Vehicle enables compositional verification of neural controllers in discrete and continuous cyber-physical systems across Rocq, Isabelle/HOL, Agda, and Imandra, including the first infinite time-horizon safety proof for a continuous medical device in a general-purpose ITP.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 6roles
background 1polarities
background 1representative citing papers
Quantifier rewriting and array non-aliasing specifications in VerCors reduce verification time for data-level parallel programs by an average factor of 9.
A source-level interaction concept for interactive program verification, prototyped in KeY, improves user understanding of proof states and defect detection according to a user study.
Fuzz testing with the AValAnCHE prototype can uncover robustness issues in deductive verifiers such as VerCors and works across other similar tools.
AI agents can generate code in a capability-safe Scala dialect that statically prevents information leakage and malicious side effects while preserving task performance.
SpecRL uses the fraction of negative tests rejected by candidate specifications as a reward signal in RL training to produce stronger and more verifiable formal specifications than prior methods.
citing papers explorer
-
Compositional Neural-Cyber-Physical System Verification in the Interactive Theorem Prover of Your Choice
Vehicle enables compositional verification of neural controllers in discrete and continuous cyber-physical systems across Rocq, Isabelle/HOL, Agda, and Imandra, including the first infinite time-horizon safety proof for a continuous medical device in a general-purpose ITP.
-
Scalable Deductive Verification of Data-Level Parallel Programs
Quantifier rewriting and array non-aliasing specifications in VerCors reduce verification time for data-level parallel programs by an average factor of 9.
-
A New Interaction Concept for Interactive and Autoactive Program Verification
A source-level interaction concept for interactive program verification, prototyped in KeY, improves user understanding of proof states and defect detection according to a user study.
-
Crash-free Deductive Verifiers
Fuzz testing with the AValAnCHE prototype can uncover robustness issues in deductive verifiers such as VerCors and works across other similar tools.
-
Tracking Capabilities for Safer Agents
AI agents can generate code in a capability-safe Scala dialect that statically prevents information leakage and malicious side effects while preserving task performance.
-
Reinforcement Learning with Negative Tests as Completeness Signal for Formal Specification Synthesis
SpecRL uses the fraction of negative tests rejected by candidate specifications as a reward signal in RL training to produce stronger and more verifiable formal specifications than prior methods.