{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002953554,0.0005919664,0.0005411567,0.004803177,0.00208503,0.002052265,0.001873522,0.0006081936,0.004283349],"category_scores_gemma":[0.01305644,0.0002439798,0.001002306,0.004446114,0.001355777,0.001140496,0.001773196,0.001228107,0.001256484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0132218,"about_ca_system_score_gemma":0.03198848,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9167808,"about_ca_topic_score_gemma":0.9496369,"domain_scores_codex":[0.9977551,0.000139504,0.0001823337,0.0001875027,0.001433692,0.0003018607],"domain_scores_gemma":[0.9894489,0.0005596613,0.001085742,0.0003029972,0.007674738,0.0009279232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001885605,0.0002920951,0.8425857,0.0003739519,0.0001299292,0.0001452372,0.006106516,0.0006279079,0.0009507371,0.002052367,0.01411835,0.1324287],"study_design_scores_gemma":[0.00001755816,0.00010864,0.9828128,0.0001407815,0.00005181469,0.0000861325,0.004376558,0.001248968,0.0006091854,0.0004564886,0.01003453,0.00005655305],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.93301,0.0009627686,0.00278012,0.001569877,0.0001541702,0.0008593794,0.01284641,0.0001767163,0.04764062],"genre_scores_gemma":[0.9770891,0.001119807,0.005822003,0.0002682106,0.00002601651,0.0004709571,0.008542448,0.00002554003,0.006636039],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08321923,"threshold_uncertainty_score":0.1674186,"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."}}