{"id":"W2413587883","doi":"10.1097/dss.0000000000000553","title":"A Randomized, Blinded Study to Validate the Merz Hand Grading Scale for Use in Live Assessments","year":2015,"lang":"en","type":"article","venue":"Dermatologic Surgery","topic":"Orthopedic Surgery and Rehabilitation","field":"Medicine","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Inter-rater reliability; Kappa; Medicine; Grading scale; Grading (engineering); Cohen's kappa; Randomized controlled trial; Physical therapy; Blinded study; Rating scale; Surgery; Psychology; Statistics; Mathematics","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":[0.00552642,0.000183843,0.0009583942,0.0003185442,0.0001145055,0.00005315211,0.00006996489,0.00007966136,0.0000109095],"category_scores_gemma":[0.004833565,0.0001075134,0.0002601431,0.0004287247,0.0001354386,0.0001840758,0.0000483985,0.0001590173,0.00002678466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006143937,"about_ca_system_score_gemma":0.0001928178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000137997,"about_ca_topic_score_gemma":0.00006986245,"domain_scores_codex":[0.9973432,0.0009614075,0.0006590643,0.0003296256,0.0003370401,0.0003696656],"domain_scores_gemma":[0.9900759,0.009086257,0.0001489232,0.0003161041,0.0001934589,0.0001793142],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0249623,0.000867548,0.9650684,0.0000439678,0.0001094168,0.0001157224,0.004045352,0.00002318638,0.00002000623,0.00001676419,0.002872395,0.001854928],"study_design_scores_gemma":[0.4152411,0.001170827,0.4670612,0.0009927691,0.001532485,0.000936717,0.09067885,0.005534057,0.002288215,0.003092981,0.00986411,0.001606737],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9932969,0.0001146019,0.0008377822,0.001693581,0.0007690828,0.003101411,0.000004635545,0.0000516504,0.0001303921],"genre_scores_gemma":[0.9973674,0.00001459203,0.0004787478,0.001136043,0.00006203621,0.0006942715,0.00002322212,0.00001792795,0.0002057008],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4980073,"threshold_uncertainty_score":0.5786577,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1576833898685142,"score_gpt":0.3798585321806786,"score_spread":0.2221751423121643,"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."}}