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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Spotorno, Enzo Nicolás, Fröhlich, Antônio Augusto Medeiros
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911405701070848
author Spotorno, Enzo Nicolás
Fröhlich, Antônio Augusto Medeiros
author_facet Spotorno, Enzo Nicolás
Fröhlich, Antônio Augusto Medeiros
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_21249
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Position: Certifiable State Integrity in Cyber-Physical Systems -- Why Modular Sovereignty Solves the Plasticity-Stability Paradox
Spotorno, Enzo Nicolás
Fröhlich, Antônio Augusto Medeiros
Artificial Intelligence
Machine Learning
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.
title Position: Certifiable State Integrity in Cyber-Physical Systems -- Why Modular Sovereignty Solves the Plasticity-Stability Paradox
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2601.21249