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.

⚡ TabPFN: Foundation Model for Tabular Data ⚡

01Result

PriorLabs/TabPFN ↗

PriorLabs/TabPFN AI coding statistics: 47.5%

of 276 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
47.5% agent · top contributor 26%28 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

131
agent commits
145
other considered commits
28
agent contributors
26%
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

127assisted
4autonomous

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
2026-0210.5%19
2026-0319%21
2026-0429.6%27
2026-0538.5%52
2026-0650%56
2026-0760%30
2026-0866.7%36
2026-0977.1%35

Peak month: 77.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic11943.1%
Gemini CLIGoogle124.3%
OpenAI CodexOpenAI10.4%
Cursor AgentAnysphere10.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • 6e42a1a4 on GitHubCount distinct values for all columns of a numeric array at once in modaliClaude Code
  • 27f4b303 on GitHubFreeze import-time objects so the per-test gc.collect() stays cheap (#1279Claude Code
  • 0440d1af on GitHubRun unpinned tests on the fast TabPFN-3.5 checkpoint (#1281)Claude Code
  • 5a729389 on GitHubadd KV cache dtype as explicit argument [PRI-347] (#1120)Gemini CLI
  • bcb144ea on GitHubFix overflow in Yeo-Johnson inverse transform clip bound (#1105)Gemini CLI
  • af063726 on GitHubSynchronize the single-device stream in parallel_execute so timing reflectGemini CLI
  • 75afafec on GitHubAdd a multitask architecture module and its model sources (#1256)OpenAI Codex
  • afe14306 on GitHubfeat: add fine-tuning validation frequency (#1144)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 window337
Merge commits removed−0
CI / dependency bots removed−61
Considered276

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Gemini CLI commitsBrowse repositories with detected Gemini CLI 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 PriorLabs/TabPFN

Scan another repository

Try