{"id":"W4210694348","doi":"10.1055/s-0041-1740162","title":"Comparison of Summative Temporal Bone Dissection Scales Demonstrate Equivalence","year":2022,"lang":"en","type":"article","venue":"International Archives of Otorhinolaryngology","topic":"Ear Surgery and Otitis Media","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Sciences Centre; University of Manitoba","funders":"","keywords":"Medicine; Temporal bone; Summative assessment; Reliability (semiconductor); Rating scale; Intra-rater reliability; Scale (ratio); Construct validity; Physical therapy; Surgery; Formative assessment; Statistics; Confidence interval; Cartography; Mathematics; Internal medicine","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":[0.0001365955,0.00009015384,0.0003371063,0.0002655456,0.00005785964,0.000002319156,0.0001659967,0.00002757391,0.0004441556],"category_scores_gemma":[0.000122748,0.00008982618,0.0001333432,0.00009111151,0.0003048299,0.0000622693,0.00015161,0.0002559649,0.000003851228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002162738,"about_ca_system_score_gemma":0.00006196937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000079669,"about_ca_topic_score_gemma":0.00003116965,"domain_scores_codex":[0.9988297,0.0001324211,0.0004411999,0.0001739974,0.0002953415,0.0001272984],"domain_scores_gemma":[0.9991301,0.0003395676,0.0002978088,0.0001263726,0.00005232683,0.00005386535],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006125847,0.000437227,0.9186339,0.00005268763,0.000111427,0.00004410409,0.0008878697,0.00006003254,0.0716834,0.002509641,0.0001272114,0.004839886],"study_design_scores_gemma":[0.0006202168,0.0006504786,0.9587929,0.00007206707,0.00002716456,0.0002644836,0.0005313912,0.002306915,0.03408908,0.001743541,0.0008122038,0.00008951064],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9889013,0.0002674448,0.0007061489,0.0004076564,0.0007025811,0.0001506057,0.00008429444,0.00002124433,0.008758792],"genre_scores_gemma":[0.9981709,0.00002405617,0.001058913,0.00004620938,0.00007331572,0.00002168128,0.0001437367,0.000009204456,0.000451984],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04015902,"threshold_uncertainty_score":0.4863192,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02839320243389145,"score_gpt":0.3338872255547959,"score_spread":0.3054940231209045,"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."}}