Topics — The twenty-eight kinds of claim this anthology files against — the primary axis of both the practice registry and the reading list, and the same twenty-eight for each (ADR-026). The filing rule is the point: take a domain topic when the claim is ABOUT the domain; a claim merely discovered in one still takes its kind. The axis organizes the record, it does not bound it: content the list cannot place is evidence the list is short (ADR-059).
Physical sciences — models whose data is the physical world — learned surrogates for simulation in fluids, PDEs, molecular dynamics and cosmology, foundation models for weather, climate and solar observation — what they are trusted to replace, what their benchmarks can show, and which of their methods travel to other domains.
2 of 737 LIT documents. Back to the full index.
| # | Title | Summary | Status |
|---|---|---|---|
| LIT-715 | Surya: Foundation Model for Heliophysics | Roy et al. (2025), ARXIV-2508.14112. A 366M-parameter transformer pretrained on full-resolution (4096²) multi-instrument SDO imagery to forecast the next frame, then rollout-tuned, forecasts solar dynamics zero-shot. With LoRA fine-tuning it beats task-specific baselines on four downstream heliophysics tasks. | Deferred — seeded from the abstract and a skim on 2026-09-25; not read in full |
| LIT-763 | Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems | Zhdanov et al. (2025), ARXIV-2502.17019 — Erwin. Build a ball tree over an irregular point set so that every ball at a level holds the same number of points in contiguous memory, then run full self-attention inside each ball, coarsen and refine through the tree in a U-Net, and alternate with a tree built on a rotated copy of the cloud so balls exchange information. Runtime fits n^1.054. Best on cosmology at large training sets, on EAGLE turbulence (3× faster and 8× less memory than EAGLE’s own model), and on ShapeNet-Car; a clear failure on the Airfoil PDE mesh. | Active |