{"id":"W2102888726","doi":"10.1002/cjs.5550360306","title":"On population‐based measures of agreement for binary classifications","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Cohen's kappa; Kappa; Statistic; Statistics; Population; Binary number; Inference; Binary data; Contrast (vision); Mathematics; Agreement; Econometrics; Computer science; Medicine; Artificial intelligence; Linguistics","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":[0.1620518,0.0008680741,0.002050713,0.00729518,0.001220305,0.003424222,0.002528791,0.002157739,0.002061177],"category_scores_gemma":[0.4733306,0.0006728368,0.002352249,0.004317383,0.005293442,0.004695741,0.004772914,0.003164683,0.0005496696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002218184,"about_ca_system_score_gemma":0.002306737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002129414,"about_ca_topic_score_gemma":0.001505293,"domain_scores_codex":[0.80596,0.1532159,0.006234399,0.008731492,0.02489417,0.0009640315],"domain_scores_gemma":[0.4765494,0.4526475,0.02021622,0.02702447,0.02250693,0.001055565],"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":[0.001736789,0.0003918289,0.1419921,0.001459041,0.004255861,0.0003534395,0.006339433,0.1381071,0.001459279,0.2876574,0.01076052,0.4054872],"study_design_scores_gemma":[0.0002566859,0.001383146,0.06224278,0.0008861799,0.0006140889,0.001031309,0.001973241,0.3926512,0.002904608,0.5264645,0.00902277,0.0005695123],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07538948,0.001088563,0.9136457,0.0006566884,0.0003449641,0.0004591584,0.0004836209,0.0005248439,0.007406906],"genre_scores_gemma":[0.7579608,0.0003515969,0.2389059,0.000275435,0.000138893,0.001083802,0.0005388171,0.0001507958,0.0005940899],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1620518,"threshold_uncertainty_score":0.8570219,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3749121106352241,"score_gpt":0.3604218302652674,"score_spread":0.0144902803699567,"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."}}