From 479b2f52733f7b53542b58fbe1b560f051876795 Mon Sep 17 00:00:00 2001 From: Claude Date: Wed, 18 Nov 2026 03:42:19 +0000 Subject: [PATCH] Stage plan: synthesis update, frozen Track A/B protocols, idle-GPU rule Co-Authored-By: Claude Opus 5.5 --- docs/claude/stage-research-plan-2026-11-18.md | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/docs/claude/stage-research-plan-2026-11-18.md b/docs/claude/stage-research-plan-2026-11-18.md index 887a39744..ce1cfa61a 100644 --- a/docs/claude/stage-research-plan-2026-11-18.md +++ b/docs/claude/stage-research-plan-2026-11-18.md @@ -19,3 +19,12 @@ Undermind deep searches (workspace "Injection Molding Hele Shell Manifold Neural 1. Now: phase 3 continues (item 1 → seed 1 → c → b → ensemble). Literature (deep searches, MeltAssist synthesis), Track A and B protocol extraction, and Track C/D specs proceed on paper in parallel. 2. Next compute after item 1: Track A on Gre24's protocol (cheap), then Track B GINO reproduction. 3. Tracks C/D pilots only after their gates and the licence answer. + +## Update after MeltAssist synthesis (2026-11-18, parts 1-3) + +- **Track A protocol frozen:** five independent random 314/315 splits (our published seeds; protocol-level re-creation), per-part RMSE / max(full truth) proxy, min/median/max over test parts averaged over splits; A and H2 paired on the same splits; family leakage of random splits reported. +- **Track B frozen:** original GINO decoder protocol only (ShapeNet 611, 500/111; Ahmed 551, 500/51; de-normalised relative L2). Targets: GINO 7.12 % / 8.31 % and same-protocol results confirmed by MeltAssist; other splits in a context table. ShapeNet data (Zenodo 13936501) pre-authorised after the ID-mapping check; Ahmed on hold until the original 551 source is confirmed. Reproduce GINO with the paper recipe first. +- **Track C evidence:** batch Moldflow automation is proven (Greif; Per23: 1,080 runs, about 22 min/run, 3 geometries). openInjMoldSim's high-fidelity example cost 34 h on 192 cores, so open-source 3D VOF is *not* a cheap mass generator. Report independent geometries and conditions separately, and acceptance rate and total cost per valid label. +- **Track D evidence:** GeoPT (13,463 ShapeNet geometries × random dynamics fields, no CFD labels; 144-576 GPU-h) reports 20-60 % label savings on several 3D tasks (not molding). Geometry-only pretraining is therefore the first D arm, compared with scratch at equal fine-tune budget, pretraining cost reported separately. +- **Track E:** RL evidence (Kim25 surrogate-environment process optimisation; Sza22 VARTM layup) is narrow and not thermoplastic filling; stays literature-only until a trusted environment exists. +- **Idle GPUs:** approved queue items may use GPUs that item 1 does not need, each after its own review: Track A H2 first, then seed 1.