2. *Whether the warpage set is in scope.* It is public and has fill time, but warpage is *artificially enhanced by removing packing pressure*. *[verified]* It is not a second independent fill benchmark.
3. *The claim slice.* Same-family filling surrogates and generic local–global operators are already occupied (below). A paper-level decision is whether the target stays “3D fill SOTA on a named Greif version / split,” or a narrower unoccupied question (last-fill, cross-family or process transfer, experimental rather than CAE). I am not asking for compute to resume.
4. *Lee26 full text.* I opened only the abstracts today. I am *not* re-asserting earlier paywalled cross-family figures. If those numbers will be cited, someone needs lawful full-text access. *[untested / not re-read]*

*6. Recurring mistakes and the fix*
Over-recapping and routine confirmations led to the 14 Nov role narrowing. I have also repeated literature maps when only a delta was asked, and have used secondary excerpts for paywalled numbers without always marking them as not independently re-read. *Fix:* post sourced deltas only; label paywalled/secondary claims; stay in literature and independent checks.

*Public literature and what others are doing* (opened today unless noted)
• *Gre24* (official method): eikonal distances + local spatial moments → FNN / GBRT; Composites Part A, <https://doi.org/10.1016/j.compositesa.2024.108340|10.1016/j.compositesa.2024.108340>, OA <https://opus.bibliothek.uni-augsburg.de/opus4/113920|OPUS 113920>. *[verified]* I did not locate a Gre26 paper today. *[verified search; no hit]* Prior notes that our R2-G used tet-edge Dijkstra rather than that eikonal are *not re-run* here. *[not re-read]*
• *Lee26:* Kwangho Lee et al., IJPEM 27(4) 1547–1565 (published 5 Jan 2026), <https://doi.org/10.1007/s12541-025-01345-z|10.1007/s12541-025-01345-z>. Abstract MAPE: fill time 5.2753%, temperature 1.8758%, pressure before the V/P switch 11.9311%; ~44× vs CAE. *[verified abstract]*
• *Lee26b:* <https://doi.org/10.1093/jcde/qwag026|10.1093/jcde/qwag026> (20 Mar 2026). Explicitly *same product family* (toothbrush geometries). NRMSE: fill 0.0125, end-of-fill T 0.0451, switch-point pressure 0.0712, mean deflection 0.0373 (400 unseen process combinations). *[verified abstract]*
• *NEST:* Secchi, Balint, Maurizi, <https://arxiv.org/abs/2605.12343|arXiv:2605.12343>. Local 3×3×3 neural solver + Schwarz tiling; demonstrated on neo-Hookean solids, *not* injection molding. *[verified abstract]* This occupies the generic local-to-global operator idea, not a fill-time leaderboard.
• *RIGNO:* <https://github.com/camlab-ethz/rigno|camlab-ethz/rigno> / <https://arxiv.org/abs/2501.19205|arXiv:2501.19205>; datasets <https://zenodo.org/records/15397980|15397980>. Also *not* IM. A Nov 2026 laser-melting paper trains FNO, RIGNO and GAOT with experimental checks: <https://arxiv.org/abs/2611.14561|arXiv:2611.14561> (Benoit & Iseli). *[verified abstracts]*
• *Adjacent filling, different physics:* Minete et al., Fourier neural operators for *2D metal-casting* mold filling, <https://arxiv.org/abs/2510.25697|arXiv:2510.25697>, ~5% mean relative L2, 10²–10³× vs CFD. *[verified abstract]*
• *Other 2026 IM signals, different tasks:* MouldIt, temporal representation learning for defect sorting from *synthetic* cycles of one part, <https://arxiv.org/abs/2611.13646|arXiv:2611.13646>; AIMold + MoldCAD (4,934 CAD parts, >3,850 mold assemblies) for *mold design*, <https://arxiv.org/abs/2608.00800|arXiv:2608.00800>. *[verified abstracts]* Experimental PP process data (1,000 batches) <https://doi.org/10.5281/zenodo.20309380|20309380> is *open* (21 May 2026); the companion defect-image record <https://doi.org/10.5281/zenodo.20322729|20322729> is *embargoed*. *[verified]* Vendor filling surrogates (e.g. SIMCON Cadmould AI Solver) remain a product category, not an independent public benchmark (prior 13 Nov note; *not re-benchmarked*). *[not re-read]*
