{"id":"W4417465483","doi":"10.48550/arxiv.2512.14000","title":"On the Hardness of Conditional Independence Testing In Practice","year":2025,"lang":"","type":"preprint","venue":"ArXiv.org","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Conditional independence; Independence (probability theory); Test (biology); Measure (data warehouse); Covariance; Conditional variance","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004794212,0.0006491588,0.0007723621,0.000435621,0.0005193185,0.0002025728,0.004345029,0.0005771134,0.0001616311],"category_scores_gemma":[0.03838622,0.0005794289,0.000203331,0.00187683,0.0005009678,0.0009040531,0.005158443,0.005478457,0.0001321535],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003540989,"about_ca_system_score_gemma":0.002091862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008801903,"about_ca_topic_score_gemma":0.00002805664,"domain_scores_codex":[0.992801,0.001924663,0.001368062,0.001661749,0.001553972,0.0006905427],"domain_scores_gemma":[0.9784616,0.01629733,0.001934025,0.002030598,0.001166074,0.000110332],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0001192287,0.0004188983,0.2939591,0.0002531021,0.0001617709,0.0001614916,0.002296243,0.5485436,0.000128985,0.1499684,0.000114013,0.003875106],"study_design_scores_gemma":[0.001253724,0.0002395343,0.4960082,0.004667389,0.0001783337,0.00006308269,0.0009238279,0.4704372,0.0007890667,0.02342036,0.0008762751,0.001143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4410812,0.0001972806,0.5111576,0.0105541,0.005797687,0.001595427,0.00005137122,0.0001555992,0.02940976],"genre_scores_gemma":[0.9825535,0.00002733759,0.01480109,0.001575068,0.0002358073,0.0001014257,0.00001357683,0.0000253621,0.0006667662],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5414724,"threshold_uncertainty_score":0.9996657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0728923376602707,"score_gpt":0.333310105440735,"score_spread":0.2604177677804643,"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."}}