{"id":"W2808430903","doi":"10.1007/s40037-018-0435-8","title":"Examining the effects of gaming and guessing on script concordance test scores","year":2018,"lang":"en","type":"article","venue":"Perspectives on Medical Education","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; McGill University","funders":"","keywords":"Concordance; Likert scale; Test (biology); Statistics; Psychology; Scale (ratio); Social psychology; Mathematics; 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"],"consensus_categories":[],"category_scores_codex":[0.003370784,0.0001031547,0.0001649185,0.0001098625,0.0002550722,0.00009046225,0.0003677225,0.00004970809,0.0001780414],"category_scores_gemma":[0.08151824,0.00005806861,0.00003074696,0.0003276574,0.0008475005,0.000115338,0.00004933823,0.0001881255,0.00003286883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000762343,"about_ca_system_score_gemma":0.0002661899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004376108,"about_ca_topic_score_gemma":0.0000132668,"domain_scores_codex":[0.9970338,0.0002985839,0.000324313,0.000417772,0.001780878,0.0001446601],"domain_scores_gemma":[0.993365,0.005458388,0.0002064736,0.00042049,0.0004267031,0.0001229002],"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":[0.0001262526,0.002076524,0.1193733,0.00009640296,0.00003268077,0.000001771694,0.08036845,0.000003385903,0.01225005,0.015786,0.01348601,0.7563992],"study_design_scores_gemma":[0.0007782149,0.002986024,0.8302478,0.002351953,0.00003196646,0.000005818907,0.1240772,0.001099396,0.01572138,0.01950028,0.002923553,0.0002764165],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9877645,0.0008352269,0.000702612,0.004102796,0.001124895,0.0002365793,5.336386e-7,0.00001250227,0.005220295],"genre_scores_gemma":[0.9979042,0.00008754558,0.0002681139,0.001021239,0.0004780351,0.00001941028,3.301514e-7,0.000004815007,0.00021633],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7561228,"threshold_uncertainty_score":0.9262185,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07302416389855387,"score_gpt":0.392594142714597,"score_spread":0.3195699788160431,"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."}}