# Outlier Detection **Entity class:** Sensor And Multimodal-Fusion Layer concept **Outlier Detection** is an observation or analytic method used to identify departures, recurring structure, or candidate signals for further assessment. Outlier Detection belongs in the ontology because AI can compute over this structure while analysts retain responsibility for interpretation and authorized action. ## Counterterrorism predictive-graph role The page records capability and analytic function. Any claim of a named operational deployment remains subject to the [[wiki/Counterterrorism Predictive Graph Evidence Ladder|evidence ladder]]. The analytic state should distinguish ground truth, observed evidence, inferred state, and predicted state. ## Relationships - **domain router:** [[wiki/Intelligence Fusion|Intelligence Fusion]]. - **ontology neighbors:** [[wiki/Anomaly Detection|Anomaly Detection]] and [[wiki/Behavior Detection|Behavior Detection]]. - **synthesis:** [[wiki/Counterterrorism Predictive Graph|Counterterrorism Predictive Graph]] and [[wiki/Predictive Intelligence Loop|Predictive Intelligence Loop]]. ## Sources - [IARPA — DIVA program (accessed September 23, 2026)](https://www.iarpa.gov/research-programs/diva) - [IARPA — AGILE technical overview (accessed September 23, 2026)](https://www.iarpa.gov/images/research-programs/AGILE/AGILE_ModSim_-_Final.pdf) **As of:** 2026-09-23