SpecMine: A Large-Scale Corpus of Spec-Driven Development Artifacts

• URL: http://arxiv.org/abs/2608.25202v3
• Date: Tue, 01 Sep 2026 20:50:48 GMT
• Title: SpecMine: A Large-Scale Corpus of Spec-Driven Development Artifacts
• Abstract summary: SpecMine captures Spec-Driven Development (SDD) in public GitHub repositories.<n>It lets the community study, for the first time, how software is specified in the age of AI agents.
• Score: 7.933620345044633
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Scanning the Harness: An Empirical Study of Supply-Chain Defects in AI Coding-Agent Configurations [0.0]
  AI coding agents such as Claude Code, Cursor, GitHub Copilot, and OpenAI Codex are configured through artifacts developers write and share.<n>This harness is a dependency layer installed from marketplaces and public repositories, running with the developer's privileges.<n>We study it over 3,171 public GitHub repositories: 2,660 setups that assemble two or more component types and 511 published skill collections.
  arXiv  Detail & Related papers  (2026-09-07T11:27:24Z)
• Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills [86.15447717549154]
  We present DisCo, a skill-powered research agent that creates skills and uses them during research.<n>We call this missing layer operational knowledge, the know-how that separates knowing a method from making it work.
  arXiv  Detail & Related papers  (2026-09-02T15:49:41Z)
• CommitDistill: A Lightweight Knowledge-Centric Memory Layer for Software Repositories [0.5872014229110213]
  Software accumulate large amounts of unstructured knowledge in commit messages, pull-request discussions, and issue threads.<n>Recent work on typed-memory architectures for agents (MemGPT, generative agents, and the PlugMem module of Yang et al.) argues that agent memory should be distilled, typed knowledge rather than raw interaction text.<n>We adapt that stance to a software repository's own git history under a constrained regime: deterministic, dependency-free, local-only, no embeddings.
  arXiv  Detail & Related papers  (2026-05-18T12:14:28Z)
• A Dataset of Agentic AI Coding Tool Configurations [11.087963504113937]
  dataset covers 4,738 repositories across five tools (Claude Code, GitHub Copilot, OpenAI Codex, Cursor, Gemini) and eight configuration mechanisms.<n>We collected 15,591 configuration artifacts, the full content of 18,167 configuration files associated with these configuration artifacts, and 148,519 AI-co-authored commits.<n>This data supports research on context engineering, AI tool adoption patterns, and human-AI collaboration.
  arXiv  Detail & Related papers  (2026-05-08T19:58:27Z)
• Agent READMEs: An Empirical Study of Context Files for Agentic Coding [8.019313057979522]
  We study 2,303 agent context files from 1,925 repositories to characterize their structure, maintenance, and content.<n>We find that these files are not static documentation but complex, difficult-to-read artifacts that evolve like configuration code, maintained through frequent, small additions.<n>These findings indicate that while developers use context files to make agents functional, they provide few guardrails to ensure that agent-written code is secure or performant, highlighting the need for improved tooling and practices.
  arXiv  Detail & Related papers  (2025-11-17T02:18:55Z)
• Trace: Securing Smart Contract Repository Against Access Control Vulnerability [58.02691083789239]
  GitHub hosts numerous smart contract repositories containing source code, documentation, and configuration files.<n>Third-party developers often reference, reuse, or fork code from these repositories during custom development.<n>Existing tools for detecting smart contract vulnerabilities are limited in their ability to handle complex repositories.
  arXiv  Detail & Related papers  (2025-10-22T05:18:28Z)
• Your Build Scripts Stink: The State of Code Smells in Build Scripts [7.543600033457145]
  Insecure URLs were the most prevalent code smell in Maven build scripts.<n>HardcodedPaths/URLs were commonly observed in both Gradle and CMake scripts.<n>Wildcard Usage emerged as the most frequent smell in Makefiles.
  arXiv  Detail & Related papers  (2025-06-22T09:01:42Z)
• SWE-smith: Scaling Data for Software Engineering Agents [100.30273957706237]
  SWE-smith is a novel pipeline for generating software engineering training data at scale.<n>We create a dataset of 50k instances sourced from 128 GitHub repositories.<n>We train SWE-agent-LM-32B, achieving 40.2% Pass@1 resolve rate on the SWE-bench Verified benchmark.
  arXiv  Detail & Related papers  (2025-04-30T16:56:06Z)
• Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning [70.04746094652653]
  We introduce PaperCoder, a framework that transforms machine learning papers into functional code repositories.<n>PaperCoder operates in three stages: planning, designs the system architecture with diagrams, identifies file dependencies, and generates configuration files.<n>We then evaluate PaperCoder on generating code implementations from machine learning papers based on both model-based and human evaluations.
  arXiv  Detail & Related papers  (2025-04-24T01:57:01Z)
• CLOVER: A Test Case Generation Benchmark with Coverage, Long-Context, and Verification [71.34070740261072]
  This paper presents a benchmark, CLOVER, to evaluate models' capabilities in generating and completing test cases.<n>The benchmark is containerized for code execution across tasks, and we will release the code, data, and construction methodologies.
  arXiv  Detail & Related papers  (2025-02-12T21:42:56Z)
• An Empirical Study of Dotfiles Repositories Containing User-Specific Configuration Files [1.7556600627464058]
  Hundreds of thousands choose to publicly host their repositories on GitHub.<n>We collected and analyzed publicly-hosted dotfiles repositories on GitHub.<n>We found that 25.8% of the top 500 most-starred GitHub users maintain some form of publicly accessible dotfiles repository.
  arXiv  Detail & Related papers  (2025-01-30T18:32:46Z)
• DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories [83.5195424237358]
  Existing benchmarks are poorly aligned with real-world code repositories. We propose a new benchmark named DevEval, which has three advances. DevEval comprises 1,874 testing samples from 117 repositories, covering 10 popular domains.
  arXiv  Detail & Related papers  (2024-05-30T09:03:42Z)
• VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learning [104.74705190239119]
  We introduce VSCode, a model with novel 2D prompt learning to jointly address four SOD tasks and three COD tasks. We utilize VST as the foundation model and introduce 2D prompts within the encoder-decoder architecture to learn domain and task-specific knowledge. VSCode outperforms state-of-the-art methods across six tasks on 26 datasets.
  arXiv  Detail & Related papers  (2023-11-25T12:34:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.