{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.007256483,0.000999482,0.002655558,0.0007013031,0.0009144876,0.0005070522,0.001864541,0.002561311,0.004861589],"category_scores_gemma":[0.03261684,0.0007713316,0.0006140441,0.00416375,0.001013703,0.00007839745,0.001173748,0.00449992,0.00001978175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00048673,"about_ca_system_score_gemma":0.002331471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004649234,"about_ca_topic_score_gemma":0.0003061751,"domain_scores_codex":[0.9880346,0.002603912,0.001816906,0.002264404,0.003511758,0.001768438],"domain_scores_gemma":[0.9719381,0.02133896,0.0006874094,0.002382987,0.002758548,0.0008940417],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002458801,0.0004546706,0.002846542,0.002602862,0.004513348,0.00008960687,0.0003796227,0.0001100031,0.000007399157,0.8656856,0.002928761,0.1201357],"study_design_scores_gemma":[0.0005401714,0.000298353,0.001247129,0.001749299,0.003677559,0.000008756209,0.0001142725,0.2088352,0.0002890092,0.7767999,0.005734305,0.0007060823],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001403888,0.0002992158,0.9745134,0.001869021,0.000867959,0.002051275,0.01861706,0.00009392565,0.0002843001],"genre_scores_gemma":[0.005920881,0.0003978405,0.9885715,0.0001476017,0.001087382,0.0007539025,0.002185435,0.00007156516,0.0008639022],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2087252,"threshold_uncertainty_score":0.9994738,"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."}}