Review economics
modelscope/ms-swift
Read from the 100 most recently merged pull requests ·
Not enough merged pull requests on both sides yet to compare how they land in review.
≥1%
Attributed
a floor
2
Attributed PRs
98
Other PRs
100
Read
Attributed — the latest 2
The rest — the latest 5
#9856 Fix missing LoRARequest injection in GRPOVllmEngine.infer_async
1 reviews · 11h to merge
#9834 Support ds v4 flash 0731
1 reviews · 33h to merge
#9853 docs(readme): fix v3.0 release note links
1 reviews · 1h to merge
#9851 fix(infer): reject prompts without generation space
1 reviews · 2h to merge
#9844 Fix GRPO offload compatibility with FSDP2 CPU offload
3 reviews · 6h to merge
How this was measured
1% of merged commits carry agent attribution — a floor, not the share; tools that only complete code inline leave no commit trail, so the unattributed side includes AI-assisted work; reads 100 of 3450 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, Gemini CLI.
“Attributed” means a commit carried an agent’s signature — a co-author trailer, an agent commit identity, or an agent bot account. Tools that only complete code inline leave no such mark, so the other column is “rest”, not “human-written”. Full method and its limits
The badge reads this repo’s current report, so it follows the number.
Tell me when this moves
We re-read modelscope/ms-swift weekly and email only when the number changes materially.
Read your own repos
This one is public. For a private repo, run the same read locally through your own GitHub credentials — nothing is installed and nothing is sent to us.
npx @ambera/review-taxWant this continuously on modelscope/ms-swift — each pull request paired to the task it came from, and the work graded from its review loop rather than its diff size? Claim this repo in Forge
Browse every repo people have read · Read a different repository