{"id":"W4410629997","doi":"10.1136/bmjopen-2024-096107","title":"Completeness of reporting of simulation studies on responder analysis methods and simulation performance: a methodological survey","year":2025,"lang":"en","type":"review","venue":"BMJ Open","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Joseph’s Healthcare Hamilton; Impact; McMaster University; Ontario Clinical Oncology Group","funders":"","keywords":"Medicine; Binary data; Data extraction; Covariate; Statistics; Bayesian probability; Computer science; Binary number; MEDLINE; Mathematics","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":"reporting","study_design":"observational","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.448467,0.0002583682,0.004520493,0.0007247415,0.0003287609,0.00003258582,0.0005045748,0.0004779393,0.00004643455],"category_scores_gemma":[0.4941453,0.0001940978,0.0004050455,0.002753351,0.0004282714,0.0001317951,0.0004893036,0.0002513694,6.777947e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007277194,"about_ca_system_score_gemma":0.0007979152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005737933,"about_ca_topic_score_gemma":0.0005262233,"domain_scores_codex":[0.7217356,0.272261,0.004447198,0.000742242,0.0005249137,0.0002890091],"domain_scores_gemma":[0.6990573,0.2938178,0.005938294,0.0004838719,0.0006567125,0.00004607091],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.005954827,0.00007891035,0.01082286,0.01066135,0.003536149,0.000005502723,0.003747035,0.05638341,0.000001340597,0.0002660099,0.000009515586,0.9085331],"study_design_scores_gemma":[0.001772394,0.001257278,0.7687811,0.04600427,0.02607676,0.000005127726,0.006468384,0.02469569,0.00007170688,0.00204795,0.1199989,0.002820452],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.009900203,0.939253,0.03906266,0.00003306329,0.0006346517,0.009754771,0.0001112744,0.00003619972,0.001214189],"genre_scores_gemma":[0.006130913,0.9005426,0.09190927,0.00003529594,0.00006307157,0.0003352506,0.0001153323,0.00001914242,0.0008490755],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9057126,"threshold_uncertainty_score":0.7915079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9393145250890469,"score_gpt":0.7662681919119205,"score_spread":0.1730463331771264,"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."}}