{"id":"W4410949386","doi":"10.1371/journal.pone.0322887","title":"Simulation study to evaluate when Plasmode simulation is superior to parametric simulation in comparing classification methods on high-dimensional data","year":2025,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Deutsche Forschungsgemeinschaft","keywords":"Parametric statistics; Computer science; Resampling; Context (archaeology); Ranking (information retrieval); Parametric model; Data mining; Algorithm; Machine learning; Statistics; 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":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05341943,0.001196976,0.001870957,0.001964837,0.0008974419,0.001744998,0.001790185,0.002955449,0.007846573],"category_scores_gemma":[0.2113524,0.0004642066,0.002452087,0.00164996,0.001719731,0.002584459,0.002373009,0.00459164,0.0008168677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001231046,"about_ca_system_score_gemma":0.001697422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002393808,"about_ca_topic_score_gemma":0.001584588,"domain_scores_codex":[0.9787624,0.01675038,0.001055926,0.001433553,0.001471647,0.0005259906],"domain_scores_gemma":[0.544386,0.4247677,0.007458134,0.01217174,0.0100722,0.001144114],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00691833,0.00194236,0.04030229,0.003183707,0.002707329,0.0004786095,0.0008744029,0.7640056,0.002977026,0.09062268,0.01285813,0.07312953],"study_design_scores_gemma":[0.000829435,0.002489328,0.006080096,0.000751437,0.0005650286,0.0002954834,0.0004838632,0.9376166,0.004460877,0.03760944,0.008693648,0.0001247706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3497107,0.005020599,0.6152031,0.003124337,0.001425699,0.003686073,0.005001854,0.001561568,0.01526601],"genre_scores_gemma":[0.7705916,0.0008365293,0.2155154,0.001083745,0.0001961889,0.005774401,0.003565256,0.0002860548,0.002150818],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9465806,"threshold_uncertainty_score":0.2825123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5743275149190448,"score_gpt":0.5237992248954791,"score_spread":0.05052829002356563,"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."}}