{"id":"W2613103431","doi":"10.1177/0962280217702540","title":"Comparing heteroscedastic measurement systems with the probability of agreement","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Actua; University of Waterloo","funders":"","keywords":"Homoscedasticity; Heteroscedasticity; Metric (unit); Observational error; Computer science; Statistics; Mathematics; Engineering","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":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2491005,0.0001963715,0.0007489277,0.0001930507,0.0007492167,0.0005378898,0.00370574,0.0001293468,0.0009842395],"category_scores_gemma":[0.2642455,0.0000938111,0.00007258228,0.00048932,0.003859668,0.0001293842,0.0009970277,0.001314337,0.00005060629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003437005,"about_ca_system_score_gemma":0.0006091844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008102896,"about_ca_topic_score_gemma":0.0008219313,"domain_scores_codex":[0.9526764,0.01634418,0.00191822,0.001123183,0.02686098,0.001077035],"domain_scores_gemma":[0.963456,0.0296455,0.0004460865,0.003082256,0.002771659,0.0005984426],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001067526,0.001821126,0.1860478,0.0006931314,0.0001425976,0.0001146066,0.001029089,0.0009232444,0.001354864,0.1263264,0.006515109,0.6739646],"study_design_scores_gemma":[0.002358788,0.001462191,0.6582694,0.001280135,0.00003346442,0.000008780909,0.002336929,0.08004145,0.0007546898,0.2430131,0.01004713,0.0003939176],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03989564,0.000237175,0.9370567,0.007563225,0.0004715428,0.001661591,0.00001337777,0.000009726415,0.01309103],"genre_scores_gemma":[0.9373242,0.00001628138,0.0622551,0.00003607123,0.00007110191,0.0001958201,5.419494e-7,0.00000866726,0.00009219721],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8974286,"threshold_uncertainty_score":0.999929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7493861067260326,"score_gpt":0.6289003428450651,"score_spread":0.1204857638809674,"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."}}