{"id":"W2148833920","doi":"10.1177/000348940711601101","title":"Objective Assessment of Temporal Bone Drilling Skills","year":2007,"lang":"en","type":"article","venue":"Annals of Otology Rhinology & Laryngology","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Wilson Centre","funders":"","keywords":"Otorhinolaryngology; Logistic regression; Checklist; Inter-rater reliability; Medicine; Reliability (semiconductor); Temporal bone; Rating scale; Statistics; Surgery; Psychology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003036267,0.0006314893,0.0002503839,0.0007930619,0.0001248342,0.0003217928,0.0003995822,0.000297324,0.002815091],"category_scores_gemma":[0.01086238,0.0001099246,0.0002916099,0.000244839,0.0003625982,0.0004610129,0.0007802961,0.0002747977,0.000394024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000142418,"about_ca_system_score_gemma":0.0004746346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003764866,"about_ca_topic_score_gemma":0.0009323893,"domain_scores_codex":[0.9972906,0.000896882,0.0004148938,0.0002116679,0.001083698,0.0001023356],"domain_scores_gemma":[0.9869816,0.004749464,0.004012818,0.0004090189,0.003340471,0.0005066284],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001096774,0.001257212,0.5814803,0.002006506,0.000262568,0.0004317272,0.002375115,0.002978033,0.05517505,0.0002487122,0.001776779,0.3509112],"study_design_scores_gemma":[0.0001305861,0.007359786,0.9547635,0.0004362954,0.0001610838,0.002890765,0.001398611,0.005745275,0.02244682,0.0002797052,0.004295935,0.00009173921],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9748437,0.0005815893,0.01755166,0.00008605261,0.00004038916,0.000391611,0.0003665688,0.0001060875,0.006032276],"genre_scores_gemma":[0.9824091,0.0004312026,0.0148167,0.0000622261,0.00003032395,0.0002638356,0.0003373919,0.00001586049,0.001633358],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003036267,"threshold_uncertainty_score":0.01605749,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04583407195606679,"score_gpt":0.3891187038055335,"score_spread":0.3432846318494668,"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."}}