{"id":"W6927654321","doi":"10.3389/fpsyg.2020.02230.s014","title":"Data_Sheet_9_International Comparative Study on PISA Mathematics Achievement Test Based on Cognitive Diagnostic Models.CSV","year":2020,"lang":"en","type":"dataset","venue":"Figshare","topic":"Advanced Energy Technologies and Civil Engineering Innovations","field":"Energy","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":[0.00003052155,0.000572814,0.0004926741,0.0002592875,0.0001288913,0.00008012697,0.000810602,0.0002349601,0.02010659],"category_scores_gemma":[0.004477731,0.0005418473,0.00009214866,0.0004217792,0.00001606149,0.0001006829,0.0002871988,0.0008235143,0.003437827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001834801,"about_ca_system_score_gemma":0.0000691174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002987711,"about_ca_topic_score_gemma":0.0001289615,"domain_scores_codex":[0.9979409,0.00002553898,0.0004658431,0.0006329226,0.0006313375,0.0003034803],"domain_scores_gemma":[0.996033,0.002664529,0.0003003804,0.0007066509,0.0002188959,0.00007660376],"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":[0.00001214542,0.00125848,4.052624e-7,0.0001129258,0.0001080269,0.00005521314,0.00002439428,0.2213905,3.665819e-7,0.0004771982,0.7764809,0.00007945287],"study_design_scores_gemma":[0.0008600894,0.001254188,0.00006123799,0.004246168,0.00007548592,0.000001237845,0.000378368,0.05178846,0.00008220103,0.0002626929,0.9402665,0.0007233004],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000005169979,0.00001068706,0.000291977,0.0000804984,0.0001024679,0.0005979908,0.9965732,0.000333656,0.002004409],"genre_scores_gemma":[0.008363659,0.000004167218,0.0001936772,0.0006026598,0.0001504661,0.001916261,0.9886398,0.0000582198,0.00007110891],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.169602,"threshold_uncertainty_score":0.9997033,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09064645088571316,"score_gpt":0.308972217778936,"score_spread":0.2183257668932228,"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."}}