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 contact solver for physics-based simulations involving 👚 shells, 🪵 solids, 🪢 rods, 🧱 rigid bodies and ⏳ sand.

01Result

st-tech/ppf-contact-solver ↗

st-tech/ppf-contact-solver AI coding statistics: 91.9%

of 111 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

91.9% agent · top contributor 100%1 contributor

individual

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

102

agent commits

other considered commits

agent contributors

100%

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

102assisted

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

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	98	88.3%
GitHub Copilot	GitHub	4	3.6%

03Evidence

Inspect the matches

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

Matched commit samples

7deaf588 on GitHubdocs: expand disclaimer with solver limitationsClaude Code
89ede968 on GitHubdocs: add Building Your Own Solver section to READMEClaude Code
b3e6d6f0 on GitHubdocs: list extreme cases where a solution may not be foundClaude Code
647041ff on GitHubdocs: clarify reproduction file guidanceGitHub Copilot
80f9fb65 on GitHubdocs: thank YouTube communityGitHub Copilot
81c5564a on GitHubdocs: update deployment and acknowledgementsGitHub 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 window	111
Merge commits removed	−0
CI / dependency bots removed	−0
Considered	111

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 →Python AI coding statisticsCompare evidence across Python 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 st-tech/ppf-contact-solver

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	100%	2
2026-03	100%	6
2026-04	87.5%	8
2026-05	91.2%	57
2026-06	100%	4
2026-07	100%	7
2026-08	93.3%	15
2026-09	83.3%	12