{"id":"W6885830477","doi":"10.1371/journal.pone.0233732.s001","title":"Agreement test for Newcastle–Ottawa scale scores evaluated by reviewers.","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Scale (ratio); Measure (data warehouse); Test (biology); Level of measurement; Reliability (semiconductor)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.11069,0.0009452438,0.002791732,0.008157984,0.002084393,0.001930429,0.002797012,0.001600064,0.01085415],"category_scores_gemma":[0.3738441,0.00108878,0.004388799,0.004556672,0.001520142,0.003426628,0.004262628,0.001949211,0.002851806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001894787,"about_ca_system_score_gemma":0.004816954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004518913,"about_ca_topic_score_gemma":0.01006966,"domain_scores_codex":[0.8476031,0.07188307,0.03757829,0.01118517,0.03026789,0.001482454],"domain_scores_gemma":[0.6008099,0.2632272,0.0333227,0.02506676,0.07575756,0.001815802],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01388974,0.0007111936,0.4395816,0.02078176,0.02353107,0.0005010079,0.01804535,0.005834705,0.005827409,0.01596277,0.1134437,0.3418898],"study_design_scores_gemma":[0.003316332,0.003802918,0.6778601,0.008358249,0.01226629,0.003468357,0.009063467,0.03968601,0.01425186,0.04491487,0.1811453,0.001866132],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3457452,0.02323963,0.4318428,0.002752042,0.005447585,0.02979101,0.06692288,0.005203422,0.0890554],"genre_scores_gemma":[0.7883096,0.001630597,0.1598138,0.0005544659,0.0004012329,0.02592141,0.0142508,0.001318396,0.007799625],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8893101,"threshold_uncertainty_score":0.5853914,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3904297146738943,"score_gpt":0.4112590352549984,"score_spread":0.02082932058110404,"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."}}