一句话：提出架构语义增强的仓库级变更摘要方法，支持跨提交、多粒度且可追溯的演化理解。
现有变更摘要多局限于单个提交或函数，难以刻画跨提交演化；仓库级理解工具又偏重单版本静态文档，忽略时间演化。本文提出 ChangeWiki，一种架构语义增强的仓库级变更摘要方法。它构建带多源上下文的分层多粒度变更实体树以推断变更意图与影响，恢复跨版本模块结构，并采用双向上下文引导聚合：自底向上综合代码级变更，同时以架构语义作自顶向下约束，生成一致、可追溯且兼顾局部修改与系统级演化的摘要。作者在真实项目基准上评估，语义准确性、完整性与跨粒度可追溯性均显著提升；原型已在工业界部署，减少定位上游变更引发问题的人工开销。
Understanding software evolution at the repository level is essential for tasks such as release management, code review, and regression testing. However, existing change summarization techniques are largely confined to single commits or functions, failing to capture cross-commit evolutionary context, while recent repository-level understanding tools focus on static documentation of single-version codebases, overlooking evolution over time. To bridge this gap, we propose ChangeWiki, an architecture semantic-augmented approach for repository-level change summarization. ChangeWiki first constructs hierarchical, multi-granularity change entity trees enriched with multi-source contexts to infer change intent and impact. It then recovers modular structures across versions and employs a bidirectional context-guided aggregation mechanism, synthesizing code-level changes from the bottom up while injecting architectural semantics as top-down constraints. ChangeWiki finally generates coherent, traceable summaries that capture both local modifications and system-level evolution. We construct comprehensive benchmarks and evaluate ChangeWiki on real-world projects. Experimental results demonstrate significant improvements in semantic accuracy, completeness, and cross-granularity traceability. A prototype of ChangeWiki has been deployed in an industrial setting for upstream-downstream code evolution, where developers reported that the hierarchical summaries significantly reduced manual effort in issue localization caused by upstream changes and show potential for automating version release notes.
@inproceedings{paperbot12182,
title = {ChangeWiki: Repository-Level Change Summarization Augmented with Architecture Semantics},
author = {Zijun Wang and Wuxia Jin and Jiale Li and Zhanhong Mou and Ting Liu},
booktitle = {ASE},
year = {2026},
doi = {10.1145/3832783.3834436}
}