{"id":"W7017887811","doi":"","title":"A cognitive diagnostic assessment of PISA math items: What skills have Canadian student mastered?","year":2022,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Cognition; Test (biology); Cognitive skill; Item response theory; Achievement test; Cognitive development; Educational assessment; Test score","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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002729859,0.0002926349,0.0008652681,0.001938915,0.0004114797,0.0001739632,0.001518532,0.0002186146,0.0005877393],"category_scores_gemma":[0.0101431,0.0003235762,0.0002964814,0.00141669,0.0001237852,0.0004516263,0.0003009735,0.0004703725,0.00002604041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004215632,"about_ca_system_score_gemma":0.0006304525,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.07530356,"about_ca_topic_score_gemma":0.9046521,"domain_scores_codex":[0.995602,0.0007399835,0.0004412326,0.0007397398,0.002071901,0.0004051719],"domain_scores_gemma":[0.9767547,0.02022618,0.001408776,0.0005944909,0.0007634184,0.0002524409],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00009361542,0.0004807389,0.9103199,0.0001904289,0.0004637075,0.0006045528,0.00825029,0.000183369,0.0000365228,0.0006073465,0.005517901,0.07325163],"study_design_scores_gemma":[0.000348332,0.0001753252,0.5887398,0.0002652201,0.0001062609,0.000003562857,0.4077836,0.0001211984,0.000007205656,0.0002890372,0.001979915,0.0001805535],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9761295,0.0007366611,0.0006474194,0.000294359,0.001836142,0.0006675292,0.0003029138,0.00002319147,0.0193623],"genre_scores_gemma":[0.9885485,0.0009825886,0.003490813,0.00006313167,0.00005081716,0.000003681818,0.0002942723,0.00003102111,0.00653522],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8293486,"threshold_uncertainty_score":0.9999216,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1356568407669538,"score_gpt":0.3937507742777159,"score_spread":0.2580939335107621,"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."}}