From 8faadf94683851e035018fe32557e927498a6b17 Mon Sep 17 00:00:00 2001 From: Claude Date: Thu, 19 Nov 2026 14:07:01 +0000 Subject: [PATCH] SR-20261119-2137: fold in objections (launch scope, near-wall item, wording) Co-Authored-By: Claude Opus 5.5 --- docs/claude/stage-review-SR-20261119-2137.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/docs/claude/stage-review-SR-20261119-2137.md b/docs/claude/stage-review-SR-20261119-2137.md index 8861e424e..99c0f7aa4 100644 --- a/docs/claude/stage-review-SR-20261119-2137.md +++ b/docs/claude/stage-review-SR-20261119-2137.md @@ -43,18 +43,18 @@ Reports: MeltSol, MeltAssist, MoldSol, NewMeltAstra, Grok, MeltWin (stood down), ### Agreements (all reports consistent) 1. **What H2 is in 3D.** A mesh message-passing architecture (local messages on real mesh edges, mass-weighted aggregation, per-component global tokens, per-node decoder) that can be re-instantiated on tetrahedral volumes (Greif) and triangle surfaces (ShapeNet). Input layer, normalisation, backbone and head were retrained from scratch for ShapeNet; no weight or fill-prior transfer has been tested. 2. **What Greif establishes.** On our grouped protocol (552 parts / 204 families, 5 folds) H2 lowers family-weighted field error 7.08 → 6.58 / 6.59 % (two seeds), in every fold and robust to leaving out any family. Hard last-fill location is worse (.377 → .457 / .408 Rg). 34 shared misses (half also missed by A) are unexplained by tail-geometry attributes. Not established: new families from another source, process or gate interventions, any last-fill benefit, any paper-level comparison. -3. **What ShapeNet establishes.** GINO reproduced on its own protocol (7.43 %, 3 seeds; paper 7.12 %). The untuned H2-P is clearly worse: +2.58 pp, paired CI [+2.33, +2.85]. Only GINO's Table 2 is a verified same-protocol public number; OTNO / PCNO undetermined. No SOTA claim is possible or made. -4. **Next test.** GINO-Greif (matched protocol, 2 folds × 2 seeds, 212 parts / 78 families, paired GINO − H2) is unanimously first. Its reviews have passed (combined pre-score + custody delta fbaef6e2); it needs only Yanqi's launch OK. -5. **Generality needs data we do not have.** A real benchmark needs independent families with an official family split, explicit and varying gates, material/process variation, per-node fill time and a public licence. None public was found (Grok). Best available probes: family holdouts from ABC chunk hashes in v4/v5, and the 196-case warpage set if its families are new and its fill phase is shown to match. +3. **What ShapeNet establishes.** GINO reproduced on its own protocol (7.43 %, 3 seeds; paper 7.12 %). The untuned H2-P is clearly worse: +2.58 pp, paired CI [+2.33, +2.85]. Only GINO's Table 2 is a verified same-protocol public number; OTNO / PCNO stay context only: their author code de-normalises pressure, but the ordered case IDs, query layout and checkpoint/seed rule are not verified as matching. No SOTA claim is possible or made. +4. **Next test.** GINO-Greif (matched protocol, 2 folds × 2 seeds, 212 parts / 78 families, paired GINO − H2) is unanimously first. Its reviews have passed (combined pre-score + custody delta fbaef6e2). Pending Yanqi's decision whether to launch; before execution MeltSol adopts the exact PASS per the frozen contract, binds the formal ShapeNet ruling and the live phase-3 budget, and passes the card-admission gate. Both arms predict the residual on the same FP64 volume clock (MoldSol's question). +5. **Generality needs data we do not have.** A real benchmark needs independent families with an official family split, explicit and varying gates, material/process variation, per-node fill time and a public licence. We have not found a verified, fully matching public injection-molding benchmark (Grok; not proof that none exists). Best available probes: family holdouts from ABC chunk hashes in v4/v5, and the 196-case warpage set if its families are new and its fill phase is shown to match. ### Points resolved in this checkpoint (no further round needed) - **Packing removal and the fill phase** (Grok: should not change fill, inferred; TRON/MeltSol: switchover precedes full fill, so late fill can change). Not a matter of opinion: the pre-registered rule stands (case counts as same-process only if fill completes and switchover ≥ 99 %, post-switchover tail reported separately); the logs decide. - **Remeshing variability** (NewMeltAstra): adopted for future intervention benchmarks: a design ranking is declared unjudgeable where the true gate/process effect is smaller than the remeshing variability of the reference solver. -- **Grid mapping / near-wall aliasing** (MoldSol): added as a report item for GINO-Greif (error by distance-to-wall band), not a gate; the pre-registered gate is unchanged. +- **Grid mapping / near-wall aliasing** (MoldSol): this round reports only the existing fixed binary near-wall per-part relative L2 already in the frozen comparison contract (18e0e729); it cannot by itself attribute error to mapping aliasing. A multi-band distance-to-wall diagnostic is a separately scoped follow-up, not part of this run. - **H2-P tuning**: not now (MeltAssist, MeltSol). A tuned H2-P would need its own pre-registered entry and would still be compared with a GINO given equal tuning. ### Prioritised next tests with stop criteria -1. **GINO-Greif** (needs Yanqi's launch OK). Stop if the first-epoch projection exceeds 100,000 GPU-s, pairing is incomplete, or custody/frozen-hash gates fail. Outcome per pre-registration: GINO better → GINO-type becomes the default for both tasks; comparable → keep both, decide on cost; H2 better → isolate H2's molding-specific advantage. Last fill and the hard subset reported, not gated. +1. **GINO-Greif** (needs Yanqi's launch OK). Stop if the first-epoch projection exceeds 100,000 GPU-s, pairing is incomplete, or the local prediction-freeze / hash gates fail (Drive archiving stays on an independent HOLD and does not gate local scoring). Outcome per pre-registration: GINO better → GINO-type becomes the default for both tasks; comparable → keep both, decide on cost; H2 better → isolate H2's molding-specific advantage. Last fill and the hard subset reported, not gated. 2. **Metadata audit** (CPU, no labels): v4 LOG/YML coverage, warpage-set family overlap and V/P fields. Stop treating a source as a same-process holdout if families overlap, fill is incomplete or switchover < 99 %. 3. **Family-holdout evaluation** on genuinely new families (from step 2), frozen models only, pre-registered field and tail tolerances. Stop promoting any model whose CI on new families fails the tolerance. 4. **Parked:** last-fill losses (until a cross-seed reproducible mechanism appears), Moldflow generation (Adviser cannot export per-node fields; needs Insight/Synergy), pretraining / weight transfer (would need pretrained-vs-random at fixed target data and compute).