{"id":"W2153928704","doi":"10.1503/cmaj.1031981","title":"Tips for learners of evidence-based medicine: 3. Measures of observer variability (kappa statistic)","year":2004,"lang":"en","type":"article","venue":"Canadian Medical Association Journal","topic":"Radiology practices and education","field":"Medicine","cited_by":485,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Notice; Kappa; Cohen's kappa; Interpretation (philosophy); Statistic; Medicine; Medical physics; Computer science; Statistics; Mathematics; Machine learning; Law","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06911103,0.002147615,0.002599345,0.007858205,0.001361388,0.004224928,0.00422416,0.006547867,0.01321232],"category_scores_gemma":[0.3398944,0.00151999,0.002437414,0.00408838,0.003064774,0.007990448,0.003527419,0.00737075,0.01288168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001498399,"about_ca_system_score_gemma":0.003115841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001966541,"about_ca_topic_score_gemma":0.004750254,"domain_scores_codex":[0.8969103,0.05710827,0.01075749,0.001879983,0.03247993,0.0008640175],"domain_scores_gemma":[0.6978987,0.2158482,0.01582469,0.008976421,0.05681734,0.00463466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004750867,0.0003091365,0.009084477,0.00246652,0.0002397359,0.0002026213,0.001720987,0.000682206,0.0008752813,0.003350053,0.3806385,0.5999554],"study_design_scores_gemma":[0.002212266,0.004357342,0.1081877,0.0258241,0.001483054,0.01033526,0.01246152,0.02601036,0.01486433,0.2095208,0.5826478,0.002095552],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01404101,0.02104494,0.6443205,0.2456089,0.01170268,0.003428316,0.005910711,0.01773934,0.03620379],"genre_scores_gemma":[0.0535999,0.005417612,0.9072241,0.01507362,0.00460843,0.004358244,0.0009772282,0.002451413,0.006289525],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.06911103,"threshold_uncertainty_score":0.3654984,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1439840874599849,"score_gpt":0.357593389097819,"score_spread":0.213609301637834,"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."}}