# Are AI-assisted commits reverted more often? I checked 663 matched pairs. The honest answer is 'can't tell'

> Source: <https://dev.to/vyankatesh/are-ai-assisted-commits-reverted-more-often-i-checked-663-matched-pairs-the-honest-answer-is-33j1>
> Published: 2026-11-20 12:10:48+00:00

**Recommendation:** Size commit-outcome studies for the base rate before running them: at ~0.2% revert rates, plan for roughly 10,000 matched pairs to detect a 2x effect, and validate keyword-based fix detection before trusting a null.
More in the playbook "Evals and testing for LLM apps": <https://wpnews.pro/playbooks/evals-testing>

**Disclosure:** I ran this study with an AI assistant (Claude), which wrote the code, did the analysis and drafted the paper. It also did the manual check of my fix heuristic, so that check is **not** an independent human review. Results are aggregate; no developer, repo or commit is named. This is observational: "associated with", never "causes".

**Question:** are commits that *disclose* AI help (e.g. a `Co-Authored-By: Claude` trailer) reverted or followed by a bug-fix more often than comparable human-only commits?

I wrote down the hypotheses and definitions *before* pulling any data. The short answer: **no clear difference, but the study is too small to say much.**

`gh`. No repo was cloned and no code was run.
Matching on size worked: median diff was 102 changed lines for AI-disclosed commits and 103 for controls.

Within 30 days, **1 of 663** AI-disclosed commits was reverted, versus **2 of 663** controls. Odds ratio 0.51, 95% CI **0.05 to 5.57**. That interval spans "much safer" to "5x worse". I checked my revert detector against the 264k commits in the downloaded histories: about 0.2% of commits get reverted, so reverts are just rare. Detecting a 2x effect at that rate would take on the order of 10,000 pairs (rough calculation).

My pre-registered "fix follow-up" rule: a later commit within 14 days, touching a same file, with `fix|bug|hotfix|regression` in the message. On a feasible 220-pair subset: OR **1.15 (0.75-1.77)**, consistent with no difference.

But I then read 100 flagged follow-ups and judged only **about 30%** to be plausible fixes (95% CI 22-40%). Common errors: shared `package.json`/README/lockfiles, a keyword in the body of a non-fix commit, merges of the same fix. So that "null" mostly reflects a noisy measurement. A stricter, *exploratory* variant gave the same picture (OR 1.16, 0.72-1.86).

For this sample: **no evidence of a difference, and little ability to detect one.** A real answer needs about 10x more pairs and a validated way to link fixes to the commits they fix (issue links or SZZ-style tracing), plus some idea of how reliably people disclose.

Related reading (arXiv): [On the Use of Agentic Coding](https://arxiv.org/abs/2509.14745), [Agentic Much? Adoption of Coding Agents on GitHub](https://arxiv.org/abs/2601.18341).

*Preprint-style write-up, not peer reviewed.*

*By Vyankatesh Rohokale*
