Verus
PulseAugur coverage of Verus — every cluster mentioning Verus across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
New gamified benchmark challenges AI coding agents on Rust verification tasks
Researchers have developed SeVerus, a novel gamified benchmarking system designed to evaluate coding agents on their ability to perform verification tasks in the Rust programming language. This system challenges agents …
-
Microsoft Research unveils PDD Kit for formal verification of AI-generated code
Microsoft Research has developed PDD Kit, a tool designed to formally verify code generated by AI agents. This kit integrates with GitHub Next's Chopin environment and uses the Verus specification language to ensure tha…
-
Claude AI generates 180M lines of code proof, finds hundreds of bugs
Anthropic's Claude model, in collaboration with Theorem, has achieved a significant milestone in formal verification by generating approximately 180 million lines of machine-checked proof for 239 entry points across 123…
-
New auditing method doubles Verus/Rust program correctness evidence discovery
A new research paper on arXiv introduces a method called Phase-Separated Completeness Auditing for Verus/Rust programs. This technique aims to improve the discovery of program correctness by avoiding feedback loops that…
-
Lean-backed verifier solves 1007 competitive programming proofs
Researchers have developed a novel approach to automatically generate proofs for competitive programming problems using a verifier backed by the Lean 4 programming language. This system successfully proved all 1325 theo…
-
Amazon's Verus tool highlights AI code review's limits
Amazon has highlighted Verus, a Rust verifier tool that mechanically proves code correctness against mathematical specifications, a stark contrast to AI-driven code review. Unlike AI models that judge code quality, Veru…
-
New RESUME CONTRACT paper finds major flaws in AI agent workflow persistence
A new research paper introduces the RESUME CONTRACT, a machine-checked conformance contract designed to standardize checkpoint, interrupt, and resume semantics in workflow persistence layers. The study found that five w…
-
New system Formal Disco generates verified code datasets at scale
Researchers have developed Formal Disco, a scalable system designed to generate large datasets of formally verified programs. This system uses a distributed approach with three types of AI workers: initiators to sketch …
-
New evaluation framework tests software security by varying implementations, not just AI models
This post proposes a multidimensional evaluation framework for assessing the security of software, particularly in the context of AI-assisted development. Instead of solely varying the AI model being tested, the author …
-
New benchmark reveals AI struggles with verified code generation
A new benchmark called AlgoVeri has been developed to evaluate the performance of AI models in generating formally verified code for classical algorithms. The benchmark tests models across three languages: Dafny, Verus,…
-
AI uses proof checker to generate formally verified code
Researchers have developed a new AI method called Inductive Deductive Synthesis that uses a proof checker within its implementation loop. This approach, which is analogous to chain-of-thought but with formally verified …