{"id":"W7132913581","doi":"","title":"A Computerized Dynamic Assessment Approach to Evaluate Critical Thinking Among Psychology Undergraduates","year":2024,"lang":"","type":"dissertation","venue":"TSpace","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Office of International Science and Engineering; University of Toronto","keywords":"Critical thinking; Test (biology); Reading (process); Certainty; Dynamic assessment; Defining Issues Test; Critical reading; Criticism","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002654107,0.0006782338,0.0004796151,0.004202647,0.0005143172,0.001352917,0.0006114877,0.000570773,0.003260541],"category_scores_gemma":[0.014978,0.0002979585,0.0004500023,0.001645393,0.0005842925,0.001147952,0.00102258,0.001045668,0.0007159478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008667769,"about_ca_system_score_gemma":0.001511349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001135377,"about_ca_topic_score_gemma":0.00265982,"domain_scores_codex":[0.9978276,0.0005637921,0.0003845374,0.0004253032,0.0006619875,0.0001367758],"domain_scores_gemma":[0.9885231,0.004683183,0.002083337,0.0006652012,0.003183561,0.0008615626],"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":[0.001412834,0.00543979,0.3372354,0.0003497344,0.0001055452,0.0002254587,0.005717235,0.001858753,0.03237808,0.001985168,0.003418776,0.6098733],"study_design_scores_gemma":[0.0004402409,0.01119217,0.9150327,0.0002424853,0.0001251475,0.001130225,0.004811639,0.02175311,0.02996844,0.004262327,0.01083609,0.0002055437],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9732222,0.0001750679,0.01579081,0.0001766925,0.000050556,0.002409521,0.0005292838,0.0003466549,0.007299064],"genre_scores_gemma":[0.9247506,0.0002554358,0.06768352,0.000141691,0.00003445825,0.003002759,0.0005526075,0.00003240667,0.003546539],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004202647,"threshold_uncertainty_score":0.01403642,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07441841410009245,"score_gpt":0.5315931168702145,"score_spread":0.4571747027701221,"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."}}