{"id":"W4402082756","doi":"10.1016/j.jclinepi.2024.111512","title":"A survey of experts to identify methods to detect problematic studies: stage 1 of the INveStigating ProblEmatic Clinical Trials in Systematic Reviews project","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Research for Patient Benefit Programme; Department of Health and Social Care; National Institute for Health and Care Research; NIHR Biomedical Research Centre, Royal Marsden NHS Foundation Trust/Institute of Cancer Research","keywords":"Stage (stratigraphy); Systematic review; Medicine; MEDLINE; Data science; Computer science; Political science; 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":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7262079,0.004097173,0.005251032,0.0269419,0.008342079,0.01214855,0.008552479,0.009821978,0.01071854],"category_scores_gemma":[0.8007193,0.006542807,0.007682931,0.01521874,0.007026708,0.01695801,0.02459375,0.01332821,0.007829172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0157329,"about_ca_system_score_gemma":0.0913233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002958215,"about_ca_topic_score_gemma":0.00624464,"domain_scores_codex":[0.2389773,0.5272585,0.1654226,0.01485372,0.04840061,0.00508729],"domain_scores_gemma":[0.09711123,0.5548794,0.074288,0.05949552,0.2004251,0.01380083],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.00236694,0.00137134,0.02317006,0.06673496,0.001625155,0.0008790867,0.1466924,0.0017636,0.007813391,0.007311951,0.1368364,0.6034346],"study_design_scores_gemma":[0.004601311,0.003773865,0.03948719,0.1178118,0.00281476,0.001755004,0.06071292,0.0120403,0.009604693,0.03626283,0.7092974,0.001837924],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"protocol","genre_gemma":"empirical","genre_scores_codex":[0.04889562,0.009507878,0.3509114,0.03453387,0.002751753,0.5295415,0.00683263,0.005366157,0.01165918],"genre_scores_gemma":[0.02780592,0.002395632,0.5863166,0.007918724,0.0004230184,0.3705116,0.001771189,0.0007375701,0.002119727],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2737921,"threshold_uncertainty_score":0.3376345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.98807501326807,"score_gpt":0.8130868499801053,"score_spread":0.1749881632879647,"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."}}