{"id":"W3110308428","doi":"","title":"Scaling Up: Value added Cognitive Assessment Redesign Network for the Development of Higher-Order Thinking","year":2019,"lang":"en","type":"article","venue":"","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Cognition; Value (mathematics); Order (exchange); Computer science; Scaling; Cognitive psychology; Psychology; Business; Mathematics; Machine learning","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001036588,0.0001651013,0.0002234911,0.00002982728,0.0002255702,0.00002869071,0.0002955692,0.0001147962,0.007903755],"category_scores_gemma":[0.00002212287,0.000100553,0.00008384863,0.0002254592,0.00004833626,0.00004773769,0.00005141483,0.0001755312,0.0001612136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003804005,"about_ca_system_score_gemma":0.0001342205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001925991,"about_ca_topic_score_gemma":0.000002784899,"domain_scores_codex":[0.9984003,0.000154916,0.0004508075,0.0003625063,0.0002833745,0.0003480663],"domain_scores_gemma":[0.9968435,0.002467023,0.0002020368,0.0002226818,0.0002130263,0.00005178474],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0007889755,0.001622585,0.06991498,0.00008979179,0.00224688,0.000001254337,0.0119247,0.0007617706,0.0004046636,0.7431155,0.04910199,0.1200269],"study_design_scores_gemma":[0.003324575,0.0003375456,0.8801532,0.0002264555,0.00014593,0.00000316227,0.01031305,0.0004635853,0.000290171,0.04507778,0.05910742,0.0005571624],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.301087,0.0005791107,0.3120841,0.003256191,0.01175862,0.003437395,0.00002583029,0.0001328722,0.3676388],"genre_scores_gemma":[0.873794,0.000003148753,0.09762914,0.001960207,0.0003138016,0.0003606778,0.00006233615,0.00002031956,0.02585643],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8102382,"threshold_uncertainty_score":0.9930031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08375402964294049,"score_gpt":0.428511606699596,"score_spread":0.3447575770566555,"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."}}