{"id":"W2592866053","doi":"10.1186/s13643-017-0441-7","title":"Effect of standardized training on the reliability of the Cochrane risk of bias assessment tool: a prospective study","year":2017,"lang":"en","type":"article","venue":"Systematic Reviews","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":65,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; St. Michael's Hospital; University of Toronto","funders":"","keywords":"Medicine; Kappa; Reliability (semiconductor); Physical therapy; Randomized controlled trial; Cohen's kappa; Risk assessment; MEDLINE; Clinical psychology; Statistics; Surgery","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":[0.2333902,0.000260131,0.002960625,0.00005200931,0.0004066641,0.000115745,0.002209717,0.00006080738,0.00008590473],"category_scores_gemma":[0.1990856,0.00008028286,0.0008971494,0.0003205758,0.0003737987,0.0001146932,0.0002303493,0.0002838175,0.00001294993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000994119,"about_ca_system_score_gemma":0.0001167205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006071364,"about_ca_topic_score_gemma":0.00002830655,"domain_scores_codex":[0.9651013,0.02518062,0.00429227,0.0005036243,0.004734975,0.0001872093],"domain_scores_gemma":[0.9689186,0.01664128,0.008014901,0.005526992,0.000863271,0.00003498728],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005409111,0.001780873,0.8551649,0.1044754,0.0007904719,0.000001276525,0.02143411,0.0003538141,0.001040458,0.002762141,0.001027072,0.01062854],"study_design_scores_gemma":[0.006353878,0.009482225,0.8459819,0.09302914,0.002627683,0.000003410328,0.01512998,0.001266922,0.009308466,0.01538805,0.000807728,0.0006206254],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9699941,0.0004119044,0.0003685017,0.0002565146,0.0004060498,0.02576275,0.00002941522,0.000004742484,0.002766029],"genre_scores_gemma":[0.9987981,0.0001019979,0.0001476091,0.000009002571,0.0000168618,0.0008320037,1.019976e-7,0.000006427144,0.00008794246],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03430468,"threshold_uncertainty_score":0.8076609,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2307356376426931,"score_gpt":0.4609718262253066,"score_spread":0.2302361885826134,"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."}}