{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002543408,0.0002474293,0.0005956416,0.0007346802,0.000127244,0.00009643045,0.0003676891,0.00009749982,0.0001113398],"category_scores_gemma":[0.02259355,0.0002452824,0.00002758493,0.001174123,0.00001781801,0.0001995425,0.000289064,0.0002439059,0.00007127582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002679105,"about_ca_system_score_gemma":0.00006395375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009790968,"about_ca_topic_score_gemma":0.00005253737,"domain_scores_codex":[0.9963046,0.0009589446,0.0008570888,0.0007940071,0.0007975677,0.0002878247],"domain_scores_gemma":[0.9839126,0.01436092,0.0001505297,0.001065049,0.000387262,0.0001235724],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003863809,0.003431825,0.008150265,0.0000858056,0.0001063216,7.940662e-7,0.0009821471,0.9599413,0.001105807,0.003869815,0.00002942096,0.02191007],"study_design_scores_gemma":[0.0008012995,0.0003003622,0.07402156,0.0002664745,0.0001940558,1.501097e-8,0.0000869133,0.887005,0.0006302408,0.03646705,0.000009608979,0.0002173769],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5380001,0.000003792391,0.4602879,0.0002143818,0.00005336463,0.001261245,0.00002741229,0.00004969776,0.0001021334],"genre_scores_gemma":[0.5886865,2.418131e-7,0.4109291,0.0002100023,0.00002487383,0.00004886575,0.00003161788,0.00001711843,0.00005161469],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0729363,"threshold_uncertainty_score":0.9999999,"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."}}