一句话：提出 NNBOM 数据集，基于 55,997 个 PyTorch 仓库实证刻画神经网络软件的演化规律并构建原型工具。
神经网络开源仓库迭代极快，但传统软件物料清单（SBOM）面向包管理信息，难以刻画 NN 软件以预定义模块与预训练模型（PTM）为核心的独特组件结构与复用模式，而概念性的 AIBOM 也缺乏可大规模落地的实现。为填补这一空白，本文提出 NNBOM（Neural Network Bill of Material），从 55,997 个精选的 PyTorch GitHub 仓库构建大规模数据库，编目其第三方库（TPL）、预训练模型与模块。基于该库开展实证研究，从软件规模、组件复用与跨领域依赖三个维度分析神经网络软件的长期演化趋势，为维护者与开发者提供整体视图。最后实现多仓库演化分析器与单仓库组件评估推荐器两个原型应用，展示该分析的实际价值。
Neural networks have become integral to many fields due to their exceptional performance. The open-source community has witnessed a rapid influx of neural network (NN) repositories with fast-paced iterations, making it crucial for practitioners to analyze their evolution to guide development and stay ahead of trends. While extensive research has explored traditional software evolution using Software Bill of Materials (SBOMs), these are ill-suited for NN software, which relies on pre-defined modules and pre-trained models (PTMs) with distinct component structures and reuse patterns. Conceptual AI Bills of Materials (AIBOMs) also lack practical implementations for large-scale evolutionary analysis. To fill this gap, we introduce the Neural Network Bill of Material (NNBOM), a comprehensive dataset construct tailored for NN software. We create a large-scale NNBOM database from 55,997 curated PyTorch GitHub repositories, cataloging their TPLs, PTMs, and modules. Leveraging this database, we conduct a comprehensive empirical study of neural network software evolution across software scale, component reuse, and inter-domain dependency, providing maintainers and developers with a holistic view of its long-term trends. Building on these findings, we develop two prototype applications, Multi repository Evolution Analyzer and Single repository Component Assessor and Recommender, to demonstrate the practical value of our analysis.
@inproceedings{paperbot9421,
title = {Demystifying the Evolution of Neural Networks with BOM Analysis: Insights from a Large-Scale Study of 55,997 GitHub Repositories},
author = {Xiaoning Ren and Yuhang Ye and Xiongfei Wu and Yueming Wu and Yinxing Xue},
booktitle = {ASE},
year = {2025},
doi = {10.1109/ase63991.2025.00170}
}