{"id":"W4399722044","doi":"10.1016/j.jclinepi.2024.111428","title":"Panel stacking is a threat to consensus statement validity","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Impact; Children's Hospital Research Institute of Manitoba; Ottawa Hospital; Alberta Health; McMaster University; Jewish General Hospital; University of Ottawa; Ottawa Public Health; Hamilton Health Sciences","funders":"National Institute of General Medical Sciences; Norwegian Institute of Public Health; HORIZON EUROPE Framework Programme; Università di Bologna; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Pfizer; European Commission; Genentech; AstraZeneca; Eli Lilly and Company; National Science Foundation","keywords":"Delphi method; Transparency (behavior); Delphi; Political science; Scientific consensus; Statement (logic); Public relations; Law and economics; Law; Economics; Computer 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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.120328,0.0001236201,0.001279061,0.0002095041,0.0001467189,0.00004893068,0.000597451,0.0003457535,0.0006267516],"category_scores_gemma":[0.133801,0.00009223174,0.0005796673,0.000352708,0.0006269758,0.00009185539,0.0001526412,0.001295168,0.0001841171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001969146,"about_ca_system_score_gemma":0.001129933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006076014,"about_ca_topic_score_gemma":0.000182176,"domain_scores_codex":[0.9845734,0.009746734,0.004015291,0.0003403613,0.0006572952,0.0006669543],"domain_scores_gemma":[0.9267665,0.07098687,0.0007970098,0.0002499183,0.0005109792,0.0006887195],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002834703,0.0001677415,0.09727842,0.00005888017,0.0002216873,0.0006591466,0.002705082,0.00006057988,0.00003055757,0.04196564,0.7442737,0.1122951],"study_design_scores_gemma":[0.0002545069,0.001010797,0.01560521,0.0002599427,0.00004391708,0.00004001476,0.001293922,0.0003148249,0.00003065511,0.1613625,0.8196282,0.0001555312],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5194855,0.001018852,0.02112199,0.4437132,0.005033979,0.0004989139,0.00002662066,0.000123382,0.008977555],"genre_scores_gemma":[0.9673559,0.002599913,0.01896047,0.007480476,0.00234816,0.000007922515,5.137755e-7,0.00001965283,0.00122696],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4478705,"threshold_uncertainty_score":0.9058074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8741846453546281,"score_gpt":0.7067478297603079,"score_spread":0.1674368155943202,"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."}}