{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000271675,0.0001701733,0.0002500624,0.0002490224,0.00006432363,0.00005671133,0.0008042289,0.00004273047,0.00001460057],"category_scores_gemma":[0.0004123318,0.0001598959,0.00004275627,0.0004775494,0.00009530216,0.0002066877,0.0001175202,0.0002463548,0.00007868188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004710472,"about_ca_system_score_gemma":0.00003165451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001689719,"about_ca_topic_score_gemma":0.000001975158,"domain_scores_codex":[0.9983793,0.0001181865,0.0002667329,0.000632494,0.0003465833,0.0002566938],"domain_scores_gemma":[0.9987325,0.0007577211,0.0001020863,0.0002302985,0.00008282762,0.00009454498],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001098933,0.04517883,0.3339941,0.00008178635,0.0005485587,0.001335233,0.1726978,0.0133972,0.0004873443,0.01957644,0.1234877,0.288116],"study_design_scores_gemma":[0.00454261,0.004129093,0.03268816,0.0001778374,0.00001648129,0.000002478072,0.007643955,0.9324017,0.0001285311,0.01703107,0.0007939365,0.00044413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01366145,0.00001238883,0.9558406,0.005574336,0.00114026,0.0006313863,0.00001456467,0.00005777932,0.02306719],"genre_scores_gemma":[0.9682679,0.00000872351,0.0217557,0.009792791,0.00005579054,0.00009459189,0.000005182511,0.000006362432,0.00001301912],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9546064,"threshold_uncertainty_score":0.6520365,"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."}}