A Subjective Logic-based method for runtime confidence updates in safety arguments

📰 ArXiv cs.AI

arXiv:2605.22530v1 Announce Type: new Abstract: We present a method for dynamic quantitative assurance that enhances static safety cases with continuous, runtime-driven confidence updates. The method quantifies and propagates confidence across the development lifecycle by integrating design-time evidence and windowed runtime Safety Performance Indicators (SPIs) within a single Subjective Logic (SL)-based assurance case. At runtime, SPI evidence is continuously evaluated, and targeted claims are

Published 23 May 2026
Read full paper → ← Back to Reads