Newest papers

Anytime-Valid Runtime Monitoring of Learned Barrier Certificates

Zhipeng Cao, Taoran Wu, Weiru Cui, Luke Ong, Bai Xue · 2026 · Preprints.org

DOI: 10.20944/preprints202610.2093.v1 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

Los certificados de barrera aprendidos proporcionan un mecanismo de datos básico para establecer la seguridad de los sistemas estocásticos, pero su validez puede deteriorarse durante el despliegue cuando la dinámica subyacente difiere de la que se utiliza para la formación. Proponemos un monitor de tiempo de ejecución válido en cualquier momento que audita un certificado de barrera aprendido utilizando trayectorias cerradas observadas. El monitor está diseñado para detectar la pérdida de soporte estadístico para la condición de barrera desplegada; no garantiza por sí mismo la detección antes de la entrada insegura o la seguridad de una intervención posterior. Especificamente, la condición de barrera condicional-drift se formula como una prueba de hipótesis secuenciales episódicas, y los incrementos de barrera observados se transforman en un

Machine translation (Meta M2M100); the English original follows.

Abstract

Learned barrier certificates provide a principled mechanism for establishing safety of stochastic systems, but their validity may deteriorate during deployment when the underlying dynamics differ from those used for training. We propose an anytime-valid runtime monitor that audits a learned barrier certificate using observed closed-loop trajectories. The monitor is intended to detect loss of statistical support for the deployed barrier condition; it does not by itself guarantee detection before unsafe entry or safety of a subsequent intervention. Specifically, the conditional barrier-drift condition is formulated as an episode-wise sequential hypothesis test, and observed barrier increments are transformed into a nonnegative test supermartingale, yielding finite-sample false-alarm control under arbitrary stopping times. Inspired by finite-horizon safety verification, we further introduce a deterministic temporal shaping of the monitoring boundary, making the monitor more conservative early in a prescribed deployment horizon while preserving anytime-validity. The monitor is designed to detect statistical evidence that the safety certificate is no longer consistent with the observed dynamics, rather than to predict unsafe entry. To assess the monitor empirically, we evaluate empirical alarm behavior under valid and invalid certificates. Code and data are available at https://github.com/FormalCert-AI/runtime-barrier-monitor.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Certificate, Computer science, Software deployment, ALARM, Audit, Control (management)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange