A publicly released dataset of 15,591 configuration artifacts for five agentic AI coding tools, drawn from 4,738 GitHub repositories along with associated files and AI-co-authored commits.
AIDev: Studying AI Coding Agents on GitHub
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 9years
2026 9roles
background 1polarities
background 1representative citing papers
A validated multi-method census of 180M repositories shows AI coding agents generate over 320k commits per month, with bot-account detection recovering only 3.3% of Claude Code activity and commit/PR channels capturing disjoint populations.
Study of 930k+ agent PRs shows repository explains ~50% of integration friction variance, with agents concentrating it twice as much as humans (ICC 0.30 vs 0.16) after controls.
An empirical study of 86,156 test patches from five AI agents finds 80.2% lack strong oracle signals, with strong oracles linked to higher merge rates (OR=1.28) after regression controls.
Coding benchmarks conflate the model with the harness, environment, and verifier into a single end-to-end score, which is misaligned with agentic software engineering.
Explicit delegation contracts improve reviewability metrics for AI coding agents without changing objective correctness in a 64-run pilot study.
The central challenge in AI-augmented CI/CD is designing authority transfer from humans to agents under constraints, as current systems remain limited to bounded data-plane autonomy backed by external governance.
Empirical analysis of AI refactoring PRs shows quality attribute improvements in 22.5% of cases with new Pylint issues in 24.17% and Bandit findings in 4.7%, yet 73.5% developer acceptance.
Agentic Agile-V uses Agile-V as backbone and a Specify-Constrain-Orchestrate-Prove-Evolve-Verify loop to convert AI agent conversations into traceable engineering artifacts with acceptance evidence.
citing papers explorer
-
A Dataset of Agentic AI Coding Tool Configurations
A publicly released dataset of 15,591 configuration artifacts for five agentic AI coding tools, drawn from 4,738 GitHub repositories along with associated files and AI-co-authored commits.
-
Detecting AI Coding Agents in Open Source: A Validated Multi-Method Census of 180 Million Repositories
A validated multi-method census of 180M repositories shows AI coding agents generate over 320k commits per month, with bot-account detection recovering only 3.3% of Claude Code activity and commit/PR channels capturing disjoint populations.
-
Govern the Repository, Not the Agent: Measuring Ecosystem-Level Risk in AI-Native Software
Study of 930k+ agent PRs shows repository explains ~50% of integration friction variance, with agents concentrating it twice as much as humans (ICC 0.30 vs 0.16) after controls.
-
All Smoke, No Alarm: Oracle Signals in Agent-Authored Test Code
An empirical study of 86,156 test patches from five AI agents finds 80.2% lack strong oracle signals, with strong oracles linked to higher merge rates (OR=1.28) after regression controls.
-
Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering
Coding benchmarks conflate the model with the harness, environment, and verifier into a single end-to-end score, which is misaligned with agentic software engineering.
-
Software Delegation Contracts: Measuring Reviewability in AI Coding-Agent Work
Explicit delegation contracts improve reviewability metrics for AI coding agents without changing objective correctness in a 64-run pilot study.
-
From Assistance to Agency: Rethinking Autonomy and Control in CI/CD Pipelines
The central challenge in AI-augmented CI/CD is designing authority transfer from humans to agents under constraints, as current systems remain limited to bounded data-plane autonomy backed by external governance.
-
Quality and Security Signals in AI-Generated Python Refactoring Pull Requests
Empirical analysis of AI refactoring PRs shows quality attribute improvements in 22.5% of cases with new Pylint issues in 24.17% and Bandit findings in 4.7%, yet 73.5% developer acceptance.
-
Agentic Agile-V: From Vibe Coding to Verified Engineering in Software and Hardware Development
Agentic Agile-V uses Agile-V as backbone and a Specify-Constrain-Orchestrate-Prove-Evolve-Verify loop to convert AI agent conversations into traceable engineering artifacts with acceptance evidence.