{"id":"W4408875896","doi":"10.1136/bmj-2024-081199","title":"Development of ROBUST-RCT: Risk Of Bias instrument for Use in SysTematic reviews-for Randomised Controlled Trials","year":2025,"lang":"en","type":"article","venue":"BMJ","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; McMaster University; Impact","funders":"","keywords":"Randomized controlled trial; Systematic review; Medicine; Computer science; MEDLINE; Medical physics; Surgery; Biology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6239677,0.0002883015,0.02286902,0.0007422405,0.00006348168,0.0001726726,0.0008869923,0.00008958846,0.0002990678],"category_scores_gemma":[0.7234228,0.0001142782,0.005511835,0.000966475,0.00002637061,0.0001034161,0.00005995679,0.00004980483,0.00003536271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005165141,"about_ca_system_score_gemma":0.0002894507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008474495,"about_ca_topic_score_gemma":0.00008553059,"domain_scores_codex":[0.8786352,0.0500024,0.06726624,0.0008256448,0.002974961,0.0002955619],"domain_scores_gemma":[0.7419592,0.2010258,0.05079599,0.003679512,0.002434718,0.0001047612],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"randomized_trial","study_design_scores_codex":[0.03723275,0.002088866,0.02716004,0.3295139,0.03370639,0.000002715711,0.008583696,0.005300044,0.001953152,0.01957421,0.3799359,0.1549483],"study_design_scores_gemma":[0.5138626,0.0003561765,0.003938058,0.0739643,0.0295318,0.000003704311,0.005690674,0.1976512,0.003572469,0.010913,0.1589964,0.001519681],"study_design_candidate":"randomized_trial","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1299534,0.01056842,0.6993592,0.0004992477,0.0009646367,0.1574206,0.0001055487,0.000005581667,0.001123387],"genre_scores_gemma":[0.198537,0.0005031943,0.7459204,0.0002340177,0.00008343452,0.03681273,0.00002175726,0.00002664468,0.01786084],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4766298,"threshold_uncertainty_score":0.9916375,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8589632687708348,"score_gpt":0.5519271193988864,"score_spread":0.3070361493719485,"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."}}