Pulse
2026-09-18-v3.0
Dataset
2026-10-27-catalog-ai-v2
Ruleset
b2e8889c66f7
Scanned
2026-10-27
Window
February–September 15, 2026
Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

Mirror of Apache POI gitbox. The Java API for Microsoft Documents.

01Result

apache/poi ↗

apache/poi AI coding statistics: 13.7%

of 293 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
13.7% agent · top contributor 90%5 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

40
agent commits
253
other considered commits
5
agent contributors
90%
largest contributor

02Drivers

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

40assisted
0autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-020%29
2026-030%19
2026-0420%10
2026-0519.1%47
2026-061.1%94
2026-070%20
2026-0817.9%39
2026-0960%35

Peak month: 60%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic289.6%
GitHub CopilotGitHub124.1%

03Evidence

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

  • 3a96efca on GitHubDataFormatter: default useCachedValuesForFormulaCells to true (#1259)Claude Code
  • ae716941 on GitHubClose the filesystem if HSLF dual-storage lookup fails (#1251)Claude Code
  • 3cb3ff6f on GitHubBuild the cipher before opening the zip entry in AesZipFileZipEntrySource Claude Code
  • 1c53108d on GitHubBug 66568: Adjust selecting color from master-slideGitHub Copilot
  • 702aca1a on GitHubuse math multiplyexact for multiplication (#1095)GitHub Copilot
  • a203637d on GitHubAdd @Isolated to test classes that mutate static limits (#1094)GitHub Copilot

04Method

What entered the denominator

The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.

Exclusion ledger

Commits in window360
Merge commits removed−0
CI / dependency bots removed−67
Considered293

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Java AI coding statisticsCompare evidence across Java repositories →GitHub AI commit analyzerInspect another repository with the same evidence model →
Reproduce this observation

Run the same detector locally.

Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.

npx qmmit-cli apache/poi

Scan another repository

Try