{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02880075,0.003217607,0.002255056,0.004408705,0.0008845819,0.003797815,0.003863147,0.001432644,0.191054],"category_scores_gemma":[0.09500965,0.003119263,0.002844665,0.003527382,0.0009204316,0.003772859,0.006680813,0.003779792,0.07626463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007549652,"about_ca_system_score_gemma":0.002839179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008198289,"about_ca_topic_score_gemma":0.001478296,"domain_scores_codex":[0.9844635,0.009105291,0.002166183,0.001446777,0.002421096,0.0003972553],"domain_scores_gemma":[0.9067127,0.07257129,0.003128331,0.008035748,0.008319978,0.001231976],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001596041,0.0005942238,0.003314163,0.006150199,0.0006171274,0.0003127138,0.002637252,0.002951776,0.006268101,0.01542836,0.3420572,0.6180728],"study_design_scores_gemma":[0.002561999,0.001047395,0.01310594,0.003282875,0.0005353376,0.0008250903,0.000610843,0.02514863,0.01875839,0.0818213,0.8516812,0.0006211305],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.002038744,0.0004398882,0.8400437,0.0005524766,0.0004026003,0.005002023,0.0208498,0.1237013,0.006969558],"genre_scores_gemma":[0.00762141,0.0004455828,0.9188676,0.0004001409,0.0001918898,0.02522054,0.01129646,0.0281039,0.007852394],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.191054,"threshold_uncertainty_score":0.6391394,"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."}}