From bd88e3ae60102afd91127e4347afab3e57b34504 Mon Sep 17 00:00:00 2001 From: Claude Date: Tue, 17 Nov 2026 07:37:23 +0000 Subject: [PATCH] Research tree: B14 probing, B15 opened (learned speed + eikonal solve), lit check, B1-v2 extension Co-Authored-By: Claude Opus 5.5 --- docs/claude/research-tree.md | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/docs/claude/research-tree.md b/docs/claude/research-tree.md index b8fb2766f..7c650dc69 100644 --- a/docs/claude/research-tree.md +++ b/docs/claude/research-tree.md @@ -24,11 +24,16 @@ Rules: | B11 | Topological cleaning of predicted fields: persistence simplification removes spurious extrema and saddles before the end-of-fill and event metrics | gate: on the B3 panel, apply a fixed persistence threshold to EIK, and later to the A/H1 full-node predictions, and check event precision, last-fill distance and tau (learning folds only) | Mold spec, Melt run | PRUNED (this fixed rule, all three arms) | | B12 | Path-integrated flow-resistance features: along the gate-to-node path, the bottleneck (minimum) thickness, the integral of ds/h^2, and the number of junctions crossed. Flow-competition information that Gre24's 19 columns lack | gate: A plus these 3 columns on one grouped fold at the 100 % pool; field L2 and last-fill distance against A, paired CI | Mold spec, Melt run | OPEN | | B13 | Region-context features without type matching (a covariate-controlled O1 precursor): means of F and D_w over generic connected regions at K = 8, added to A | gate: one fold. This is a cheap reference only: a null result does **not** close type-organised context, O1 or real connectivity, which stay independent open hypotheses | Mold spec, Melt run | OPEN | +| B14 | Flow-splitting index: number of near-shortest path families (5 % of D_f) and non-largest family band-volume share | B12's fixed rule, one fold | Mold spec (c09d428d), Melt run | PROBING (parallel) | +| B15 | Learn the propagation cost, keep the solver: regress local speed f = 1/abs(grad T) (true T, learning folds only) from geometry features, then solve the eikonal with the predicted speed and map it to time with the volume clock | gate: one fold; field L2, last-fill distance and tau against A. The speed must be inferable at prediction time (no test-label velocity). Literature basis: EikoNet / Eikonal DeepONet factorisation (MeltAssist check) | Mold spec, Melt run | OPEN | +| B10x | Freeze/shrinkage validity gate (unparked as a cheap gate while compute is idle) | per-field validity on 20 v5 parts | Melt | PROBING | | P1 | O2 local tensor readings | — | — | PRUNED (S1, S2, S3-A: no gain on the current recipe) | | P2 | Own graph flow-competition solver | — | — | PRUNED (infeasible: splu resource stop, GMRES numerical failure; the idea itself is untested) | | P3 | O1 with size-matched K = 8 partitions | — | — | PRUNED (eligibility 23 %; lesson: control cut area as a covariate, do not match it) | Log (newest first): +- 2026-11-17: MeltAssist literature check (EikoNet, Eikonal DeepONet, LENO, level-set advection operator): three distinct object classes (a solver for fixed media; an operator across media; transport of a moving interface). Future branches separate *learning the potential directly* / *learning the propagation cost and keeping the solver* (opened as B15) / *learning the moving interface*. B4 does not close learned potentials. +- 2026-11-17: B1-v2 scoring hit the post-fit CPU cap (a budget stop); +36,000 CPU-s labelled extension for that scoring only. H2 CPU tests pass (MeltAssist review); the pilot then the full run (4 GPUs) are authorised. B14 and B10x running in parallel. - 2026-11-17: **B6 PRUNED (fixed HKS).** Partial r = .044 / .053 / .062 at t = .1 / 1 / 10 over lambda_1, all below .10 (learning folds only; rank of the 19 columns plus intercept is 19 of 20). - **Learned (scope per MeltAstra):** a *linear* partial correlation on the learning side, controlling for the 19 columns, is small. Neither nonlinear increments nor out-of-sample effects were tested. - 2026-11-17: **Synthesis after B3-B11.** Clock (B4), loss (B7), cleaning (B11), spectral context (B6) and the sheet certifier (B5, parked) are all ruled out at these recipes. What remains open is *new information about how flow competes*: B12 (path resistance) and B13 (region context); learned representation H2 after B1's decision.