{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09697803,0.001587935,0.004206748,0.002469929,0.002996106,0.005875529,0.005259435,0.005563477,0.007683865],"category_scores_gemma":[0.4502288,0.001654824,0.002030503,0.002462369,0.02110977,0.01586335,0.009843901,0.01246466,0.001543301],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00340014,"about_ca_system_score_gemma":0.003929076,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002504788,"about_ca_topic_score_gemma":0.001256748,"domain_scores_codex":[0.9186925,0.05414338,0.003074648,0.01094552,0.01109685,0.002047001],"domain_scores_gemma":[0.326255,0.6212305,0.007032797,0.03665508,0.006648324,0.002178236],"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":[0.0005222734,0.0001311988,0.008740776,0.0004863669,0.0002945857,0.0006174746,0.001043737,0.07508664,0.0007819889,0.8511907,0.0104132,0.05069113],"study_design_scores_gemma":[0.00006842235,0.00005456676,0.0006356827,0.00009858618,0.00001602336,0.0001512084,0.000060867,0.06433031,0.0003445711,0.932446,0.001765333,0.00002841977],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04159628,0.002707895,0.9111813,0.02203392,0.0004401373,0.0002704284,0.0008845652,0.0007685323,0.02011692],"genre_scores_gemma":[0.7752013,0.001843133,0.2086741,0.005677662,0.001964514,0.001367315,0.001220622,0.0006560479,0.003395503],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.09697803,"threshold_uncertainty_score":0.512875,"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."}}