SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.20399 · ICML · 2026

GeoPT: Scaling Physics Simulation via Lifted Geometric Pre-Training

Wojciech Matusik, Kaiming He, Mingsheng Long, Minghao Guo, Zhiyang Dou, Zongyi Li, Haixu Wu

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2602.20399.json · badge: /api/ran/2602.20399.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
Physics-Scaling/GeoPT community
Papers with Code archive
4 ran · 2 no recorded run
FunctionStatusWhere it lives
Physics_Attention_Irregular_Mesh Ran
ran on a synthesized input · constructed an object; no result was computed
Physics-Scaling/GeoPT/models/Transolver.py
pointer only (licence: NONE) · get_code("c6896d1b98a5054a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Physics-Scaling/GeoPT when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Physics_Attention_Structured_Mesh_1D Ran
ran on a synthesized input · constructed an object; no result was computed
Physics-Scaling/GeoPT/models/Transolver.py
pointer only (licence: NONE) · get_code("25b146f484dc585b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Physics-Scaling/GeoPT when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Physics_Attention_Structured_Mesh_2D Ran
ran on a synthesized input · constructed an object; no result was computed
Physics-Scaling/GeoPT/models/Transolver.py
pointer only (licence: NONE) · get_code("1ee504ec3894ee53")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Physics-Scaling/GeoPT when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Physics_Attention_Structured_Mesh_3D Ran
ran on a synthesized input · constructed an object; no result was computed
Physics-Scaling/GeoPT/models/Transolver.py
pointer only (licence: NONE) · get_code("06d81d06e3d24eea")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Physics-Scaling/GeoPT when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Model Not yet run
unverified (harvested, no recorded run)
Physics-Scaling/GeoPT/models/Transolver.py
pointer only (licence: NONE) · get_code("63f6720214ebbf11")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Physics-Scaling/GeoPT when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Transolver_block Not yet run
unverified (harvested, no recorded run)
Physics-Scaling/GeoPT/models/Transolver.py
pointer only (licence: NONE) · get_code("a46f2c212f928b72")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Physics-Scaling/GeoPT when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Neural simulators promise efficient surrogates for physics simulation, but scaling them is bottlenecked by the prohibitive cost of generating high-fidelity training data. Pre-training on abundant off-the-shelf geometries offers a natural alternative, yet faces a fundamental gap: supervision on static geometry alone ignores dynamics and can lead to negative transfer on physics tasks. We present GeoPT, a unified pre-trained model for general physics simulation based on lifted geometric pre-training. The core idea is to augment geometry with synthetic dynamics, enabling dynamics-aware self-supervision without physics labels. Pre-trained on over one million samples, GeoPT consistently improves industrialfidelity benchmarks spanning fluid mechanics for cars, aircraft, and ships, and solid mechanics in crash simulation, reducing labeled data requirements by 20-60% and accelerating convergence by 2×. These results show that lifting with synthetic dynamics bridges the geometry-physics gap, unlocking a scalable path for neural simulation and potentially beyond. Code is available at https://github.com/Physics-Scaling/GeoPT.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2602.20399")
get_code_for_paper("2602.20399")
have("2602.20399")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2602.20399.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2602.20399.svg)](https://syntology.ai/paper/2602.20399)

Connect an agent — have() is free.