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.

A scikit-learn-compatible library for estimating prediction intervals and controlling risks, based on conformal predictions.

01Result

scikit-learn-contrib/MAPIE ↗

scikit-learn-contrib/MAPIE AI coding statistics: 12.5%

of 128 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
12.5% agent · top contributor 87.5%3 contributors
individual

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

16
agent commits
112
other considered commits
3
agent contributors
87.5%
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

16assisted
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
2026-0212.5%8
2026-030%33
2026-045%20
2026-0511.1%9
2026-0634.6%26
2026-0720%20
2026-080%11
2026-090%1

Peak month: 34.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic1310.2%
GitHub CopilotGitHub21.6%
Cursor AgentAnysphere10.8%

03Evidence

Inspect the matches

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

Matched commit samples

  • db75c85c on GitHubci: drop CITATION.cff auto-update job from release workflow (#962)Claude Code
  • 91dd8775 on GitHubfix: raise NotImplementedError for RKHS path in conditional conformal (#96Claude Code
  • 76c05453 on GitHubdocs: add conditional CP gallery examples and reorganize gallery (#957)Claude Code
  • 6d4d6ec0 on GitHubfeat: add online martingale test for exchangeability (#904)GitHub Copilot
  • 02ad0f9f on GitHubchore: improve contributing guide and release checklist (#863)GitHub Copilot
  • 485ed511 on GitHubfix: update ts-changepoint notebook after quantile refactor (#956)Cursor Agent

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 window129
Merge commits removed−1
CI / dependency bots removed−0
Considered128

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →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 scikit-learn-contrib/MAPIE

Scan another repository

Try