{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005801677,0.0007166257,0.001054242,0.007012562,0.0009055798,0.001004674,0.001514881,0.0007125264,0.09957524],"category_scores_gemma":[0.02484017,0.0003182403,0.001088214,0.006626558,0.0004530521,0.001239694,0.001181304,0.0009956231,0.02361059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001747183,"about_ca_system_score_gemma":0.003044662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008523911,"about_ca_topic_score_gemma":0.007346779,"domain_scores_codex":[0.9927737,0.00182973,0.001861178,0.0005911425,0.002666732,0.0002775897],"domain_scores_gemma":[0.9712175,0.007420097,0.003543259,0.002250583,0.01488083,0.000687714],"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":[0.003604321,0.002109868,0.2255474,0.003886398,0.0002322161,0.0002674878,0.0007613502,0.001415635,0.0009826437,0.004645358,0.524585,0.2319623],"study_design_scores_gemma":[0.0007373201,0.001368037,0.69038,0.001265864,0.0001520454,0.0003422327,0.001561489,0.001362092,0.002166264,0.001819426,0.2987095,0.0001358066],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.03917228,0.0003213003,0.002195713,0.0008048692,0.0002259732,0.01022382,0.9074711,0.0005479252,0.03903699],"genre_scores_gemma":[0.1316867,0.000695741,0.008098554,0.0008773234,0.0001544879,0.05780492,0.7730766,0.0002679382,0.02733771],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.9004248,"threshold_uncertainty_score":0.3331124,"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."}}