- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
RISC-V Instruction Set Manual
01Result
riscv/riscv-isa-manual ↗riscv/riscv-isa-manual AI coding statistics: 3.8%
A small group is using agents. Adoption has spread beyond one person but is not project-wide.
02Drivers
What shapes this result
Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.
Assisted or autonomous
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
| Month | Agent share | Considered commits |
|---|---|---|
| 2026-02 | 2.3% | 44 |
| 2026-03 | 0% | 37 |
| 2026-04 | 0% | 103 |
| 2026-05 | 4.5% | 88 |
| 2026-06 | 0% | 34 |
| 2026-07 | 10% | 30 |
| 2026-08 | 0% | 17 |
| 2026-09 | 35.3% | 17 |
Peak month: 35.3%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 9 | 2.4% |
| GitHub Copilot | GitHub | 5 | 1.4% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
8c9b0122on GitHubUse American spellings for consistency with the rest of the manualClaude Code244da7baon GitHubFix ISA manual typosClaude Code637cb6deon GitHubResolve the contradiction the new convention exposedClaude Code48ffd2efon GitHubPotential fix for pull request findingGitHub Copilot9c1aa219on GitHubFix pre-commit failure in dco_check workflow formattingGitHub Copilot9cd6765eon GitHubPotential fix for pull request findingGitHub 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 | 452 |
| Merge commits removed | −72 |
| CI / dependency bots removed | −10 |
| Considered | 370 |
Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.
Continue exploring
Related coding-agent evidence
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 riscv/riscv-isa-manual