{"id":"W3084049503","doi":"10.3389/fpsyg.2020.02230","title":"International Comparative Study on PISA Mathematics Achievement Test Based on Cognitive Diagnostic Models","year":2020,"lang":"en","type":"article","venue":"Frontiers in Psychology","topic":"Cognitive Science and Mapping","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Jilin Office of Philosophy and Social Science; China Scholarship Council; East China Normal University","keywords":"Test (biology); Mathematics education; Cognition; Psychology; Process (computing); Scale (ratio); Achievement test; Field (mathematics); Computer science; Standardized test; Mathematics; Geography","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":[0.005398012,0.0004151341,0.0004482585,0.004068609,0.0005254346,0.001075968,0.000585041,0.0004029526,0.002333144],"category_scores_gemma":[0.01790063,0.000165455,0.001003899,0.003159029,0.0005553211,0.002128912,0.001318122,0.000580887,0.0005040204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007845639,"about_ca_system_score_gemma":0.0008262529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003606287,"about_ca_topic_score_gemma":0.002586964,"domain_scores_codex":[0.9960687,0.001265568,0.0005053767,0.0006980558,0.001139503,0.0003227127],"domain_scores_gemma":[0.9911489,0.003135931,0.001127622,0.0006337471,0.003131768,0.0008218851],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000266693,0.0002593594,0.9640743,0.00006965448,0.0001742443,0.0001919486,0.002523267,0.00063557,0.0003312035,0.001446424,0.0009792617,0.02904804],"study_design_scores_gemma":[0.00002058217,0.0005888843,0.9910018,0.00004052111,0.00009949666,0.0003043268,0.0029694,0.002403717,0.0003677817,0.0004734297,0.001707146,0.00002288729],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.992013,0.0002309182,0.00136224,0.00007878301,0.00003731568,0.00005569498,0.0004448762,0.00001584073,0.005761199],"genre_scores_gemma":[0.9981071,0.0001112718,0.000538495,0.00001278164,0.00001199726,0.00005555211,0.0007536758,0.000005178483,0.0004039287],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005398012,"threshold_uncertainty_score":0.0285477,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0837897227104895,"score_gpt":0.351879351568657,"score_spread":0.2680896288581675,"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."}}