{"id":"W2142004159","doi":"10.3899/jrheum.130813","title":"Item Response Theory, Computerized Adaptive Testing, and PROMIS: Assessment of Physical Function","year":2013,"lang":"en","type":"article","venue":"The Journal of Rheumatology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":208,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","keywords":"Computerized adaptive testing; Patient-Reported Outcomes Measurement Information System; Item response theory; Item bank; CLARITY; Medicine; Reliability (semiconductor); Standardization; Perspective (graphical); Short Forms; Construct (python library); Applied psychology; Function (biology); Psychometrics; Computer science; Psychology; Clinical psychology; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0154809,0.0001031569,0.0005673713,0.000310514,0.0001074517,0.0000434645,0.0005097551,0.00004959184,0.00005912826],"category_scores_gemma":[0.05904254,0.00004979067,0.00007697244,0.0006533259,0.0002940212,0.0001681188,0.000153304,0.0002538413,0.000005612734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001464191,"about_ca_system_score_gemma":0.00009269891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003963614,"about_ca_topic_score_gemma":5.606864e-7,"domain_scores_codex":[0.993971,0.004418541,0.0008096184,0.000132092,0.0005059398,0.0001628118],"domain_scores_gemma":[0.8501359,0.147348,0.001524179,0.0002502488,0.00067645,0.00006528357],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.004867864,0.0002960891,0.5812816,0.00002271852,0.0003053717,0.000005927265,0.002366733,0.0003802337,0.02271704,0.01072782,0.003307013,0.3737216],"study_design_scores_gemma":[0.001060213,0.002442164,0.7784851,0.00008228234,0.00004281864,0.001593102,0.001927994,0.0320612,0.00008814554,0.1820283,0.0001006917,0.00008792774],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9041982,0.0001219068,0.0945632,0.0003993905,0.000283187,0.0001252263,7.284783e-7,0.000007852213,0.0003003129],"genre_scores_gemma":[0.9639931,0.0000150743,0.03589916,0.00003888801,0.0000116704,0.000001986652,2.905115e-8,0.000005012017,0.00003509649],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3736337,"threshold_uncertainty_score":0.9488835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2335860100349148,"score_gpt":0.4218876205134344,"score_spread":0.1883016104785196,"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."}}