Protected Cores Are Not Enough: Certifying AI-Proposed Revisions of Temporal Specifications

arXiv:2609.33461 · cs.LO, cs.AI, cs.LG, cs.SE · Submitted 2026-09-27 · Read on arXiv

cs.LO, cs.AI, cs.LG, cs.SE

Submitted: 2026-09-27

Updated: 2026-09-27

Code: https://github.com/ruggerolanotte/protectedcores-artifact

Terminology

• Core — 244× in this paper · explained in 2 episodes
• Post-Selection — 24× in this paper · explained in 2 episodes
• Verification — 14× in this paper · explained in 2 episodes
• Adaptation — 11× in this paper · explained in 1 episode
• Admissibility — 11× in this paper · explained in 2 episodes
• Trace — 8× in this paper · explained in 2 episodes
• Alignment — 5× in this paper · explained in 1 episode
• Accuracy — 3× in this paper · explained in 1 episode
• Adaptive Monitoring — 3× in this paper · explained in 1 episode
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Adaptive Response — 2× in this paper · explained in 1 episode
• Regret — 2× in this paper · explained in 3 episodes
• Self-Evolving Agents — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Concept Drift — 1× in this paper · explained in 4 episodes
• Distribution Shift — 1× in this paper · explained in 6 episodes
• European Control Conference — 1× in this paper
• Formal Methods — 1× in this paper · explained in 3 episodes
• Frozen model — 1× in this paper · explained in 3 episodes
• International Joint Conference on Neural Networks — 1× in this paper
• Sample Efficiency — 1× in this paper · explained in 4 episodes
• Semantic Drift — 1× in this paper · explained in 3 episodes
• Steering — 1× in this paper · explained in 2 episodes

Sources

• Multi-Property Temporal Logic Monitoring
• Robust Probabilistic Shielding for Safe Offline Reinforcement Learning
• Robust Shielding for Safe Reinforcement Learning
• SENTIL: A Runtime Verification Tool for Probabilistic Temporal Logic
• Self-Evolving Agents with Anytime-Valid Certificates
• SGM: A Statistical Godel Machine for Risk-Controlled Recursive Self-Modification

Related papers

• An Information-Flow Perspective on Explainability Requirements: Specification and Verification
• A programming language combining quantum and classical control
• Causal Past Logic for Runtime Verification of Distributed LLM Agent Workflows
• Encoder-Decoder Transformers: Logical Characterizations and Periodicity
• Ultraconstructive Model Theory via Bounded Adversarial Finite Structures