{"id":"W3123716856","doi":"10.1111/eje.12649","title":"Script concordance tests: A call for action in dental education","year":2021,"lang":"en","type":"article","venue":"European Journal Of Dental Education","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Concordance; Test (biology); Dental education; Medical education; Psychology; Clinical judgment; Action (physics); Medicine; Medical physics","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":[0.0004919649,0.00008863264,0.0001919629,0.0001182143,0.00003579419,0.00003759974,0.0000683352,0.00002534737,0.00005350456],"category_scores_gemma":[0.01261719,0.00008453523,0.0001216169,0.0001878499,0.00003098782,0.0001425377,0.00001475511,0.0002141653,0.0000353943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002570084,"about_ca_system_score_gemma":0.001459947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002362751,"about_ca_topic_score_gemma":0.00004215473,"domain_scores_codex":[0.9988758,0.0001421604,0.0005249623,0.0001454355,0.0001917972,0.0001198748],"domain_scores_gemma":[0.9984697,0.0005640369,0.0003044555,0.0001223949,0.0003606105,0.0001788152],"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":[0.0005373675,0.005361721,0.2942975,0.0001042229,0.00005522958,0.0001513492,0.0008195498,0.0000113829,0.01631475,0.0002403319,0.03902627,0.6430804],"study_design_scores_gemma":[0.003023293,0.0008028066,0.9558823,0.004235732,0.0001529956,0.003224689,0.009946871,0.00003177085,0.004658766,0.0001575352,0.01772403,0.0001592013],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9896758,0.001671408,0.0003238371,0.001214253,0.003477895,0.0001649136,0.0000027157,0.000007760259,0.003461437],"genre_scores_gemma":[0.9919374,0.0002249144,0.003722878,0.001306581,0.001225433,0.000005628707,0.00005866752,0.00002186219,0.001496653],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6615849,"threshold_uncertainty_score":0.9956999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0335290089963491,"score_gpt":0.3785386474968958,"score_spread":0.3450096385005467,"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."}}