{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001026061,0.0002040791,0.001116707,0.0004853567,0.00005602969,0.000001206716,0.0001269674,0.0006034857,0.0006606821],"category_scores_gemma":[0.0003878232,0.0001836543,0.0002407668,0.0003029014,0.0008889823,0.000054026,0.00007948627,0.0004547364,0.00001727685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001649484,"about_ca_system_score_gemma":0.0001446606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006399648,"about_ca_topic_score_gemma":0.00005096288,"domain_scores_codex":[0.9977508,0.0001952841,0.0009235674,0.0003827754,0.000165794,0.0005817409],"domain_scores_gemma":[0.9975973,0.00101958,0.0004829801,0.0003384937,0.0004154141,0.0001462644],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006068024,0.0007468573,0.9588096,0.00005334777,0.0005243109,0.0005139546,0.0003836428,0.00005671693,0.00313638,0.02814096,0.0001162599,0.006911178],"study_design_scores_gemma":[0.003328057,0.001528178,0.9759758,0.00004007368,0.00009052957,0.0005635438,0.0002041611,0.0002190079,0.01090843,0.00161854,0.005370711,0.0001530215],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9647028,0.0004544698,0.001754858,0.001888476,0.000291995,0.0002911621,0.000006687809,0.00006071757,0.03054883],"genre_scores_gemma":[0.9949226,0.00008930973,0.002365527,0.002297666,0.00007579484,0.000007261633,0.00003908175,0.00001686178,0.0001859368],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03036289,"threshold_uncertainty_score":0.7489206,"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."}}