Phase 1 synthesis: H1 single factor, no causality penalty (fixed pre-run)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
ClaudeandClaude Opus 5.5 committed 2026-11-17 03:25:53 +00:00
1 parent 8cd564c429
commit ee6d2e59e8
1 file changed
+1 -1
+1 -1
View File
@@ -27,7 +27,7 @@ Literature is marked as read in full by a tool (not page by page by a person); n
## Proposed phase 2 (at most two pre-registered hypotheses; for Yanqi's choice)
- **H1, physics prior plus learning (low cost, high prior):** learn a *correction* to the training-free eikonal map instead of t* from scratch.
- Arm (corrected per MoldAstra): EIK's dimensionless prediction *is* the strict volume quantile F, which is already one of A's 19 columns, so adding it as an input adds nothing. What changes is the **target**: F as a fixed skip connection, with the model learning t* - c F from the same 19 features.
- Against A, with field L2, last-filled location and Kendall tau all pre-registered as co-primary or secondary. Optionally add a causality penalty along propagation paths.
- Against A, with field L2, last-filled location and Kendall tau all pre-registered as co-primary or secondary. Decided now, before any run: **no causality penalty** in H1, so the target change is the only factor. F and t* use the same domain and normalisation, and costs are listed separately.
- Question: can one model keep EIK's end-of-fill accuracy and A's field accuracy?
- Cost: hours of CPU (a planning estimate, not measured). The residual target does not automatically keep EIK's end-of-fill advantage; the joint metrics have to show it.
- **H2, geometry-representation route (after H1, if Yanqi chooses) (Yanqi's direction; higher cost):** a geometry-aware neural operator with the structure the ML map recommends, *using the H1 target (correction on EIK) as its physics prior*.