{"id":"W7045900711","doi":"","title":"Assessing the multilevel validity of program-level inferences based on aggregate student perceptions about their general learning","year":2014,"lang":"en","type":"other","venue":"cIRcle (University of British Columbia)","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Multilevel model; Perception; Normative; Regression analysis; Categorical variable; Data collection","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00223363,0.00009359263,0.0003792222,0.00011082,0.001237049,0.0004530139,0.0008467145,0.0002759517,0.001439892],"category_scores_gemma":[0.0005706619,0.0002107873,0.0001986346,0.0002215331,0.001250393,0.0002958747,0.0001227154,0.0005048597,0.00002886208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001156223,"about_ca_system_score_gemma":0.0004458021,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.3441963,"about_ca_topic_score_gemma":0.6017096,"domain_scores_codex":[0.9962857,0.001915845,0.0001881252,0.0004073436,0.0009302856,0.0002726916],"domain_scores_gemma":[0.9977109,0.0005419285,0.001015938,0.0003199523,0.0003170564,0.00009424589],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000002848664,0.0003992353,0.04269012,0.00007137439,0.00008550361,0.000004240841,0.00488857,0.0001319707,0.0000127589,0.00001426854,0.009408131,0.942291],"study_design_scores_gemma":[0.0004000654,0.0001271761,0.9509785,0.0008239031,0.0001047433,7.324767e-7,0.01169697,0.001972417,1.057508e-7,0.00004361128,0.03362435,0.0002274015],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.768065,0.00008434479,0.003299194,0.0006557589,0.0005773405,0.001192802,0.0001926612,0.0003764439,0.2255565],"genre_scores_gemma":[0.938431,0.0001786815,0.003130873,0.00004277879,0.0002089668,0.000002121739,0.00003236213,0.00006007338,0.05791316],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9420636,"threshold_uncertainty_score":0.9994729,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1149853243368761,"score_gpt":0.3688247159502342,"score_spread":0.2538393916133581,"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."}}