| Dimension | Shared | Only in A | Only in B | Overlap |
|---|---|---|---|---|
| Sections | 0 | 1 | 1 | 0% |
| Commands | 0 | 0 | 0 | — |
| Section tags | 0 | 1 | 1 | 0% |
What each file covers
Sections
0 shared · 1 only in A · 1 only in B- − ML Inference Memory
- + ML Rules
Commands
neither file has anySection tags
0 shared · 1 only in A · 1 only in B- − performance
- + do-not
Line diff
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
Aledon8/OpenLeukemia · .cursor/rules/ml.mdc
@@ +1 @@
1---
2description: ML workspace rules
3globs:
4 - "ml/**/*"
5alwaysApply: false
6---
7
8# ML Rules
9
10- Keep structured ML workflows separate from LLM explanation workflows.
11- Use measurable criteria: split, metric, threshold, calibration, and known failure modes.
12- Do not commit patient-identifying or sensitive medical data.
13- Model outputs support signals and trends, not diagnosis or treatment guidance.
14- Document label assumptions, cohort limitations, and evaluation caveats near relevant code or reports.
15
@@ −1 +1 @@
1−# ML Inference Memory
1+---
2+description: ML workspace rules
3+globs:
4+ - "ml/**/*"
5+alwaysApply: false
6+---
27
3−Apply this inside `ml/inference/`.
8+# ML Rules
49
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.
10+- Keep structured ML workflows separate from LLM explanation workflows.
11+- Use measurable criteria: split, metric, threshold, calibration, and known failure modes.
12+- Do not commit patient-identifying or sensitive medical data.
13+- Model outputs support signals and trends, not diagnosis or treatment guidance.
14+- Document label assumptions, cohort limitations, and evaluation caveats near relevant code or reports.
915
