Files
MeltMind/docs/claude/gre24-reproduction-spec-2026-11-15.md
T

6.8 KiB

Gre24 faithful reproduction: specification and plan (Claude, 2026-11-15 night)

Source: Greif, Lechner, Meyer, Composites Part A 185 (2024) 108340, author PDF from OPUS docId 113920, full text extracted locally with pypdf (scratch_pdf/gre24.txt). Section, equation and table numbers refer to the paper. R2-G24 in S2 was an approximation and is not this reproduction. The frozen S2/S3 results stay unchanged.

1. Method as published (status: S = specified, A = ambiguous, M = missing)

Item Paper Status
Data Autodesk Moldflow simulations of 629 random ABC geometries; one random gate; PP GF30; automatic flow. Dataset DOI in footnote 1: 10.5281/zenodo.10027027 (v4 era); "Data will be made available on request" S. Check whether the v4 record is downloadable
Mesh Reuses the Moldflow tet mesh; all nodes S
Distances (Table 1, eq. 5) Eikonal on the tet mesh with fim-python (tetFIM, Fu et al.), phi0 = 0. D_w: f = 1, source = wall boundary. D_i: f = 1, source = gate. D_f: f = D_w, source = gate S. Gate source set (node or face) is A
Normalisation (eq. 8) D*_w = D_w/max D_w, D*_i = D_i/max D_i, D*_f = D_f/max D_f S
Relative flow volume (eq. 10) V*_f(c) = vol{D_f < c}/vol(Omega), evaluated at each node's own D_f Discretisation (nodal lumped vs element volume, ties) is A
Gradients (eq. 11) Normalised gradient direction grad/norm of V*_f, D*_i, D*_w How nodal gradients are formed on tets is A
Spatial moment (eqs. 6-7) S_i = sum_j (v_j/V_i) d_ij outer d_ij over cell centres j with distance to x_i < R and abs(D_i(x_j) - D_i(x_i)) < R; R = 3 h_max (longest edge in the mesh); scikit-learn BallTree S. D_i at cell centres is A; component layout is A (6 unique)
Feature tuple (eq. 12) X* = (V*_f, gradV_f, D*_i, gradD_i, D_w, D*_w, gradD_w, S); D_w enters un-normalised as well S (about 19 columns)
Target / denormalisation (eq. 17) t*_fill = t_fill V-dot / V; t_fill = (V/V-dot) t* with the applied flow rate V-dot A for us: does v4/v5 carry V-dot, and does V/V-dot equal our t_set?
Naive model (3.3.1) t*_fill = V*_f S
GBRT (3.3.3, 4) XGBoost, 100 trees, max depth 8, learning rate 0.1, MSE S. Other XGBoost parameters are library defaults, A
FNN (3.3.2, 4) 4 hidden layers x 100, ReLU, Adam lr 1e-3, batch 1024 node pairs, MSE, PyTorch Epochs / early stopping are M
Multi-output Y* = (t*_fill, t*_cool, S*_vol, A); the paper trains on all of them We reproduce fill time only. Single-output versus joint training is A for the FNN
Protocol (4.1) 5 random splits, 315 test / 314 train geometries; RRMSE per test geometry over every node; curves averaged over the 5 splits S. The RRMSE normaliser is not defined: A
Published targets Table C.5 FNN(100,4,ReLU): t_fill RRMSE median 0.0339, min 0.0130, max 0.2565. Table C.6 GBRT(100,8): median 0.0338, min 0.0082, max 0.2550. Text: 300 of 314 test geometries well below 0.1; ML only slightly better than naive (Fig. 6, naive median not tabulated) S
Code None found in the paper; fim-python is public M. Grok to search

2. Plan (tonight; CPU, plus a GPU only for the FNN if useful)

  • R0 (Grok, 30 min, read-only). Is the Zenodo 10027027 record public, how large, and what fields (V-dot or flow rate, gate)? fim-python version and tetFIM API (gate as node set or faces). Any author code (GitHub/GitLab, Greif or Meyer, "eikonal injection molding").
  • R1 (Mold, paper only, before any run). Fix the ambiguous items with one choice each, recorded:
    • V*_f measure: lumped nodal volume, strict "<", ties reported;
    • nodal gradient: volume-weighted average of P1 element gradients;
    • D_i at cell centres: mean of the vertex values;
    • S: 6 unique components;
    • RRMSE primary = RMSE / RMS(y) per geometry; also report RMSE / max(y) and RMSE / mean(y) as secondary, because the paper does not define it;
    • analytic synthetic checks from Fig. 4: on a rod V*_f is linear in D_f; on a centre-gated disk it is quadratic.
  • R2 (MeltAstra, implementation). Pinned project venv with fim-python, xgboost and scikit-learn (record the versions); feature pipeline per section 1 plus Mold's choices; synthetic tests first.
    • Data: v4 (10027027) if downloadable at a reasonable size, otherwise v5 (624 parts, flagged as a version deviation).
    • Target: t* = t_fill V-dot/V if V-dot is available, otherwise t_fill/t_set, flagged.
  • R3 (MeltAstra, run). The paper protocol: 5 random 315/314 splits (seed fixed and recorded), naive + GBRT + FNN, per-geometry RRMSE over all nodes, and min/median/max over the 5 splits. Budget: up to 40 worker CPU-h and up to 2 GPU-h tonight; per-part guards as before; failures kept.
  • Fidelity is the core criterion (TRON clarification). The reproduction is judged by how closely method and protocol match the paper. The published numbers are a diagnostic reference for deviations, not a validation gate. Landing inside the ranges below does not by itself prove a faithful reproduction, and landing outside does not refute one. The report keeps three lists separate: (1) paper facts, (2) our implementation choices for ambiguous items, (3) items that cannot be reproduced (missing or unavailable).
  • Numeric reference ranges (fixed now, before any result, diagnostic only):
    • GBRT and FNN fill-time median RRMSE (primary normaliser) in [0.028, 0.040], around the published 0.034;
    • the naive model is within about 25 % of GBRT's median (the paper's "ML only slightly better than naive");
    • the max stays in the same regime (0.2 to 0.3).
    • Anything outside these is reported as a deviation with its likely cause (data version, RRMSE normaliser, target scaling), not tuned away.
  • R4 (after R3, possibly tomorrow). The same method on our grouped 617/209 protocol and S2 query domain. Compare against R2-G24 and the S2 B0, both at the paper's per-geometry RRMSE and at our component-mean relative L2. Attribution must change one factor at a time, because R4 otherwise changes distance, features and protocol together. Step (a): naive V*_f with eikonal D_f versus naive V*_f with our tet-edge Dijkstra D_f, with the same V*_f measure, roster, query domain and metric. That isolates the distance construction. Step (b): naive versus GBRT on the eikonal features (the value of the features and the model). Step (c): R2-G24 versus the Gre24 GBRT. No step's difference is attributed to a factor it did not isolate.

3. Note on a result that matters

Gre24 reports that its learned models are only slightly better than the naive V_f model* on fill time. In our S2, R2 (7.30 %) is well ahead of our Dijkstra B0 (10.40 %). If the faithful eikonal naive model closes most of that gap, then our B0 was mostly a weak distance construction, and the remaining public fill-time problem is smaller than S2 suggested.