一句话：AIGen：基于 MLflow、挖掘启发式与 LLM 的模块化 AIBoM 生成器，输出符合 SPDX 3.0 AI Profile 的清单。
AI 系统的负责任开发与部署需要严格记录其数据集、模型权重、训练流水线与运行时依赖等组成工件。尽管 SPDX 3.0 已引入 AI 与数据集 profile，能自动、可扩展生成标准合规 AI 物料清单（AIBoM）的工具仍稀缺。本文提出 AIGen：一个构建在 MLflow MLOps 框架上的模块化 AIBoM 生成器，结合挖掘启发式与大型语言模型，生成符合 SPDX 3.0 AI profile 的机器可读、可互操作清单。其插件接口允许在不修改核心代码的情况下扩展领域特定收集器，支持 Hugging Face、PyTorch 和 TensorFlow 等异构框架。AIGen 旨在促进欧盟 AI 法案、NIST AI 风险管理框架与 ISO/IEC 42001 合规，为透明、可问责的 AI 供应链治理提供可复用基础。
The responsible development and deployment of artificial intelligence (AI) systems requires rigorous documentation of their constituent artifacts, e.g., datasets, model weights, training pipelines, and runtime dependencies. Although the Software Package Data Exchange (SPDX) 3.0 standard introduced native support for AI and dataset profiles, practical tooling capable of generating standards-compliant AI Bills of Materials (AIBoMs) in an automated and extensible manner remains scarce. This paper presents AIGen, a modular AIBoM generator that produces machine-readable, interoperable inventories of AI system components that comply with the SPDX 3.0 AI profile. AIGen works on top of the MLflow MLOps framework and combines mining heuristics with Large Language Models to generate AIBoMs. A plugin interface allows practitioners to extend the tool with domain-specific collectors without modifying the core codebase, supporting heterogeneous AI frameworks such as Hugging Face, PyTorch, and TensorFlow. AIGen is designed to facilitate compliance with the European Union AI Act, the NIST AI Risk Management Framework, and ISO/IEC 42001, providing a concrete, reusable foundation for transparent, accountable AI supply chain governance. Tool URL: https://github.com/danielebifolco/AIGen Tool Video: https://youtu.be/_nAbXDWfVL4
@inproceedings{abs-2607-26652,
title = {AIGen: Automating AI Bill of Materials Generation through Hybrid MLOps Integration},
author = {Federica Pepe and Daniele Bifolco and Costantino Martignetti and Aureliano D'Amici and Fabiano Izzo and Damian Andrew Tamburri and Massimiliano Di Penta},
booktitle = {ASE},
year = {2026},
doi = {10.1145/3832783.3834615}
}