safety security
Approval Expired Before the Action
A guardrail verdict can be correct when checked and unsafe by the time a self-adaptive system acts.
Summary
A guardrail verdict can be correct when checked and unsafe by the time a self-adaptive system acts.
Across five reproducible environments, fixed-action replay produced verdict-change rates from 5.3 to 48.4 percent after eight simulator steps. The proposed Freshness-Bounded Shield estimates an approval horizon from safety margin and recent feature volatility; under fixed settings, the authors report reducing oracle-labeled expiry from a 3.4-to-24.7-percent range to zero-to-1.8 percent. Four language-model judges still showed nonzero use-time invalidity, motivating a check-time-and-use-time freshness contract.
Why it matters
A guardrail verdict can be correct when checked and unsafe by the time a self-adaptive system acts.
Limits and context
No additional limitation was separately recorded.
Key claims
A guardrail verdict can be correct when checked and unsafe by the time a self-adaptive system acts.
Evidence: source-2026-08-30-016
Sources
- arXiv preprint 2608.26306arXiv · primary research
Corrections
No corrections have been recorded for this story.