{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002042762,0.0000887048,0.0002411483,0.0004667626,0.0002643591,0.00003572125,0.0004119518,0.00004063152,0.0003981094],"category_scores_gemma":[0.005721161,0.0000681789,0.0001062086,0.0002815188,0.0001203752,0.00007447111,0.000003831333,0.00009967521,0.00001369522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001919061,"about_ca_system_score_gemma":0.001351617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005723071,"about_ca_topic_score_gemma":0.004787682,"domain_scores_codex":[0.9974285,0.0001208026,0.0009763683,0.000131566,0.001166267,0.000176449],"domain_scores_gemma":[0.9958609,0.001198028,0.0006276628,0.0002900095,0.001686805,0.0003366084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0002018499,0.0003447628,0.224225,0.0000525851,0.0001167015,0.0000734838,0.0009949384,0.05493079,0.0006040888,0.07178181,0.6110538,0.03562017],"study_design_scores_gemma":[0.001427579,0.001540131,0.8166478,0.0001365532,0.00007682503,0.00001678518,0.000472108,0.004947469,0.0004725631,0.1248692,0.04912782,0.0002652202],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3391194,0.0002638935,0.65055,0.004766508,0.001518236,0.0006408337,0.001897493,0.000004060993,0.001239618],"genre_scores_gemma":[0.9739378,0.00000792109,0.02553973,0.0002137773,0.0000528249,0.00000361305,0.00001284587,0.000005512534,0.0002259615],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6348184,"threshold_uncertainty_score":0.6849177,"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."}}