Position: Certifiable State Integrity in Cyber-Physical Systems -- Why Modular Sovereignty Solves the Plasticity-Stability Paradox

TL;DR

This paper proposes a modular approach called HYDRA for deploying reliable, certifiable foundation models in safety-critical cyber-physical systems, addressing the plasticity-stability paradox and enabling formal verification.

Contribution

It introduces the Modular Sovereignty paradigm with regime-specific specialists and uncertainty-aware blending, improving robustness and verifiability in CPS applications.

Findings

HYDRA enhances state integrity across regimes

Modular specialists improve fault detection

Uncertainty modeling aids certification

Abstract

The machine learning community has achieved remarkable success with universal foundation models for time-series and physical dynamics, largely overcoming earlier approximation barriers in smooth or slowly varying regimes through scale and specialized architectures. However, deploying these monolithic models in safety-critical Cyber-Physical Systems (CPS), governed by non-stationary lifecycle dynamics and strict reliability requirements, reveals persistent challenges. Recent evidence shows that fine-tuning time-series foundation models induces catastrophic forgetting, degrading performance on prior regimes. Standard models continue to exhibit residual spectral bias, smoothing high-frequency discontinuities characteristic of incipient faults, while their opacity hinders formal verification and traceability demanded by safety standards (e.g., ISO 26262, IEC 61508). This position paper argues that the plasticity-stability paradox cannot be fully resolved by global parameter updates (whether via offline fine-tuning or online adaptation). Instead, we advocate a Modular Sovereignty paradigm: a library of compact, frozen regime-specific specialists combined via uncertainty-aware blending, which we term "HYDRA" (Hierarchical uncertaintY-aware Dynamics for Rapidly-Adapting systems). This paradigm ensures regime-conditional validity, rigorous disentanglement of aleatoric and epistemic uncertainties, and modular auditability, offering a certifiable path for robust state integrity across the CPS lifecycle.