| Dimension | Shared | Only in A | Only in B | Overlap |
|---|---|---|---|---|
| Sections | 0 | 1 | 1 | 0% |
| Commands | 0 | 0 | 0 | — |
| Section tags | 1 | 1 | 0 | 50% |
What each file covers
Sections
0 shared · 1 only in A · 1 only in B- − ML Training Memory
- + ML Inference Memory
Commands
neither file has anySection tags
1 shared · 1 only in A · 0 only in B- − code-style
- performance
Line diff
Aledon8/OpenLeukemia · ml/training/CLAUDE.md
@@ −1 @@
1# ML Training Memory
2
3Apply this inside `ml/training/`.
4
5- Prefer reproducible training scripts with explicit inputs, seeds, outputs, and metrics.
6- Keep patient-identifying data out of the repository.
7- Document label assumptions and cohort limitations near the training code.
8- Structured models support signals and trends, not diagnosis.
9
Aledon8/OpenLeukemia · ml/inference/CLAUDE.md
@@ +1 @@
1# ML Inference Memory
2
3Apply this inside `ml/inference/`.
4
5- Keep inference interfaces typed, deterministic, and easy to validate.
6- Return explainable scores or signals with limitations, not clinical conclusions.
7- Preserve compatibility with `ai-service/` consumers when inference code is promoted.
8- Validate feature order, units, and missing-value behavior explicitly.
9
@@ −1 +1 @@
1−# ML Training Memory
1+# ML Inference Memory
22
3−Apply this inside `ml/training/`.
3+Apply this inside `ml/inference/`.
44
5−- Prefer reproducible training scripts with explicit inputs, seeds, outputs, and metrics.
6−- Keep patient-identifying data out of the repository.
7−- Document label assumptions and cohort limitations near the training code.
8−- Structured models support signals and trends, not diagnosis.
5+- Keep inference interfaces typed, deterministic, and easy to validate.
6+- Return explainable scores or signals with limitations, not clinical conclusions.
7+- Preserve compatibility with `ai-service/` consumers when inference code is promoted.
8+- Validate feature order, units, and missing-value behavior explicitly.
99
