{"id":"W2130302022","doi":"10.1186/2046-4053-3-144","title":"Effect of standardized training on the reliability of the Cochrane risk of bias assessment tool: a study protocol","year":2014,"lang":"en","type":"article","venue":"Systematic Reviews","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; Hospital for Sick Children; Public Health Ontario","funders":"Florida International University","keywords":"Medicine; Kappa; Reliability (semiconductor); Confidence interval; Protocol (science); Randomized controlled trial; Risk assessment; Meta-analysis; Cohen's kappa; MEDLINE; Systematic review; Medical physics; Statistics; Alternative medicine; Computer science; Internal medicine","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","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7271648,0.0005061277,0.01604555,0.0001573067,0.0001546285,0.0001474488,0.003033761,0.00009112715,0.0009300526],"category_scores_gemma":[0.4542856,0.0001201108,0.005041047,0.001689836,0.000171229,0.00008121437,0.0001908182,0.0003125907,0.0001068437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004823891,"about_ca_system_score_gemma":0.0001110813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001838414,"about_ca_topic_score_gemma":0.00001171435,"domain_scores_codex":[0.5750602,0.3771877,0.03459625,0.001003637,0.01186262,0.0002895732],"domain_scores_gemma":[0.847917,0.08858546,0.04745935,0.0141514,0.001806181,0.00008062971],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0003126182,0.001618137,0.1359554,0.7922382,0.003076185,0.000001087364,0.01674091,0.0007170305,0.0004880589,0.007684187,0.01139807,0.02977011],"study_design_scores_gemma":[0.02761192,0.03385115,0.1440611,0.4360504,0.04854677,0.00006338403,0.03218724,0.08323159,0.005496242,0.0189597,0.1658886,0.004051883],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"protocol","genre_gemma":"empirical","genre_scores_codex":[0.2624574,0.0002447178,0.006329673,0.0001545171,0.0002456262,0.7247317,0.00002717224,0.000005122609,0.005804038],"genre_scores_gemma":[0.8646634,0.00001141554,0.0007113423,0.00002572444,0.00002462251,0.1341949,3.061753e-7,0.00001533359,0.0003530621],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6022059,"threshold_uncertainty_score":0.9999833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5401063625017969,"score_gpt":0.5570791840396857,"score_spread":0.01697282153788882,"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."}}