fix(causal): Use operator rho clamp and strict sanity check#4
fix(causal): Use operator rho clamp and strict sanity check#4DaviBonetto merged 1 commit intomainfrom
Conversation
Replace the mean-channel proxy with an operator-level rho check, remove the hard per-channel floor, and keep the dt clamp monotonic with a strict post-check. Add focused smoke tests for bias handling and clamp behavior.
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (2)
✨ Finishing Touches🧪 Generate unit tests (beta)
📝 Coding Plan
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Replace the causal-clamp proxy with an operator-level rho check in the dt hook, remove the hard per-channel floor that was over-constraining the intervention, and keep rho_current/rho_after explicit in the diagnostics.
This keeps the implementation aligned with the paper's clamp semantics and makes the Colab reproduction easier to verify with a strict sanity check.
Also adds focused smoke tests for dt_bias application, rho computation, and clamp monotonicity.