{"id":"W114458342","doi":"10.1177/070674371005500310","title":"Measure for Measure: New Developments in Measurement and Item Response Theory","year":2010,"lang":"en","type":"article","venue":"The Canadian Journal of Psychiatry","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"Baycrest Hospital; University of Toronto","funders":"","keywords":"Item response theory; Classical test theory; Normative; Measure (data warehouse); Psychology; Econometrics; Psychometrics; Test (biology); Scale (ratio); Interpretation (philosophy); Cognitive psychology; Sample (material); Level of measurement; Statistics; Computer science; Mathematics; Clinical psychology; Epistemology; Data mining","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0676444,0.0001472416,0.000308796,0.0009378194,0.0003630501,0.0002590683,0.001067445,0.0001209177,0.00006761983],"category_scores_gemma":[0.136943,0.000087471,0.000113203,0.00108479,0.0001239716,0.000149646,0.00002215203,0.0005806001,0.000004905889],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001108994,"about_ca_system_score_gemma":0.007382182,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001020418,"about_ca_topic_score_gemma":0.31078,"domain_scores_codex":[0.9963214,0.001021234,0.000874052,0.0002274051,0.001163774,0.0003921631],"domain_scores_gemma":[0.9887417,0.008728107,0.0006137969,0.000404588,0.0008141404,0.000697656],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001416388,0.00002598456,0.6180147,0.000007579344,0.00009372544,0.00001455222,0.001886425,0.00001710959,0.0008354991,0.01958033,0.03773354,0.3203742],"study_design_scores_gemma":[0.001079806,0.0001113579,0.6313412,0.00008293772,0.00002032921,0.0001775377,0.0009671712,0.000009413956,0.00004642104,0.343272,0.02274617,0.0001456764],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9139413,0.007416144,0.01112933,0.05084018,0.01350961,0.0005871229,0.00001237445,0.00001133003,0.002552596],"genre_scores_gemma":[0.9368882,0.000003633643,0.06186497,0.0006146355,0.0003695246,0.000002831466,7.14018e-8,0.00001413908,0.0002420432],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3236917,"threshold_uncertainty_score":0.9982451,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3343001166771012,"score_gpt":0.3961017540352872,"score_spread":0.06180163735818595,"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."}}