SPECTRE-G2 is a unified anomaly detector that uses eight complementary signals to detect 'unknown unknown' structural anomalies.
March 24, 2026
Original Paper
Beyond a Single Signal: SPECTREG2, A Unified MultiExpert Anomaly Detector for Unknown Unknowns
arXiv · 2603.21160
The Takeaway
Standard uncertainty quantification often fails on diverse structural shifts. This multi-expert approach combines density, geometry, and causal signals, providing a robust tool for safety-critical systems operating in open-world environments.
From the abstract
Epistemic intelligence requires machine learning systems to recognise the limits of their own knowledge and act safely under uncertainty, especially when faced with unknown unknowns. Existing uncertainty quantification methods rely on a single signal such as confidence or density and fail to detect diverse structural anomalies. We introduce SPECTRE-G2, a multi-signal anomaly detector that combines eight complementary signals from a dual-backbone neural network. The architecture includes a spectr