{"id":"W2027833822","doi":"10.1371/journal.pone.0096920","title":"Poor Reliability between Cochrane Reviewers and Blinded External Reviewers When Applying the Cochrane Risk of Bias Tool in Physical Therapy Trials","year":2014,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":125,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Health Services; Alberta Health; University of Alberta","funders":"Alberta Innovates; Killam Trusts; Fondation pour la Recherche Médicale; University of Alberta; Canadian Institutes of Health Research; Physiotherapy Foundation of Canada; Alberta Innovates - Health Solutions; Women and Children's Health Research Institute","keywords":"Meta-analysis; Medicine; Systematic review; Randomized controlled trial; Physical therapy; MEDLINE; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reproducibility","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"evaluation","study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7825037,0.005684729,0.01851199,0.02385377,0.004124051,0.0111713,0.009418225,0.008665399,0.004493807],"category_scores_gemma":[0.9080584,0.006100999,0.01977711,0.02087192,0.009619364,0.01071167,0.01089169,0.006256822,0.001761508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008317084,"about_ca_system_score_gemma":0.02204719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00374599,"about_ca_topic_score_gemma":0.005478794,"domain_scores_codex":[0.07759128,0.5456726,0.2941353,0.02526035,0.05555366,0.00178681],"domain_scores_gemma":[0.03768147,0.6997509,0.1258656,0.04419968,0.09086777,0.001634694],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"systematic_review","study_design_gemma":"observational","study_design_scores_codex":[0.01504697,0.000322571,0.0627668,0.5664136,0.08750074,0.00128594,0.02909644,0.00501068,0.003436042,0.01345801,0.0353738,0.1802884],"study_design_scores_gemma":[0.01907703,0.003620482,0.09357367,0.4528044,0.1194079,0.003480781,0.009082714,0.03603551,0.0168977,0.09301957,0.1492426,0.003757575],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0745585,0.295572,0.3707998,0.0217411,0.02632162,0.1716534,0.01598636,0.003707075,0.01966016],"genre_scores_gemma":[0.3720359,0.02025349,0.3338251,0.008207289,0.002881504,0.2550596,0.004111603,0.001217494,0.00240803],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2174963,"threshold_uncertainty_score":0.2682118,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7283816013967103,"score_gpt":0.4958130527997156,"score_spread":0.2325685485969947,"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."}}