diff --git a/docs/claude/stage-research-plan-2026-11-18.md b/docs/claude/stage-research-plan-2026-11-18.md index c308c3eef..887a39744 100644 --- a/docs/claude/stage-research-plan-2026-11-18.md +++ b/docs/claude/stage-research-plan-2026-11-18.md @@ -8,7 +8,7 @@ Undermind deep searches (workspace "Injection Molding Hele Shell Manifold Neural | Track | Question | First step (owner) | Gate before anything expensive | |---|---|---|---| -| A. Greif SOTA | Does H2 beat Gre24 *on Gre24's own protocol*? Our grouped protocol is stricter, so the paper number (3.38 % median RRMSE) is not comparable with ours | Phase 3 continues unchanged (item 1 running). MeltAssist: extract Gre24's exact split, metric and reported numbers. MeltAstra: then evaluate A and H2 on that protocol | Reproduction of Gre24's own number on its protocol first (we have 3.96 % on v4) | +| A. Greif SOTA | Does H2 beat Gre24 *on Gre24's own protocol*? Our grouped protocol is stricter, so the paper's numbers (Table C.6: 3.38 % median RRMSE at 100 trees / depth 8; 3.31 % at depth 6, the lowest in that table; MeltAssist 2026-11-18) are not comparable with ours. The exact split seed is not published, so Track A compares A and H2 on the *same* re-created split(s), never against the paper number alone | Phase 3 continues unchanged (item 1 running). MeltAssist: extract Gre24's exact split, metric and reported numbers. MeltAstra: then evaluate A and H2 on that protocol | Reproduction of Gre24's own number on its protocol first (we have 3.96 % on v4) | | B. GINO benchmark | Does our mesh model match or beat GINO and later SOTA on GINO's public 3D tasks (ShapeNet car pressure 500/111; Ahmed body 500/51)? | MeltAssist: verify data sources, splits, metrics and the current reported SOTA table. MeltAstra: download, reproduce the GINO baseline | Reproduce a published baseline within its reported error before claiming anything | | C. Data generation | Can we generate thousands of filling simulations cheaply enough and faithfully enough? | Deep search 1 + MoldAstra: a fidelity ladder (eikonal proxy → Hele-Shaw / 2.5D → open-source 3D VOF → commercial) with cost per part. **Question to Yanqi: is a Moldflow or Moldex3D licence available?** Greif's own data came from scripted Moldflow 2023, which is the fastest faithful route | A pilot on about 10 Greif parts comparing the generator with the Moldflow labels, with a pre-registered fidelity threshold | | D. Pretraining | Does pretraining (synthetic labels from C, or self-supervised geometry) improve H2 on Greif at equal fine-tune budget? | MoldAstra: evaluation design (equal compute, same splits). Self-supervised geometry pretraining needs no generator and can be tested first | Only after phase-3 item 1 shows a data limit, or after C passes its fidelity gate |