Saved in:
Bibliographic Details
Main Author: Roth, Simon
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.04199
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914618777010176
author Roth, Simon
author_facet Roth, Simon
contents Twenty-eight within-subject counterfactual experiments across 2,047 iid tabular datasets, plus a boundary experiment on 129 temporal datasets, measure the severity of four data leakage classes in machine learning. Class I (estimation: fitting scalers on full data) is negligible: all nine conditions produce $|ΔAUC| \leq 0.005$. Class II (selection: peeking, seed cherry-picking) is substantial: the measured effect is consistent with about 90% noise exploitation inflating reported scores. Class III (memorization) scales with model capacity: $d_z$ = 0.37 (Naive Bayes) to 1.11 (Decision Tree) at 10% duplication. Class IV (boundary) is invisible under random cross-validation. Within this iid tabular regime, the textbook emphasis is inverted: normalization leakage matters least; selection leakage at practical dataset sizes matters most.
format Preprint
id arxiv_https___arxiv_org_abs_2604_04199
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Which Leakage Types Matter? A Quantitative Landscape Across 2,047 Benchmark Datasets
Roth, Simon
Machine Learning
Twenty-eight within-subject counterfactual experiments across 2,047 iid tabular datasets, plus a boundary experiment on 129 temporal datasets, measure the severity of four data leakage classes in machine learning. Class I (estimation: fitting scalers on full data) is negligible: all nine conditions produce $|ΔAUC| \leq 0.005$. Class II (selection: peeking, seed cherry-picking) is substantial: the measured effect is consistent with about 90% noise exploitation inflating reported scores. Class III (memorization) scales with model capacity: $d_z$ = 0.37 (Naive Bayes) to 1.11 (Decision Tree) at 10% duplication. Class IV (boundary) is invisible under random cross-validation. Within this iid tabular regime, the textbook emphasis is inverted: normalization leakage matters least; selection leakage at practical dataset sizes matters most.
title Which Leakage Types Matter? A Quantitative Landscape Across 2,047 Benchmark Datasets
topic Machine Learning
url https://arxiv.org/abs/2604.04199