Beyond a Single Signal: SPECTREG2, A Unified MultiExpert Anomaly Detector for Unknown Unknowns
This provides a practical solution for improving epistemic intelligence in machine learning systems, enabling safer operation under uncertainty in open-world settings.
The paper tackles the problem of detecting diverse structural anomalies, or unknown unknowns, by introducing SPECTRE-G2, a multi-signal anomaly detector that outperforms baselines on metrics like AUROC, AUPR, and FPR95 across synthetic and real-world datasets.
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 spectral normalised Gaussianization encoder, a plain MLP preserving feature geometry, and an ensemble of five models. These produce density, geometry, uncertainty, discriminative, and causal signals. Each signal is normalised using validation statistics and calibrated with synthetic out-of-distribution data. An adaptive top-k fusion selects the most informative signals and averages their scores. Experiments on synthetic, Adult, CIFAR-10, and Gridworld datasets show strong performance across diverse anomaly types, outperforming multiple baselines on AUROC, AUPR, and FPR95. The model is stable across seeds and particularly effective for detecting new variables and confounders. SPECTRE-G2 provides a practical approach for detecting unknown unknowns in open-world settings.