{"id":"W2146976162","doi":"10.1002/(sici)1097-0258(20000215)19:3<373::aid-sim337>3.0.co;2-y","title":"Testing the equality of two dependent kappa statistics","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Statistics; Kappa; Correlation; Monte Carlo method; Mathematics; Cohen's kappa; Goodness of fit; Dependency (UML); Sample size determination; Variable (mathematics); Computer science; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01463562,0.0001596583,0.0004365018,0.0001061005,0.0001287112,0.00003519339,0.0008215466,0.00003758503,0.00546636],"category_scores_gemma":[0.01668274,0.00008785782,0.00002191709,0.0007223649,0.0006210688,0.00005408334,0.00007111597,0.0002935005,0.0001087362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006649305,"about_ca_system_score_gemma":0.00009942054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001001015,"about_ca_topic_score_gemma":0.0006780621,"domain_scores_codex":[0.9938334,0.0007102268,0.001599391,0.0003923825,0.003155049,0.0003095853],"domain_scores_gemma":[0.9887842,0.009418523,0.0003409826,0.0007828973,0.000582,0.00009143108],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009540518,0.0002852184,0.09400722,0.00006967088,0.00003091168,0.00004357227,0.003204483,0.00447572,0.00116882,0.09661052,0.04216598,0.7578425],"study_design_scores_gemma":[0.001895219,0.0004329739,0.1491368,0.0001718927,0.00005242628,0.000006656131,0.001584292,0.01274943,0.0001400724,0.8244635,0.00915303,0.0002137071],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1872347,0.0005463707,0.7453173,0.003448757,0.001312718,0.001222724,0.001363933,0.00003883952,0.05951462],"genre_scores_gemma":[0.922231,0.00005878457,0.07571973,0.0005517206,0.0001681844,0.00001450345,0.00001900848,0.00001007761,0.001226982],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7576288,"threshold_uncertainty_score":0.9954428,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2670104097609483,"score_gpt":0.4556427207423286,"score_spread":0.1886323109813803,"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."}}