{"id":"W4406682337","doi":"10.1016/j.jclinepi.2025.111684","title":"Risk of bias assessment tools often addressed items not related to risk of bias and used numerical scores","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Risk assessment; Medicine; Statistics; Environmental health; Computer science; Psychology; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6611201,0.004176794,0.0137789,0.04313065,0.003688995,0.01373472,0.007503231,0.007789996,0.007667899],"category_scores_gemma":[0.8846158,0.002794999,0.01287779,0.0408091,0.01045175,0.01995515,0.01000409,0.007289747,0.001561925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01536028,"about_ca_system_score_gemma":0.02522759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003141347,"about_ca_topic_score_gemma":0.005091488,"domain_scores_codex":[0.1621403,0.4871583,0.2820463,0.01137297,0.05536884,0.001913297],"domain_scores_gemma":[0.0393133,0.7871255,0.1138718,0.0161297,0.0427215,0.0008380868],"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":[0.002437248,0.0002272357,0.03616549,0.5353922,0.02542083,0.0004539439,0.01088132,0.003388119,0.00133796,0.03482218,0.02877128,0.3207022],"study_design_scores_gemma":[0.003480732,0.001179412,0.03582842,0.6402341,0.03454218,0.001942548,0.004601739,0.0123577,0.005906515,0.1396645,0.1186453,0.001616799],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02550452,0.3749244,0.4425375,0.03285804,0.01072679,0.08389309,0.01250463,0.001311231,0.01573981],"genre_scores_gemma":[0.275084,0.07715393,0.4742627,0.01710078,0.00376991,0.1472555,0.003406367,0.0005224918,0.001444342],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3388799,"threshold_uncertainty_score":0.4178994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9081162111132932,"score_gpt":0.674554332401094,"score_spread":0.2335618787121992,"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."}}