{"id":"W2793870071","doi":"10.1007/s40037-018-0410-4","title":"i-Assess: Evaluating the impact of electronic data capture for OSCE","year":2018,"lang":"en","type":"article","venue":"Perspectives on Medical Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; McMaster University; Impact","funders":"","keywords":"Cronbach's alpha; Generalizability theory; Rasch model; Reliability (semiconductor); Modality (human–computer interaction); Internal consistency; Inter-rater reliability; Medicine; Repeated measures design; Post hoc; Rating scale; Post-hoc analysis; Kappa; Statistics; Physical therapy; Psychology; Clinical psychology; Psychometrics; Mathematics; Artificial intelligence; Computer science; Internal medicine","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01593553,0.0001061479,0.0002129949,0.000212396,0.0002080236,0.00007399923,0.001740178,0.00008282006,0.001013984],"category_scores_gemma":[0.5285444,0.00005289181,0.0001001611,0.001324922,0.0002970498,0.0001541706,0.000128892,0.0002536958,0.00001754854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001496702,"about_ca_system_score_gemma":0.002470784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002882936,"about_ca_topic_score_gemma":0.00001881018,"domain_scores_codex":[0.9967377,0.0006101954,0.0004020803,0.0005586389,0.001414602,0.0002767977],"domain_scores_gemma":[0.9430906,0.05119034,0.0007981519,0.002538506,0.002140509,0.0002419038],"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":[0.0003024209,0.0009588165,0.009824225,0.000008982165,0.0001056892,1.112579e-7,0.01596184,0.00003940667,0.0004657672,0.02225148,0.07392875,0.8761525],"study_design_scores_gemma":[0.001389141,0.005343819,0.3069521,0.0001834177,0.0000940445,0.00003528342,0.1967595,0.1813377,0.0001565696,0.3019775,0.005308182,0.0004626761],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9032808,0.002055207,0.07663706,0.007747265,0.001226136,0.000616658,0.00002529246,0.00003590751,0.008375679],"genre_scores_gemma":[0.9918275,0.00003756804,0.006769528,0.000214371,0.0008696975,0.00002507294,0.000008990737,0.000008044576,0.0002392585],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8756899,"threshold_uncertainty_score":0.9998992,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.60814605761424,"score_gpt":0.6509570250056883,"score_spread":0.0428109673914483,"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."}}