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

> Source: <https://donsbot.com/2026/11/17/ai-assisted-code-at-scale-provenance-quality-centrality-and-review-time/>
> Published: 2026-11-18 04:34:16+00:00

**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 the playbook "Evals and testing for LLM apps": <https://wpnews.pro/playbooks/evals-testing>

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](https://drops.dagstuhl.de/storage/00lipics/lipics-vol394-esem2026/LIPIcs.ESEM.2026.93/LIPIcs.ESEM.2026.93.pdf) — [DOI: 10.4230/LIPIcs.ESEM.2026.93](https://doi.org/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.
