SOURCE-LINKED INTELLIGENCE

Selective Inference for CART with Binary Outcomes

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Binary classification trees select subgroups using the same outcomes later used to assess their differences. We develop finite-sample conditional tests of a common success probability within a parent selected by deterministic Gini CART. The construction retains all eligible cutpoints and conditions on the selected split, its ancestor path, the parent success total, and outside outcomes. The resulting uniform label fiber gives an exact count distribution, while a reversible parallel Monte Carlo construction yields super-uniform inclusive and exactly uniform tie-randomized p-values for any presp

Read original source ↗ Open in workspace

recordType

paper

region

Global