{"id":"W2994056206","doi":"10.1097/phm.0000000000001359","title":"Evaluation of Longitudinal Assessment for Use in Maintenance of Certification","year":2019,"lang":"en","type":"article","venue":"American Journal of Physical Medicine & Rehabilitation","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sunnybrook Health Science Centre","funders":"","keywords":"Certification; Maintenance of Certification; Medicine; Rehabilitation; Physical therapy; Physical examination; Internal medicine; Management","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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":[],"category_scores_codex":[0.02203259,0.00008222913,0.0006604686,0.0006380929,0.00001282662,0.000007453913,0.0002633019,0.00001742271,0.00002486427],"category_scores_gemma":[0.1585416,0.00005178072,0.0001505337,0.001804764,0.0003416663,0.0003089563,0.0000160533,0.0001165619,7.182432e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001276764,"about_ca_system_score_gemma":0.0001532302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008973618,"about_ca_topic_score_gemma":0.000005000796,"domain_scores_codex":[0.9949574,0.001130164,0.001308157,0.0002142087,0.002271042,0.0001189856],"domain_scores_gemma":[0.9373245,0.05590802,0.002403219,0.0002873694,0.004030562,0.0000463829],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001397629,0.0001611761,0.215606,0.00001645419,0.0000144047,7.010923e-8,0.0008598686,0.002749579,0.007484499,0.0009322001,0.00004489864,0.7719911],"study_design_scores_gemma":[0.001151287,0.01766192,0.8956682,0.0002308137,0.00005944542,0.000001491166,0.005624356,0.03940635,0.00009909079,0.04001313,0.00003575853,0.00004818113],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9662744,0.00003307299,0.03220092,0.0007973981,0.0002268297,0.0003514435,0.00000245042,0.000001700717,0.0001117997],"genre_scores_gemma":[0.9467,8.833363e-7,0.05319132,0.00001284201,0.00007636248,0.000008397184,8.152122e-7,0.000004640241,0.000004703056],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7719429,"threshold_uncertainty_score":0.8485464,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3580259271085565,"score_gpt":0.5333457614917764,"score_spread":0.1753198343832199,"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."}}