0.0006071832,0.001607412,0.0004837479,0.0005416772,0.001113362],"category_scores_gemma":[0.1362934,0.0001968403,0.0002591588,0.0007224852,0.00131563,0.001931614,0.001322002,0.0009160762,0.0002101885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005519197,"about_ca_system_score_gemma":0.0007725309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001452399,"about_ca_topic_score_gemma":0.002126379,"domain_scores_codex":[0.9627274,0.02563488,0.001878578,0.0009696758,0.008060282,0.0007291274],"domain_scores_gemma":[0.7655109,0.1616135,0.04367085,0.005419025,0.02038949,0.003396253],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000888972,0.000467745,0.7162044,0.0006154423,0.0002876832,0.0002833153,0.1120684,0.0005030097,0.003594199,0.001303293,0.001226666,0.1625569],"study_design_scores_gemma":[0.0001009928,0.002688096,0.8081041,0.0008380191,0.0002994675,0.001357007,0.1680249,0.00297039,0.005371008,0.002760552,0.00727763,0.0002078979],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9906824,0.0006414997,0.003433186,0.0004452124,0.00003727913,0.00006522867,0.00003759639,0.00002128858,0.004636291],"genre_scores_gemma":[0.9980953,0.0002275708,0.001051812,0.00004112194,0.00003974448,0.00004069568,0.0000247246,0.000004136898,0.0004748196],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9790748,"threshold_uncertainty_score":0.1106644,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3669533084308778,"score_gpt":0.6016822682881954,"score_spread":0.2347289598573176,"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."}}