{"id":"W4410221436","doi":"10.1016/j.jclinepi.2025.111824","title":"Assessing the feasibility and impact of clinical trial trustworthiness checks via an application to Cochrane Reviews: Stage 2 of the INSPECT-SR project","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Department of Health and Social Care; National Institute for Health and Care Research","keywords":"Trustworthiness; Stage (stratigraphy); Systematic review; Meta-analysis; Medicine; Cochrane collaboration; Clinical trial; Medical physics; MEDLINE; Computer science; Internal medicine; Cochrane Library; Political science","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":[0.8742239,0.007176443,0.01442879,0.03480887,0.005994764,0.01681879,0.01080027,0.01034584,0.01566897],"category_scores_gemma":[0.9525712,0.01107623,0.02836627,0.03065633,0.01028176,0.0162822,0.02256474,0.01141709,0.004587464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01830746,"about_ca_system_score_gemma":0.1080519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003680804,"about_ca_topic_score_gemma":0.006536468,"domain_scores_codex":[0.09028353,0.673065,0.1711639,0.01293438,0.05027128,0.00228192],"domain_scores_gemma":[0.01546397,0.7841416,0.06289244,0.06181824,0.07373903,0.0019447],"domain_codex":"methods","domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.01794005,0.001442782,0.02856708,0.2817956,0.02245495,0.0006347701,0.03348333,0.007301503,0.00387847,0.01952149,0.04044478,0.5425352],"study_design_scores_gemma":[0.04289136,0.02182363,0.07019094,0.3293287,0.05521366,0.002209204,0.009334856,0.1147126,0.02695658,0.09902221,0.2240395,0.004276736],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"protocol","genre_gemma":"empirical","genre_scores_codex":[0.02465636,0.009491174,0.3477155,0.008943939,0.00244827,0.5885673,0.00578575,0.005569337,0.00682237],"genre_scores_gemma":[0.02397824,0.001077016,0.5832952,0.0008457334,0.0002309354,0.3884995,0.001162419,0.0004637263,0.0004473334],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1257761,"threshold_uncertainty_score":0.1551043,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9158969746153991,"score_gpt":0.7556013264309793,"score_spread":0.1602956481844198,"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."}}