Review economics
roboflow/supervision
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.8× the reviews submitted of the rest.
≥49%
Attributed
a floor
47
Attributed PRs
53
Other PRs
100
Read
Attributed — the latest 5
#2474 docs: convert fenced examples to doctests in dataset/formats/coco.py
2 reviews · 5h to merge
#2469 fix(dataset): 3D empty mask for VOC background
1 reviews · 4h to merge
#2465 refactor: vectorize `get_labels_text()` in annotators/utils
2 reviews · 41h to merge
#2425 docs: improve doctests in draw/utils.py
1 round · 4 reviews · 15.5d to merge
#2449 feat(vlm): add Gemini 3.5 Flash parsing support
3 reviews · 4h to merge
The rest — the latest 5
#2028 ITZ-90 replaces ga tag with unified instance tag
1 reviews · 239.0d to merge
#2470 test(metrics): verify live sklearn parity
5 reviews · 2.1d to merge
#2473 ⬆️ Bump cryptography from 48.0.1 to 50.0.0 in the uv group across 1 directory
1 reviews · 1h to merge
#2472 ⬆️ Bump pymdown-extensions from 10.21.3 to 11.0 in the uv group across 1 directory
1 reviews · 3h to merge
#2462 releasing `0.30.0`
0 reviews · 6.1d to merge
How this was measured
49% 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 1369 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, OpenAI Codex, GitHub Copilot coding agent, Cursor agent.
“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 roboflow/supervision 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 roboflow/supervision — 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