{"id":"W3035107461","doi":"10.1177/0146621620929431","title":"OpenMx: A Modular Research Environment for Item Response Theory Method Development","year":2020,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Institute on Drug Abuse; National Institutes of Health","keywords":"Modular design; Computer science; Implementation; Item response theory; Source code; Code (set theory); Selection (genetic algorithm); Software; Software engineering; Theoretical computer science; Programming language; Machine learning; Statistics; Mathematics; Psychometrics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1367548,0.0003539798,0.0006984674,0.0003882715,0.0005998886,0.0002572282,0.002182934,0.0002477593,0.0009966706],"category_scores_gemma":[0.1155536,0.0002351757,0.0002021472,0.001853547,0.0002032837,0.00006869371,0.0005525107,0.0005993436,0.0007675589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002469597,"about_ca_system_score_gemma":0.00008169239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.316912e-7,"about_ca_topic_score_gemma":2.30539e-7,"domain_scores_codex":[0.9850789,0.005110349,0.001435629,0.002091699,0.005260665,0.001022704],"domain_scores_gemma":[0.951246,0.04618058,0.000340191,0.001161669,0.0004800087,0.0005915749],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.008510056,0.0005391631,0.0003380428,0.00001530104,0.0001017802,0.00001459455,0.001299672,0.0002853353,0.07766089,0.01485276,0.01506183,0.8813206],"study_design_scores_gemma":[0.002729097,0.001403507,0.05448961,0.00002219636,0.00002239614,0.000007519898,0.002504734,0.0004148304,0.01020749,0.1310377,0.796499,0.0006618664],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05831437,0.000459964,0.9232092,0.006693102,0.0002756776,0.002264758,0.000008164497,0.0001369433,0.008637769],"genre_scores_gemma":[0.5871417,0.000010402,0.4095684,0.002177484,0.0001416689,0.0007867218,0.000001717842,0.00002569763,0.0001462123],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8806587,"threshold_uncertainty_score":0.9999166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9218223146811826,"score_gpt":0.5923631288612036,"score_spread":0.329459185819979,"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."}}