StructBench checkpoints: wave_propagation_1d

Blessed reference checkpoints of the StructBench benchmark wave_propagation_1d, published with code release v0.4.0 (ADR-0074 clause 8). Each folder holds what running and checking the model needs: the registered checkpoint, the resolved config.json, the normalisation statistics when the model uses them, the metrics-<split>.json of the scored splits, and a SHA256SUMS covering those files. The results registry that reads these numbers is the benchmark's landing page, docs/benchmarks/wave_propagation_1d.md.

Row Family Scheme Run commit Run date Bundle Checkpoint SHA-256 Headline
CGN cgn autoregressive 48046ea 2026-07-10 cgn-48046ea/ model-best-050000.pt 2139335fb0cb2f6cccaf9be69e69cced369deb6eda80f6970b292deeba07dc0a test_interp rollout_rel_l2_disp 0.3507

Use

Download a folder and evaluate it with the StructBench CLI, which rebuilds the simulator from the folder's own config.json (the evaluation overwrites the downloaded metrics-<split>.json; keep a copy to compare):

hf download StructBench/wave-propagation-1d --revision v0.4.0 --local-dir bundles
structbench-train --mode rollout --out bundles/<bundle> --data-root <canonical cases>

Verify a file against SHA256SUMS before trusting it. Code and benchmark definitions: https://github.com/qilinli/StructBench (Apache-2.0).

Citation

The checkpoints and the code are released together β€” cite the software (CITATION.cff in the code repository):

@software{structbench,
  author  = {Li, Qilin},
  title   = {StructBench: verification and validation benchmarks for learned surrogates of structural response},
  year    = {2026},
  version = {0.5.0},
  doi     = {10.5281/zenodo.24214777},
  url     = {https://github.com/qilinli/StructBench},
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support