{"id":"W6908762632","doi":"10.3389/fpsyg.2020.02230.s012","title":"Data_Sheet_7_International Comparative Study on PISA Mathematics Achievement Test Based on Cognitive Diagnostic Models.CSV","year":2020,"lang":"en","type":"dataset","venue":"Figshare","topic":"Mathematics, Computing, and Information Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Cognition; Process (computing); Achievement test; Item response theory; Metacognition; Cognitive development; Cognitive skill","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001810896,0.000588749,0.0006002356,0.0003058288,0.0002673365,0.0008379599,0.002257111,0.0001385106,0.007108802],"category_scores_gemma":[0.004720779,0.0005327687,0.0001177846,0.0003437853,0.00001489727,0.0006530049,0.0007815129,0.0006742463,0.008921431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001322981,"about_ca_system_score_gemma":0.0002832419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003427472,"about_ca_topic_score_gemma":0.000005860305,"domain_scores_codex":[0.996617,0.00008685682,0.0008586492,0.0007044915,0.001396503,0.0003365406],"domain_scores_gemma":[0.9926777,0.004824177,0.001009824,0.000858436,0.0004504301,0.000179379],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005135591,0.001589974,6.128091e-7,0.0007609832,0.00005519957,0.00002997063,0.001440876,0.002099361,2.950626e-8,0.000128514,0.9937274,0.0001619704],"study_design_scores_gemma":[0.0009182678,0.000997127,0.00002898438,0.01045115,0.00004383367,0.000004244558,0.0004029538,0.8256196,0.0000277962,0.0004492862,0.1603258,0.0007309124],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000002355951,0.000008813357,0.01475258,0.00008541144,0.0001575208,0.001214778,0.9814001,0.0001588382,0.002219576],"genre_scores_gemma":[0.002268177,0.000001164896,0.001631118,0.002166558,0.000170668,0.0003997195,0.9933111,0.00002137685,0.00003008151],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.8334016,"threshold_uncertainty_score":0.9997124,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1266528095215903,"score_gpt":0.3272529516910063,"score_spread":0.200600142169416,"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."}}