{"id":"W2058166804","doi":"10.1080/10401334.2010.488197","title":"Assessment in the Context of Uncertainty Using the Script Concordance Test: More Meaning for Scores","year":2010,"lang":"en","type":"article","venue":"Teaching and Learning in Medicine","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":71,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Concordance; Raw score; Standard deviation; Test (biology); Medicine; Meaning (existential); Context (archaeology); Set (abstract data type); Metric (unit); Statistics; Raw data; Psychology; Mathematics; Computer science; Operations 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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007410241,0.0001353767,0.0004384194,0.0000864067,0.0002319424,0.0000134144,0.0001381193,0.00007736501,0.00001200852],"category_scores_gemma":[0.1222894,0.00006868086,0.00004533234,0.000139058,0.0004354444,0.00002727716,0.00002863243,0.002618578,1.71106e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002732195,"about_ca_system_score_gemma":0.0001076545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003288028,"about_ca_topic_score_gemma":0.0003663356,"domain_scores_codex":[0.9984741,0.0003306828,0.0004483572,0.0002245978,0.000290657,0.0002315969],"domain_scores_gemma":[0.9646224,0.03482525,0.000188589,0.0002377103,0.00006367712,0.00006235927],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001049639,0.0001673513,0.9162812,0.00008685424,0.00002039668,0.00002260063,0.02441771,0.0007508881,0.005602226,0.003666173,0.0003861644,0.04849351],"study_design_scores_gemma":[0.00731481,0.001570294,0.7874128,0.008923863,0.0002068241,0.0001436101,0.06838644,0.1215053,0.00003499378,0.000584113,0.003713094,0.0002038397],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9885799,0.0003514531,0.000551591,0.008972607,0.000187188,0.0004016477,0.000001316055,0.0000211433,0.0009331871],"genre_scores_gemma":[0.9952644,0.00003155279,0.002224829,0.002057379,0.0002822835,0.00002174693,0.00001090765,0.00001422164,0.00009266391],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1288683,"threshold_uncertainty_score":0.9996824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03906379159632414,"score_gpt":0.3966457841668997,"score_spread":0.3575819925705756,"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."}}