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.

CMS Offline Software

01Result

cms-sw/cmssw ↗

cms-sw/cmssw AI coding statistics: 0.7%

of 2,556 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

0.7% agent · top contributor 42.1%6 contributors

team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

agent commits

2,537

other considered commits

agent contributors

42.1%

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

19assisted

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

Peak month: 3.1%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
GitHub Copilot	GitHub	12	0.5%
Claude Code	Anthropic	8	0.3%

03Evidence

Inspect the matches

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

Matched commit samples

832c0e7d on GitHubL1TSC82ProngJetModel (#150)GitHub Copilot
ae2c9c9c on GitHubSupport for ClearEvent signalGitHub Copilot
22441b9a on GitHubAdd tests for computeCommonTopEntriesGitHub Copilot
d6f8ea11 on GitHubRecord the real ClassVersion=4 checksum for l1t::io_v1::P2GTCandidateClaude Code
2d00a201 on GitHubDrop unused setIsolationPT/setScalarSumPT setters from P2GTCandidateClaude Code
009d5e59 on GitHubAdd isEtSum/isHtSum flags and physical isolation/HT accessors to P2GTCandiClaude Code

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 window	3,536
Merge commits removed	−980
CI / dependency bots removed	−0
Considered	2,556

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 →C++ AI coding statisticsCompare evidence across C++ 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 cms-sw/cmssw

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	429
2026-03	0%	366
2026-04	3.1%	289
2026-05	0.7%	295
2026-06	0.8%	484
2026-07	0.3%	319
2026-08	0%	261
2026-09	2.7%	113