Every commit scored for change-risk against this repo's own history, so 'elevated' means elevated here rather than on some global curve.
Needs review
5 commits sit in this repo's top risk tercile, which is 36% of the 14scored. The cut is drawn against this codebase's own history rather than a global curve, so a quiet repo still fills its top band, and here it starts at 8.1 out of 10. What pushes a commit up is size and spread together: a large change confined to one area scores below a smaller one scattered across a dozen files.
Commit categories over time, read off the subject line. Fixes carry the accent because that is the series this chart exists to show.
How this repo's commit mix shifts over time.
Ranked by change-risk, highest first. Priority is a tercile of this repo's own distribution, so a quiet repo still fills its top band.
| # | Commit | Author | When | Lines | Risk | Top driver |
|---|---|---|---|---|---|---|
| 1 | 7ca26230AI FaceMat pipeline: SegFace + SAM2 face matte generation for Scratch | Es Fem | 2mo ago | +966 -0 | 96%Elevated | more lines added than baseline |
| 2 | 92b26716Add installer, extract scratch_api.py module | Es Fem | 2mo ago | +483 -229 | 89%Elevated | more lines added than baseline |
| 3 | 0086f66bfix(install): Rewrite script to address uv offline failures and Blackwell (sm_120) compatibility | es-fem | 2mo ago | +190 -178 | 82%Elevated | more lines added than baseline |
| 4 | 3be0d591Add SwinV2B and SwinB-LaPa models, dataset-aware class mapping | Es Fem | 2mo ago | +140 -16 | 75%Elevated | more lines added than baseline |
| 5 | 6fea9c24README: rewrite for Scratch Custom Commands workflow (install, configure, use) | Es Fem | 2mo ago | +103 -166 | 68%Elevated | more lines added than baseline |
| 6 | 64423ba4Installer: auto-detect GPU, set correct CUDA/PyTorch versions | Es Fem | 2mo ago | +75 -4 | 61%Typical | more lines added than baseline |
| 7 | 784e7897README: update installation to use installer, add project structure and scratch_api docs | Es Fem | 2mo ago | +46 -19 | 54%Typical | more lines added than baseline |
| 8 | d910e8bdREADME: add Scratch custom button integration with XML example | Es Fem | 2mo ago | +43 -0 | 46%Typical | more lines added than baseline |
| 9 | 1eb7c125Add Scratch REST API port and access key configuration | Es Fem | 2mo ago | +22 -1 | 39%Typical | more lines added than baseline |
| 10 | e6a2812bREADME: document Scratch REST API port/auth configuration | Es Fem | 2mo ago | +18 -0 | 32%Below typical | more lines added than baseline |
| 11 | fa14feb0README: add GPU auto-detection table to installation docs | Es Fem | 2mo ago | +11 -2 | 25%Below typical | more focused than baseline |
| 12 | 6b700c6bRefactor comments and add OUTPUT_NODE_TYPE_UUID | osmaras | 2mo ago | +8 -5 | 18%Below typical | fewer lines added than baseline |
| 13 | 3dc7f5f6Fix installer: add SegFace Model dropdown to generated .acc template | Es Fem | 2mo ago | +4 -0 | 11%Below typical | fewer lines added than baseline |
| 14 | f1319d27Fix typos in README for Stage 4 | osmaras | 2mo ago | +2 -2 | 4%Below typical | fewer lines added than baseline |
Two views of the same model: where the cuts fall, and what commit shape lands you above them.
Every scored commit, binned on the raw 0 to 10 score rather than the percentile. Percentile ranks are uniform by construction, so that axis has no shape to draw. The dashed lines are the tercile cuts behind each row's priority pill.
The 14 most recent commits, on their own recency sample rather than the feed above: that defaults to risk-sorted, so reusing it would plot only the top tercile and call it the spread. Big and scattered is what the model penalises. Click a dot to open it.
Repowise tracks change history across 2 files in osmaras/ai_facemat. In the last 90 days 2 files were touched, 7 times in total, most often AI_FaceMat.py. Every commit is scored for change risk from its size, spread and the history of the files it touches.
