Document pre-existing RuntimeWarnings in CallawaySantAnna bootstrap

Add TODO item for RuntimeWarnings that occur during influence function
aggregation in staggered.py. These warnings (divide by zero, overflow,
invalid value in matmul) occur with small sample sizes or edge cases
but don't affect result correctness.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Author: igerber

TODO.md

@@ -85,6 +85,10 @@ Enhancements for `honest_did.py`:
 ## CallawaySantAnna Bootstrap Improvements
 
 - [ ] Consider aligning p-value computation with R `did` package (symmetric percentile method)
+- [ ] Investigate RuntimeWarnings in influence function aggregation (`staggered.py:1722`, `staggered.py:1999-2018`)
+  - Warnings: "divide by zero", "overflow", "invalid value" in matmul operations
+  - Occurs during bootstrap SE computation with small sample sizes or edge cases
+  - Does not affect correctness (results are still valid), but should be suppressed or handled gracefully
 
 ---