{"id":"W4412872054","doi":"10.1101/2025.07.17.25331623","title":"Evaluation of the replicability of systematic reviews with meta-analyses of the effects of health interventions","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; Ottawa Hospital; Bruyère; University of Ottawa","funders":"National Health and Medical Research Council; Medical Research Council; National Institute for Health and Care Research","keywords":"Psychological intervention; Meta-analysis; Systematic review; Psychology; Medicine; MEDLINE; Political science; Psychiatry; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.830501,0.006578812,0.02043339,0.01772624,0.003027834,0.01014282,0.01225726,0.0103012,0.006970806],"category_scores_gemma":[0.9450594,0.006302385,0.04703198,0.01914162,0.01627145,0.01598647,0.01252705,0.008863167,0.001835544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006772025,"about_ca_system_score_gemma":0.006512224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00204015,"about_ca_topic_score_gemma":0.002009753,"domain_scores_codex":[0.08449922,0.6645838,0.1700238,0.02739767,0.05220827,0.001287273],"domain_scores_gemma":[0.0287711,0.8079425,0.05118282,0.08997317,0.02136363,0.000766902],"domain_codex":"methods","domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"meta_analysis","study_design_gemma":"observational","study_design_scores_codex":[0.02982581,0.0006029135,0.09873021,0.2106604,0.4608696,0.00195578,0.01148631,0.01710536,0.003385249,0.01936579,0.006083093,0.1399294],"study_design_scores_gemma":[0.03444523,0.02113055,0.1271988,0.1091369,0.4200365,0.003994995,0.004116078,0.08167844,0.01398081,0.134622,0.04699332,0.002666418],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08757482,0.1641642,0.6179147,0.01024721,0.01256204,0.08608545,0.007954087,0.002669199,0.01082822],"genre_scores_gemma":[0.6566486,0.00901706,0.2181969,0.002562403,0.001887038,0.1068623,0.003024089,0.000788171,0.00101337],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.169499,"threshold_uncertainty_score":0.2090226,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9200655670706293,"score_gpt":0.6388862532246138,"score_spread":0.2811793138460155,"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."}}