# Anomaly Outlier Detection

> Score each class's deviation from the dominant behavioral signature, identify the outliers, and name why each deviates, so inconsistency is localized to the deviant implementation rather than reported as an aggregate rate.

Record: `algo:anomaly-outlier-detection`
Kind: pattern-distillation
Canonical: https://banes-lab.com/ontology/algorithms#algo-anomaly-outlier-detection
Closure: https://banes-lab.com/json/records/algo/anomaly-outlier-detection/closure

## stage

- [see](https://banes-lab.com/records/stage/see.md)

## axis

- [analysis](https://banes-lab.com/records/reason/axis-analysis.md)

## grounds

- [ana-anomaly](https://banes-lab.com/records/reason/node-ana-anomaly.md)

## detects

- [anomaly](https://banes-lab.com/records/reason/lens-anomaly.md)