SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.03409 · 2020

Learning Mesh-Based Simulation with Graph Networks

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2010.03409.json · badge: /api/ran/2010.03409.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
echowve/meshGraphNets_pytorch reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
CCSI-Toolset/MGN reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
fig2data Ran
ran, honoured the contract we drafted
echowve/meshGraphNets_pytorch/render_results.py
code served (permissive licence) · get_code("e7e2742326c28429")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned ndarray, ndim 3, dtype family int, shape (200, 300, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import matplotlib.pyplot as plt
import matplotlib.figure

# Create a minimal matplotlib figure
fig = plt.figure(figsize=(3, 2))
ax = fig.add_subplot(111)
ax.plot([1, 2, 3], [1, 4, 2])
ax.set_title("Test Plot")

ARGS = {
    "fig": fig
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
PIL, matplotlib, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (200, 300, 4) — shape (200, 300, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
render Ran
ran; our contract draft was wrong, not the code
echowve/meshGraphNets_pytorch/render_results.py
code served (permissive licence) · get_code("1238daf814ff116d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import matplotlib.pyplot as plt
from matplotlib.tri import Triangulation

# Create a simple triangulation mesh
np.random.seed(42)
n_points = 20
x = np.random.rand(n_points)
y = np.random.rand(n_points)
crds = np.column_stack([x, y])
triang = Triangulation(x, y)

# Create time series data for target and predicted velocity fields
n_timesteps = 15
n_vertices = n_points

# result is a tuple of (predicted, target)
# Each is a time series of velocity vectors at each vertex
predicted_series = np.random.randn(n_timesteps, n_vertices, 2) * 0.5
target_series = np.random.randn(n_timesteps, n_vertices, 2) * 0.5

result = (predicted_series, target_series)

# Calculate velocity magnitudes to determine v_max and v_min
all_velocities = np.concatenate([
    np.linalg.norm(predicted_series, axis=-1).flatten(),
    np.linalg.norm(target_series, axis=-1).flatten()
])
v_max = np.max(all_velocities)
v_min = np.min(all_velocities)

# i is the frame index
i = 1

args = (i, result, crds, triang, v_max, v_min)

ARGS = {"args": args}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
PIL, matplotlib, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
rollout_error Ran
ran, honoured the contract we drafted
echowve/meshGraphNets_pytorch/rollout.py
code served (permissive licence) · get_code("6ec74c26926c8475")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned ndarray, ndim 1, dtype family float, shape (100,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

np.random.seed(0)

# Create predicteds and targets with shape (number_len, ...)
# number_len will be the first dimension
# Let's use a small number_len for testing, e.g., 100
number_len = 100
feature_dim = 12  # arbitrary feature dimension that will be flattened

predicteds = np.random.randn(number_len, feature_dim)
targets = np.random.randn(number_len, feature_dim)

ARGS = {
    'predicteds': predicteds,
    'targets': targets
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (100,) — shape (100,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
tableau_builder Ran
ran; our contract draft was wrong, not the code
CCSI-Toolset/MGN/GNN/MeshGraphNets.py
pointer only (licence: NOASSERTION) · get_code("34453417d3c1864e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, CCSI-Toolset/MGN (NOASSERTION). 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.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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

Mesh-based simulations are central to modeling complex physical systems in many disciplines across science and engineering. Mesh representations support powerful numerical integration methods and their resolution can be adapted to strike favorable trade-offs between accuracy and efficiency. However, high-dimensional scientific simulations are very expensive to run, and solvers and parameters must often be tuned individually to each system studied. Here we introduce MeshGraphNets, a framework for learning mesh-based simulations using graph neural networks. Our model can be trained to pass messages on a mesh graph and to adapt the mesh discretization during forward simulation. Our results show it can accurately predict the dynamics of a wide range of physical systems, including aerodynamics, structural mechanics, and cloth. The model's adaptivity supports learning resolution-independent dynamics and can scale to more complex state spaces at test time. Our method is also highly efficient, running 1-2 orders of magnitude faster than the simulation on which it is trained. Our approach broadens the range of problems on which neural network simulators can operate and promises to improve the efficiency of complex, scientific modeling tasks.

For agents

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

get_harvested_code_for_paper("2010.03409")
get_code_for_paper("2010.03409")
have("2010.03409")

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

curl https://syntology.ai/api/ran/2010.03409.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.03409.svg)](https://syntology.ai/paper/2010.03409)

Connect an agent — have() is free.