{"id":"W6965204032","doi":"10.3389/fpsyg.2020.02230.s005","title":"Data_Sheet_13_International Comparative Study on PISA Mathematics Achievement Test Based on Cognitive Diagnostic Models.CSV","year":2020,"lang":"en","type":"dataset","venue":"Figshare","topic":"Plant Ecology and Soil Science","field":"Environmental 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":[0.00011545,0.0003835052,0.0003569899,0.00006375411,0.0002173628,0.00007655814,0.00105246,0.0001507643,0.1562575],"category_scores_gemma":[0.002948683,0.0003318628,0.00006232379,0.0001951569,0.00005252201,0.000167834,0.0004877704,0.0005833218,0.05941047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002067409,"about_ca_system_score_gemma":0.00005394525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003233385,"about_ca_topic_score_gemma":0.0005743888,"domain_scores_codex":[0.9976096,0.0001020171,0.0003056224,0.0007607357,0.0009137416,0.0003083316],"domain_scores_gemma":[0.9945039,0.004666649,0.0002659998,0.0003739529,0.00002157399,0.0001679778],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002215495,0.002101393,0.0001145759,0.00003272226,0.00002348211,0.0001739489,0.0001428956,0.004139896,4.475407e-7,0.000001497805,0.9932342,0.00001283246],"study_design_scores_gemma":[0.002701378,0.006486457,0.04881087,0.006098619,0.0002365213,0.00001440047,0.0008734813,0.1242675,0.00005983598,0.0002809417,0.8079551,0.002214958],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0002064779,0.000001573035,0.000004138919,0.00009054859,0.00007746122,0.001021905,0.995559,0.00003104469,0.003007857],"genre_scores_gemma":[0.0259594,0.000001398913,0.00002251381,0.001763415,0.00005364916,0.0005667778,0.9715586,0.00001069126,0.00006357241],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1852791,"threshold_uncertainty_score":0.9999133,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09652419569059288,"score_gpt":0.30474368595893,"score_spread":0.2082194902683371,"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."}}