Review economics
tracel-ai/burn
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.9× the reviews submitted of the rest.
≥6%
Attributed
a floor
6
Attributed PRs
94
Other PRs
100
Read
Attributed — the latest 5
#5256 fix(burn-optim): correct LBFGSConfig::init doc comment
1 reviews · 6h to merge
#5251 Update to new cubecl environment
0 reviews · 4h to merge
#5204 feat: add sequential learning rate scheduler
1 round · 3 reviews · 3.4d to merge
#5194 Fix deadlock when a Backward step runs a nested backward
1 reviews · 5.1d to merge
#5209 docs: document per-device default dtypes; make AlreadyInitialized error actionable
1 round · 2 reviews · 9h to merge
The rest — the latest 5
#5302 test(burn-tensor): run the doc examples instead of only compiling them
1 round · 2 reviews · 24h to merge
#5307 fix(tensor): topk check for k <= shape[dim]
0 reviews · 1h to merge
#5303 update cubecl and cubek
2 reviews · 17h to merge
#5306 fix(cubecl): update rev for constant bitcasts fix
0 reviews · 0h to merge
#5301 fix(docs): correct chained reduction doc examples in numeric.rs
1 reviews · 0h to merge
How this was measured
6% 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 2908 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, Devin.
“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 tracel-ai/burn 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 tracel-ai/burn — 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