{"id":"W4381282730","doi":"10.1080/15305058.2023.2214648","title":"The analysis of TIMSS 2015 data with confirmatory mixture item response theory: A multidimensional approach","year":2023,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Confirmatory factor analysis; Item response theory; Class (philosophy); Psychology; Mathematics education; Structural equation modeling; Polytomous Rasch model; Sample (material); Latent class model; Cognition; Psychometrics; Mathematics; Statistics; Developmental psychology; Artificial intelligence; Computer science","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03752734,0.0001204211,0.0003883866,0.001569794,0.0001594976,0.0001718099,0.002859401,0.00004826943,0.00003722357],"category_scores_gemma":[0.3058342,0.00006046657,0.0001436402,0.004647022,0.0001836548,0.0003067629,0.0005449347,0.0002884439,0.000007477617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003468797,"about_ca_system_score_gemma":0.0002300039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001192893,"about_ca_topic_score_gemma":0.000002445597,"domain_scores_codex":[0.9944501,0.001279714,0.001120532,0.0002862797,0.002669386,0.000194025],"domain_scores_gemma":[0.8217819,0.1724452,0.002073327,0.0006825376,0.002922592,0.00009438432],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.007351219,0.0002952498,0.5579388,0.00001053637,0.007972754,0.0005736614,0.001747583,0.07577638,0.009435109,0.002778317,0.0448066,0.2913138],"study_design_scores_gemma":[0.0009233812,0.0001829948,0.6400357,0.0001182503,0.0003478175,0.0004757733,0.003734874,0.342062,0.0001253738,0.004025065,0.007783344,0.0001854002],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9578756,0.0005268704,0.03737101,0.001953447,0.0009350386,0.00008875431,0.0001146134,0.00003172991,0.001102905],"genre_scores_gemma":[0.9123429,0.0000135796,0.0869462,0.00009529054,0.0001748027,0.000001326177,0.00001253802,0.00001067046,0.0004026938],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2911284,"threshold_uncertainty_score":0.9910681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5081435997123916,"score_gpt":0.5085350331339626,"score_spread":0.0003914334215709969,"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."}}