{"id":"W2782320564","doi":"10.1007/s40037-017-0391-8","title":"Detecting rater bias using a person-fit statistic: a Monte Carlo simulation study","year":2018,"lang":"en","type":"article","venue":"Perspectives on Medical Education","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; Université de Sherbrooke","funders":"Fonds de Recherche du Québec-Société et Culture","keywords":"Monte Carlo method; Statistic; Medical physics; Computer science; Psychology; Medicine; Statistics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008527765,0.0003265732,0.0004216501,0.0004645524,0.0007551674,0.0004343485,0.0006723261,0.000163701,0.00420603],"category_scores_gemma":[0.04872096,0.0002459629,0.0001406253,0.001021883,0.0003981862,0.0004370488,0.00009132592,0.0004752293,0.0007676512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007171537,"about_ca_system_score_gemma":0.0008223636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009062422,"about_ca_topic_score_gemma":0.001029113,"domain_scores_codex":[0.991454,0.001316511,0.000936471,0.001222615,0.004597975,0.0004724002],"domain_scores_gemma":[0.9940164,0.00220148,0.0004831812,0.0009988195,0.001858356,0.0004417763],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.001100702,0.01472838,0.1534236,0.00006461286,0.0003622903,0.0000095374,0.4521339,0.02163647,0.00151114,0.0007822872,0.01147297,0.3427742],"study_design_scores_gemma":[0.003031683,0.002361671,0.2125761,0.0005151933,0.0002529523,0.00001829378,0.6020955,0.1491325,0.0002939006,0.005986898,0.02219791,0.001537395],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9720289,0.000144344,0.02193735,0.001732829,0.00205027,0.000911088,0.000007035251,0.0000713475,0.001116806],"genre_scores_gemma":[0.993521,0.000008569723,0.003512372,0.0005369782,0.001345571,0.00004591601,0.000003114575,0.00002606723,0.001000458],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3412368,"threshold_uncertainty_score":0.9999993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4676450050714238,"score_gpt":0.5170803826767165,"score_spread":0.04943537760529271,"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."}}