cd /news/artificial-intelligence/ai-assisted-code-at-scale-provenance… · home › topics › artificial-intelligence › article
[ARTICLE · art-171516] src=donsbot.com ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

AI-assisted code at scale: provenance, quality, centrality and review time

A peer-reviewed ESEM 2026 paper by Audris Mockus, Peter C. Rigby, Don Stewart, Chandra Maddila and Nachiappan Nagappan analyzing 400,000 diffs from more than 10,000 developers at Meta found that AI-assisted code lands in less central code, in larger changes, in test files, and from higher-tenure authors. The study, "A Preliminary Analysis of the Impact of AI Assisted/Generated Code on Quality, Centrality and Review Time at Scale" (LIPIcs vol. 394, pp. 93:1–93:23), also reports that review time goes down and severe-incident rates are lower for diffs containing AI code, though both results are confounded because AI code appears in less central contexts to begin with. The paper is the first published peer-reviewed documentation of Mockus's code provenance system, which identifies AI authorship by tracking every character changed in files through source control rather than relying on heuristics.

recommendation

Attribute AI code by tracking character-level provenance through source control rather than heuristics, and control for code centrality before crediting AI with lower review time or incident rates.

more in playbook: Evals and testing for LLM apps
read1 min views3 publishedNov 18, 2026
AI-assisted code at scale: provenance, quality, centrality and review time
Image: source

A rare paper publication from me, the first for a while:

A Preliminary Analysis of the Impact of AI Assisted/Generated Code on Quality, Centrality and Review Time at Scale — Audris Mockus, Peter C. Rigby, Don Stewart, Chandra Maddila, and Nachiappan Nagappan. ESEM 2026, Software Engineering in Practice track, Munich, 8–9 Oct 2026. LIPIcs vol. 394, pp. 93:1–93:23.

PDF — DOI: 10.4230/LIPIcs.ESEM.2026.93 This is the first published peer-reviewed piece on the code provenance system I’ve been working on for the last two years. The core idea: track every character’s provenance. Identify AI authorship through the characters changed in files, and track the change through source control — using accurate filesystem and source-control-based analysis, not heuristics.

It’s a lot more sophisticated now, but the core idea is there.

What we found, across 10,000+ developers and 400,000 diffs at Meta: AI-assisted code lands more in less central code, in larger changes, in test files, and from higher-tenure authors. Review time goes down and severe-incident rates are lower for diffs with AI code — though both are confounded by the fact that AI code shows up in less central contexts to begin with.

The paper is the first published documentation of this work.

── more in #artificial-intelligence 4 stories · sorted by recency
skills-desktop.vercel.app · · #artificial-intelligence
Skills Desktop
── more on @audris mockus 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/ai-assisted-code-at-…] indexed:0 read:1min 2026-11-18 · —