Integrity is a single Go binary that ingests 22 CMS datasets, scores 1.47 million Medicare providers across 10 years of history, and serves an interactive investigation dashboard. It detects anomalous billing patterns using 27 features across 8 categories, a three-way ensemble scoring method (weighted composite, ML corroboration, gradient boosted trees), and graph analysis across an 82.6 million edge provider network.

Out-of-sample validation found 37 confirmed fraud cases totaling over $500M — providers never in the training data, flagged purely from billing pattern anomalies. Average detection lead time: 6.9 years before OIG exclusion.