{"id":"W2797014392","doi":"10.1177/0829573518765010","title":"Developing Proficiency in Standardized Cognitive Assessment Scoring: How Much Is Enough?","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of School Psychology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology; Standardized test; Wechsler Intelligence Scale for Children; Wechsler Adult Intelligence Scale; Clinical psychology; Cognition; Wechsler Preschool and Primary Scale of Intelligence; Intelligence quotient; Medical education; Applied psychology; Mathematics education; Psychiatry; Medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0984753,0.000570219,0.0007307067,0.001889957,0.0005482587,0.002215395,0.001549819,0.0009215482,0.0003814653],"category_scores_gemma":[0.3230902,0.0003442347,0.0005344791,0.00165358,0.00165225,0.004015172,0.001404439,0.001164631,0.0003815201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001045648,"about_ca_system_score_gemma":0.003875345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003220183,"about_ca_topic_score_gemma":0.005444341,"domain_scores_codex":[0.9385422,0.03340888,0.009419599,0.002513171,0.01492891,0.001187166],"domain_scores_gemma":[0.694167,0.1910897,0.04271829,0.02340697,0.04551142,0.003106653],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001530308,0.0002141856,0.7337341,0.0002610735,0.0001513853,0.00005029983,0.00300386,0.000789484,0.0008264555,0.0004116402,0.001062393,0.2593421],"study_design_scores_gemma":[0.00003759809,0.002818004,0.9666314,0.00103826,0.0001814187,0.000826841,0.005397149,0.008758591,0.004707169,0.002709998,0.006777225,0.0001164118],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9511231,0.00185054,0.03877427,0.003290974,0.0001920724,0.0004933262,0.0002092248,0.0002489594,0.003817594],"genre_scores_gemma":[0.9725547,0.001014503,0.0252582,0.0003653293,0.00006970527,0.0001827293,0.0002782675,0.00004511606,0.0002313808],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0984753,"threshold_uncertainty_score":0.5207934,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1039526991943376,"score_gpt":0.4554083521238081,"score_spread":0.3514556529294705,"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."}}