{"id":"W4415372161","doi":"10.21203/rs.3.rs-7830468/v1","title":"Explaining Black-Box Models Through Statistical Inference","year":2025,"lang":"","type":"preprint","venue":"Research Square","topic":"Data Analysis with R","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"","keywords":"Spurious relationship; Heuristics; Pairwise comparison; Statistical inference; Heuristic; Statistical model; Inference; Statistical hypothesis testing; Stability (learning theory)","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":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.009040215,0.001233905,0.001934281,0.001801672,0.001524734,0.004533238,0.01209101,0.001069903,0.001325045],"category_scores_gemma":[0.006233115,0.001260935,0.0005441468,0.005450861,0.002224623,0.003130402,0.03202624,0.007965884,0.00210318],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001220754,"about_ca_system_score_gemma":0.007789653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003002579,"about_ca_topic_score_gemma":0.0003046487,"domain_scores_codex":[0.9760283,0.005118302,0.002130865,0.005165298,0.007768117,0.00378909],"domain_scores_gemma":[0.9765322,0.009350685,0.0004678645,0.008159214,0.004435799,0.001054268],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000107296,0.0006049248,0.0004954947,0.002684782,0.0005194105,0.000546663,0.01302407,0.07281116,0.00001677827,0.8470598,0.01834077,0.04378888],"study_design_scores_gemma":[0.0004915015,0.0003015162,0.0003493043,0.003433113,0.0000735556,0.000004881976,0.001475393,0.7743087,0.0001398696,0.211063,0.007409861,0.0009492472],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005003539,0.000872679,0.9399039,0.002152809,0.000657295,0.001783667,0.001983093,0.0002544882,0.05189167],"genre_scores_gemma":[0.788655,0.005592111,0.1956476,0.0003181403,0.000572416,0.0006807871,0.001133037,0.00008885648,0.007312012],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7881547,"threshold_uncertainty_score":0.9997752,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1905112513852044,"score_gpt":0.4710558457389411,"score_spread":0.2805445943537367,"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."}}