| Dimension | Shared | Only in A | Only in B | Overlap |
|---|---|---|---|---|
| Sections | 0 | 1 | 1 | 0% |
| Commands | 0 | 0 | 0 | — |
| Section tags | 0 | 2 | 2 | 0% |
What each file covers
Sections
0 shared · 1 only in A · 1 only in B- − ML Evaluation Memory
- + ML Instructions
Commands
neither file has anySection tags
0 shared · 2 only in A · 2 only in B- − code-style
- − performance
- + do-not
- + agent-behaviour
Line diff
Aledon8/OpenLeukemia · ml/evaluation/CLAUDE.md
@@ −1 @@
1# ML Evaluation Memory
2
3Apply this inside `ml/evaluation/`.
4
5- Report validation setup, data splits, metrics, and known limitations.
6- Prefer clinically cautious interpretation of model quality.
7- Track false positives, false negatives, calibration, and subgroup concerns when relevant.
8- Evaluation artifacts should support review, not overstate readiness.
9- Summaries should state what the model can and cannot support.
10
Aledon8/OpenLeukemia · .github/instructions/ml.instructions.md
@@ +1 @@
1---
2applyTo: "ml/**/*"
3---
4
5# ML Instructions
6
7- Keep structured ML workflows separate from LLM explanation workflows.
8- Use measurable criteria: split, metric, threshold, calibration, and known failure modes.
9- Do not commit patient-identifying or sensitive medical data.
10- Model outputs support signals and trends, not diagnosis or treatment guidance.
11- Document label assumptions, cohort limitations, and evaluation caveats near the relevant code or report.
12
@@ −1 +1 @@
1−# ML Evaluation Memory
1+---
2+applyTo: "ml/**/*"
3+---
24
3−Apply this inside `ml/evaluation/`.
5+# ML Instructions
46
5−- Report validation setup, data splits, metrics, and known limitations.
6−- Prefer clinically cautious interpretation of model quality.
7−- Track false positives, false negatives, calibration, and subgroup concerns when relevant.
8−- Evaluation artifacts should support review, not overstate readiness.
9−- Summaries should state what the model can and cannot support.
7+- Keep structured ML workflows separate from LLM explanation workflows.
8+- Use measurable criteria: split, metric, threshold, calibration, and known failure modes.
9+- Do not commit patient-identifying or sensitive medical data.
10+- Model outputs support signals and trends, not diagnosis or treatment guidance.
11+- Document label assumptions, cohort limitations, and evaluation caveats near the relevant code or report.
1012
