CIR+CVN: Bridging LLM Semantic Understanding and Petri-Net Verification for Concurrent Programs

2026-04-10

AI Summary

Recovering concurrent structures directly from source code is highly challenging, as shared resources and their protection mechanisms are often obscured by aliasing, ownership semantics, and API idioms. This work proposes a specification-driven, model-first verification approach: natural language requirements are first translated by a large language model into a semantically precise Concurrent Intermediate Representation (CIR), which is then mechanically compiled into a weighted Petri net with three-valued guards—termed a Concurrency Verification Net (CVN). By integrating static rule checking with dynamic goal reachability analysis, the method enables exhaustive, traceable verification and provides actionable repair guidance. Evaluated on nine representative bounded concurrency patterns, the approach effectively supports iterative bug detection and filters out semantically incomplete repair candidates through goal-directed reachability constraints.

Technology Category

• Computer Vision: Language and Vision
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures

Abstract

Recovering concurrency structure directly from source code is difficult because shared-resource identity and protection relations are often obscured by aliasing, ownership, and API-specific idioms. We therefore study a specification-driven, model-first verification architecture for LLM-assisted concurrent program construction. Instead of verifying arbitrary source code, a large language model first synthesizes a verification-oriented concurrency artifact from a natural-language requirement or system specification. The first formalism, the Concurrency Intermediate Representation (Cir), is a statement-level, alias-free model in which shared resources are globally named, protection relations are explicit, and each statement carries a stable identifier. The second formalism, the Concurrency Verification Net (Cvn), is a weighted place/transition Petri net with a finite global store and three-valued guards for data-dependent branching. A validated Cir artifact is translated mechanically to Cvn, explored exhaustively, and any counterexample is mapped back to statement identifiers to guide targeted repair. To reduce the risk of bug-free but behavior-dropping repairs, acceptance additionally applies a lightweight goal-reachability check over designated critical outcomes. We formalize both representations, prove translation-correspondence results for deadlock and signal-loss analysis, define a two-layer checking architecture with 61 static rules and 5 analysis predicates, and evaluate the pipeline on 9 representative bounded-concurrency patterns. The results show that the method supports iterative bug detection and repair on Cir artifacts and that goal reachability helps filter semantically incomplete repairs. The trust boundary of the present work is the generated Cir artifact rather than arbitrary source code.

Problem

• concurrent programs
• shared-resource identity
• protection relations
• aliasing
• concurrency structure recovery

Innovation

• Concurrency Intermediate Representation
• Concurrency Verification Net
• LLM-assisted verification
• Petri net
• goal reachability