SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.00382 · NeurIPS · 2024

Towards Universal Mesh Movement Networks

Mingrui Zhang, Chen, Matthew Piggott, Jiancheng Liu, Chunyang Wang, Stephan Kramer, Joseph Wallwork, Siyi Li

arXiv · PDF · Open in the Atlas

Code that ran

3 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 2 failures of our instrument; 4 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/2407.00382.json · badge: /api/ran/2407.00382.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
mesh-adaptation/um2n canonical (classifier label)
classifier basis: classifier_2025
3 ran · 4 no recorded run
FunctionStatusWhere it lives
GlobalFeatExtractor Ran
ran on a synthesized input · constructed an object; no result was computed
mesh-adaptation/um2n/UM2N/model/M2N.py
code served (permissive licence) · get_code("52b419a6d667246e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, GlobalFeatExtractor: the run constructed the object and did not call it, so no result was computed. 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 torch
import torch.nn as nn

torch.manual_seed(0)

# The GlobalFeatExtractor.__init__ takes these parameters:
# - in_c (int): Number of input channels
# - out_c (int): Number of output channels
# - drop_p (float, optional): Dropout probability
# - use_drop (bool, optional): Use dropout layer or not

ARGS = {
    "in_c": 3,
    "out_c": 16,
    "drop_p": 0.2,
    "use_drop": True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type GlobalFeatExtractor — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a GlobalFeatExtractor output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
get_sample_param_of_nu_generalization_by_idx_train Ran
ran; our contract draft was wrong, not the code
mesh-adaptation/um2n/script/evaluate.py
code served (permissive licence) · get_code("76d4374c717e46d6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 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.

# Setup code for get_sample_param_of_nu_generalization_by_idx_train

ARGS = {
    'idx_in': 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — 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
weighted_mse Ran
ran; our contract draft was wrong, not the code
mesh-adaptation/um2n/script/train_model.py
code served (permissive licence) · get_code("39c97f78043b08e8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 0, dtype family float, shape () 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 torch

torch.manual_seed(0)

# Create a small stand-in data object with a .y attribute
class Data:
    def __init__(self):
        self.y = torch.randn(2, 4)

# Create arguments
out = torch.randn(2, 4)
data = Data()
weight = torch.randn(2)

ARGS = {
    "out": out,
    "data": data,
    "weight": weight
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () 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
DeformGAT Not yet run
unverified (harvested, no recorded run)
mesh-adaptation/um2n/UM2N/model/M2N.py
code served (permissive licence) · get_code("0d971f4cea200e5e")
How it ran

no invocation recorded.

LocalFeatExtractor Not yet run
unverified (harvested, no recorded run)
mesh-adaptation/um2n/UM2N/model/M2N.py
code served (permissive licence) · get_code("41f037911d073d0a")
How it ran

no invocation recorded.

M2N Not yet run
unverified (harvested, no recorded run)
mesh-adaptation/um2n/UM2N/model/M2N.py
code served (permissive licence) · get_code("188f779b4abc2944")
How it ran

no invocation recorded.

NetGATDeform Not yet run
unverified (harvested, no recorded run)
mesh-adaptation/um2n/UM2N/model/M2N.py
code served (permissive licence) · get_code("7264f9a78256f027")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 7 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

Solving complex Partial Differential Equations (PDEs) accurately and efficiently is an essential and challenging problem in all scientific and engineering disciplines. Mesh movement methods provide the capability to improve the accuracy of the numerical solution without increasing the overall mesh degree of freedom count. Conventional sophisticated mesh movement methods are extremely expensive and struggle to handle scenarios with complex boundary geometries. However, existing learning-based methods require re-training from scratch given a different PDE type or boundary geometry, which limits their applicability, and also often suffer from robustness issues in the form of inverted elements. In this paper, we introduce the Universal Mesh Movement Network (UM2N), which -once trained -can be applied in a non-intrusive, zero-shot manner to move meshes with different size distributions and structures, for solvers applicable to different PDE types and boundary geometries. UM2N consists of a Graph Transformer (GT) encoder for extracting features and a Graph Attention Network (GAT) based decoder for moving the mesh. We evaluate our method on advection and Navier-Stokes based examples, as well as a real-world tsunami simulation case. Our method out-performs existing learning-based mesh movement methods in terms of the benchmarks described above. In comparison to the conventional sophisticated Monge-Ampère PDE-solver based method, our approach not only significantly accelerates mesh movement, but also proves effective in scenarios where the conventional method fails. Our project page can be found at https://erizmr.github.io/UM2N/.

For agents

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

get_harvested_code_for_paper("2407.00382")
get_code_for_paper("2407.00382")
have("2407.00382")

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

curl https://syntology.ai/api/ran/2407.00382.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.00382.svg)](https://syntology.ai/paper/2407.00382)

Connect an agent — have() is free.