{"id":"W2099077995","doi":"10.1177/0962280215601133","title":"Assessing agreement between two measurement systems: An alternative to the limits of agreement approach","year":2015,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Interchangeability; Agreement; Metric (unit); Limits of agreement; Computer science; Units of measurement; Physics; 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"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3749643,0.0003073855,0.0009721339,0.0006872685,0.0002732591,0.000609609,0.003568112,0.0001736044,0.0006258779],"category_scores_gemma":[0.2304376,0.0001750129,0.00009620861,0.002449658,0.0009993035,0.0003155131,0.0009649156,0.001505947,0.0001720804],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001002482,"about_ca_system_score_gemma":0.001365161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001354066,"about_ca_topic_score_gemma":0.0002028967,"domain_scores_codex":[0.9017674,0.04603641,0.003419851,0.001767464,0.0454216,0.00158723],"domain_scores_gemma":[0.9661933,0.02439417,0.0003365949,0.001891713,0.005061493,0.002122768],"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":[0.0001650629,0.001129789,0.007303854,0.00009439813,0.00009324845,0.00003767438,0.003018375,0.002225057,0.0002898197,0.0350492,0.007562968,0.9430305],"study_design_scores_gemma":[0.00698043,0.006074854,0.08956563,0.001806341,0.0001365812,0.00001517509,0.0811056,0.2376251,0.003379,0.4907228,0.08113442,0.001454089],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0114914,0.0003286806,0.9649674,0.004965167,0.0006921373,0.001886587,0.00003972745,0.00001259065,0.01561636],"genre_scores_gemma":[0.6608213,0.00001554669,0.3380594,0.0001872084,0.0004664141,0.0003149985,0.000007411359,0.00001721429,0.0001105187],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9415765,"threshold_uncertainty_score":0.7760447,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8455312682296875,"score_gpt":0.6788734831139276,"score_spread":0.1666577851157599,"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."}}