{"id":"W2106989151","doi":"10.1080/01421590802047315","title":"Turning words into numbers: establishing an empirical cut score for a letter graded examination","year":2008,"lang":"en","type":"article","venue":"Medical Teacher","topic":"Medical Education and Admissions","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Gold standard (test); Cut-off; Medicine; Certification; Test (biology); Medical physics; Statistics; Mathematics; Radiology; 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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001082225,0.0001777495,0.0003237825,0.0001266302,0.0002348121,0.00002685035,0.0001860606,0.000332746,0.01227916],"category_scores_gemma":[0.01951686,0.0001331093,0.0001174067,0.0002781083,0.0002404529,0.000214313,0.00004246183,0.0008277476,0.0000451779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001077562,"about_ca_system_score_gemma":0.0008794193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005067822,"about_ca_topic_score_gemma":0.00001442981,"domain_scores_codex":[0.9976061,0.0001865885,0.0004020175,0.0003991203,0.001036996,0.0003691684],"domain_scores_gemma":[0.9970824,0.0001977499,0.00007463134,0.0002954959,0.00009737721,0.002252352],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000154133,0.002835863,0.1124705,0.0002609394,0.00009907858,0.000370515,0.03982048,7.128264e-7,0.0005231902,0.0002590885,0.7334177,0.1097877],"study_design_scores_gemma":[0.006844386,0.0006963307,0.0532442,0.0009771285,0.0001797897,0.0007974085,0.003113713,0.02296443,0.0003461295,0.0005991505,0.9095758,0.0006614921],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.947535,0.00009443008,0.007719578,0.04018479,0.0005506874,0.0003985309,5.750454e-7,0.0001824079,0.003334046],"genre_scores_gemma":[0.955919,0.00001859006,0.002836009,0.02467507,0.002802372,0.0001090675,0.0001794362,0.00004510587,0.01341534],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1761581,"threshold_uncertainty_score":0.9887422,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1066127779496196,"score_gpt":0.4009628479495917,"score_spread":0.2943500699999722,"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."}}