GitHub projects keep local coding styles despite AI influence
Converging Naming Styles, Persistent Network Locality: GitHub in the LLM Era
Social and Information Networks
Summary
This paper looks at how programmers name things in their code on GitHub, especially now that AI tools help them. Even though AI suggests similar naming styles to many users everywhere, smaller groups of developers still keep their own local naming habits. The authors found that recent projects use longer names and less variety overall, but people working closer together in GitHub’s network still have more similar styles. This means AI influences naming but doesn’t erase local coding cultures.
What this means in practice
- •For software development teams: Design tools that suggest coding styles balancing AI recommendations with team-specific conventions to maintain code readability and team cohesion.
- •For software repository managers: Develop metrics to track naming style changes in repositories over time, helping to monitor AI tool impact on coding practices within developer communities.
Authors
Yuto Tamura, Sho Tsugawa
Abstract
Social conventions often emerge through repeated interactions within social networks, allowing shared practices to coexist with variation across groups. Large language models (LLMs) introduce a potentially different coordination structure: a small number of widely used models can expose socially distant users to similar patterns and suggestions. Whether broad convergence under such shared technological influences eliminates network-local variation remains unclear. We examine this question in software development, where identifier naming styles provide observable conventions and LLM-based tools have rapidly diffused. Using public GitHub repositories created between 2015 and September 2025 across six programming languages, we characterize naming styles with 27 features and examine their association with detected LLM-related commits, their diversity across repository creation cohorts, and their relationship to owner proximity in a large-scale collaboration network. Repositories with detected LLM-related commits tend to use longer identifiers and, in several languages, make greater use of naming patterns already prevalent within the language. We also observe lower naming-style diversity in recent creation cohorts, with marked declines appearing around 2023-2024 in several languages, although their timing and trajectories differ. At the same time, network locality persists: in five of the six languages, repositories whose owners are closer in the collaboration network remain more similar in naming style even among recent, more homogeneous cohorts. These findings show that aggregate convergence and network-local variation can coexist, highlighting the need to examine not only how much cultural variation remains, but also how that variation continues to be structured by human social relationships in the era of widely shared AI systems.