point in time

The most expensive leakage bug in feature-store ML: training joins that grab feature values from after the label event. The timeline that exposes it, the one query that proves it, and the fix that survives audit.

The bug that makes offline metrics a lie: training on information that didn't exist at prediction time. A concrete fraud example with timestamps, the as-of join that fixes it, and the label-maturity trap automated retraining adds on top.