Uncovering Code Insights: Leveraging GitHub Artifacts for Deeper Code Understanding

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Nevo, Ziv, Raz, Orna, Yorav, Karen
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908631196237824
author Nevo, Ziv
Raz, Orna
Yorav, Karen
author_facet Nevo, Ziv
Raz, Orna
Yorav, Karen
contents Understanding the purpose of source code is a critical task in software maintenance, onboarding, and modernization. While large language models (LLMs) have shown promise in generating code explanations, they often lack grounding in the broader software engineering context. We propose a novel approach that leverages natural language artifacts from GitHub -- such as pull request descriptions, issue descriptions and discussions, and commit messages -- to enhance LLM-based code understanding. Our system consists of three components: one that extracts and structures relevant GitHub context, another that uses this context to generate high-level explanations of the code's purpose, and a third that validates the explanation. We implemented this as a standalone tool, as well as a server within the Model Context Protocol (MCP), enabling integration with other AI-assisted development tools. Our main use case is that of enhancing a standard LLM-based code explanation with code insights that our system generates. To evaluate explanations' quality, we conducted a small scale user study, with developers of several open projects, as well as developers of proprietary projects. Our user study indicates that when insights are generated they often are helpful and non trivial, and are free from hallucinations.
format Preprint
id arxiv_https___arxiv_org_abs_2511_03549
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Uncovering Code Insights: Leveraging GitHub Artifacts for Deeper Code Understanding
Nevo, Ziv
Raz, Orna
Yorav, Karen
Software Engineering
Artificial Intelligence
Understanding the purpose of source code is a critical task in software maintenance, onboarding, and modernization. While large language models (LLMs) have shown promise in generating code explanations, they often lack grounding in the broader software engineering context. We propose a novel approach that leverages natural language artifacts from GitHub -- such as pull request descriptions, issue descriptions and discussions, and commit messages -- to enhance LLM-based code understanding. Our system consists of three components: one that extracts and structures relevant GitHub context, another that uses this context to generate high-level explanations of the code's purpose, and a third that validates the explanation. We implemented this as a standalone tool, as well as a server within the Model Context Protocol (MCP), enabling integration with other AI-assisted development tools. Our main use case is that of enhancing a standard LLM-based code explanation with code insights that our system generates. To evaluate explanations' quality, we conducted a small scale user study, with developers of several open projects, as well as developers of proprietary projects. Our user study indicates that when insights are generated they often are helpful and non trivial, and are free from hallucinations.
title Uncovering Code Insights: Leveraging GitHub Artifacts for Deeper Code Understanding
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2511.03549