The Price of Correlated Tests: How Strict Should a Model Release Gate Be?

arXiv:2610.00993 · stat.ML, cs.LG, stat.ME · Submitted 2026-10-01 · Read on arXiv

stat.ML, cs.LG, stat.ME

Submitted: 2026-10-01

Updated: 2026-10-01

Comments: 6 pages, 1 figure, 4 tables. Submitted to ACDSA 2027

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 10× in this paper · explained in 2 episodes
• Accuracy — 3× in this paper · explained in 1 episode

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing
• From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier