构建首个大规模AI驱动开发规范数据集，揭示代码生成新范式。
SpecMine: A Large-Scale Corpus of Spec-Driven Development Artifacts
- 通过扫描47万份spec文件与5992个拉取请求，捕捉AI编码流程中的规范-代码关联
- 发现12910个Kiro工具项目中，863000次文档引用和128万次代码文件关联
- 适合研究AI辅助编程、软件工程演化与开发者工作流的学者与工程师
Spec-Driven Development（SDD）是一种新兴实践：由开发者撰写或由AI生成并人工校对的结构化自然语言规格说明书，驱动AI编码代理实现功能。自2025年以来，大量工具（如GitHub Spec Kit、OpenSpec、AWS Kiro等）涌现，但其产生的开发资产从未被大规模研究。本文提出SpecMine，一个涵盖公共GitHub仓库中SDD实践的语料库，包含两次普查：覆盖多数工具的广义普查（470,795个spec.md/specs.md文件，来自73,030个仓库，归属17个命名工具），以及针对Kiro工具的独特布局普查（98,574个文件，来自12,910个仓库）。每个规范均附带完整仓库元数据、提交历史及解析后的文档结构。为探究规范如何转化为代码，我们对11个工具中至少十星的仓库，扫描所有修改过规范的拉取请求，共捕获5,992个PR，涉及581个仓库及其变更集。该数据首次直接观测到‘规范与实现同步更新’这一最简工作流。此外，通过建立包含2,421,323个类型化引用的索引（其中128万指向代码文件，86.3万指向同级文档，15.2万指向拉取请求，6.2万指向分支，4.3万指向问题），提供了从规范到代码的独立映射路径。SpecMine使研究者首次能够系统分析人工智能时代软件编写方式。
原文摘要 · Abstract (English)
Spec-Driven Development (SDD) is a fast-emerging practice in which a structured natural-language specification, written by a developer, or (more often) drafted by an AI tool and then curated by the developer, drives an AI coding agent's implementation. A wave of tooling (GitHub Spec Kit [3], OpenSpec [4], AWS Kiro [5], and dozens of others) has appeared since 2025, yet the artifacts these tools produce have never been studied at scale. We present SpecMine, a corpus that captures SDD in public GitHub repositories through two censuses: a broad census of spec.md/specs.md files covering most tools (470,795 files across 73,030 repositories, attributed to 17 named tools), and a Kiro census of its distinct requirements/design/tasks layout (98,574 files across 12,910 repositories). Each spec is enriched with full repository metadata, complete commit history, and parsed document structure. How a spec becomes code is itself an open question, so for 11 tools we sweep every pull request that touches a spec in their repositories with at least ten stars, capturing 5,992 such PRs across 581 repositories with their changesets. That makes the simplest workflow, spec and implementation changing together in one PR, directly observable, and a census-wide index of 2,421,323 typed references (1.28M to code files, 863k to sibling documents, 152k to PRs, 62k refs, 43k branches, 22k issues) gives a second, independent link from spec to code. SpecMine lets the community study, for the first time, how software is specified in the age of AI agents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。