Artifacts-for-reproducibility

This repository contains the artifacts and automated evaluation framework developed for the structural assessment of microservice architectures generated by Large Language Models (LLMs). The framework combines static source-code analysis, dependency graph extraction, architecture interpretation, violation detection, and metric computation. The pipeline extracts dependency relationships from monolithic software systems using Tree-sitter and NetworkX, generating structural dependency graphs that capture inheritance, composition, dependency injection, repository usage, and JPA relationships. These graphs are then compared against microservice decompositions produced by LLMs under different prompting strategies, including zero-shot and few-shot. The framework automatically detects structural violations caused by dependencies crossing service boundaries and computes quantitative metrics, including Dependency Violation Rate (TVD), True Positive Dependency Preservation (TPD), Basic Cohesion (BC), and Granularity. Its objective is to provide a fully reproducible methodology for evaluating how closely LLM-generated architectures preserve the structural organization of the original monolithic source code. These artifacts were developed as part of a Master's research project in Applied Artificial Intelligence and Software Engineering and are intended to support empirical research on software architecture reconstruction, microservice migration, and AI-assisted software engineering.