{"id":"W4415966503","doi":"10.1101/2025.11.03.25339124","title":"A Generalizable Distribution Structure Analysis Algorithm with Audit-Ready Framework for Medical Research","year":2025,"lang":"","type":"preprint","venue":"medRxiv","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"L'Alliance Boviteq","funders":"","keywords":"Audit; Statistical inference; Parametric statistics; Identification (biology); Causal inference; Inference; Statistical hypothesis testing; Data quality","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":[],"consensus_categories":[],"category_scores_codex":[0.016957,0.001289333,0.001325445,0.003916617,0.0008443664,0.003024108,0.002971288,0.001452697,0.004932784],"category_scores_gemma":[0.07648479,0.0009259392,0.001611792,0.002388708,0.001412798,0.002703676,0.004176701,0.002585637,0.001666932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001972565,"about_ca_system_score_gemma":0.007560854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005365309,"about_ca_topic_score_gemma":0.004831209,"domain_scores_codex":[0.9917626,0.004088245,0.0008711856,0.001181826,0.001822106,0.000273942],"domain_scores_gemma":[0.9586733,0.0282878,0.002363713,0.003839257,0.006129046,0.0007068401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007496287,0.0003000802,0.01065261,0.0005117565,0.0002034679,0.0004185057,0.0006486271,0.236237,0.003782891,0.07791203,0.01071969,0.6578637],"study_design_scores_gemma":[0.0001161186,0.00004930021,0.0003372867,0.00005031722,0.00002608651,0.00009330641,0.00003478698,0.9452584,0.001568852,0.04965863,0.002785329,0.00002149255],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001636181,0.00004715531,0.9947382,0.0001221052,0.00001133416,0.000181411,0.00009944231,0.002922904,0.0002413179],"genre_scores_gemma":[0.04278113,0.00004738257,0.9557516,0.00009401481,0.00001920364,0.0004730843,0.000317843,0.0001989823,0.0003167141],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.016957,"threshold_uncertainty_score":0.08967829,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07896302758485607,"score_gpt":0.4498105906332047,"score_spread":0.3708475630483486,"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."}}