SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.17728 · 2024

Masked Autoencoders are PDE Learners

arXiv · PDF · Open in the Atlas

Code that ran

6 of 10 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; 4 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/2403.17728.json · badge: /api/ran/2403.17728.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
anthonyzhou-1/mae-pdes canonical (classifier label)
classifier basis: census
6 ran · 4 no recorded run
FunctionStatusWhere it lives
dict2tensor Ran
ran, honoured the contract we drafted
anthonyzhou-1/mae-pdes/common/utils.py
code served (permissive licence) · get_code("96bd32127678eb03")
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 Tensor, ndim 2, dtype family float, shape (4, 2) 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 dictionary with tensor values
# The function iterates over dict items and calls unsqueeze(0) on each value
# Then concatenates them and transposes/flattens
# So we need dict values to be 1D tensors (or at least tensors that can be unsqueezed)

d = {
    'a': torch.randn(4),
    'b': torch.randn(4),
}

ARGS = {
    'd': d
}
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 Tensor, ndim 2, dtype family float, shape (4, 2) — shape (4, 2) 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
fourier_shift_batched Ran
ran; our contract draft was wrong, not the code
anthonyzhou-1/mae-pdes/common/augmentation.py
code served (permissive licence) · get_code("562b9260400e95ae")
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 Tensor, ndim 3, dtype family float, shape (2, 4, 3) 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
import numpy as np

torch.manual_seed(0)

# Construct arguments for fourier_shift_batched
u = torch.randn(2, 4, 3)  # batch=2, t=4, x=3
eps = torch.randn(2, 4)   # batch=2, t=4
dim = -1
order = 0

ARGS = {
    'u': u,
    'eps': eps,
    'dim': dim,
    'order': order
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 3) 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
get_args Ran
ran; our contract draft was wrong, not the code
anthonyzhou-1/mae-pdes/common/utils.py
code served (permissive licence) · get_code("d2ae286375d30714")
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 Namespace. 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 tempfile
import json
import yaml
import os

# Create a temporary directory for test config files
temp_dir = tempfile.mkdtemp()

# Create a valid YAML config file
yaml_config_path = os.path.join(temp_dir, "config.yaml")
yaml_content = {
    'learning_rate': 0.001,
    'batch_size': 32,
    'epochs': 10,
    'model_type': 'neural_operator'
}
with open(yaml_config_path, 'w') as f:
    yaml.dump(yaml_content, f)

# Create a valid JSON config file
json_config_path = os.path.join(temp_dir, "config.json")
json_content = {
    'learning_rate': 0.0001,
    'batch_size': 16,
    'epochs': 5,
    'model_type': 'fno'
}
with open(json_config_path, 'w') as f:
    json.dump(json_content, f)

# Test with YAML config
ARGS = {
    'config': yaml_config_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Namespace — a Namespace output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Namespace 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_coeffs Ran
ran, honoured the contract we drafted
anthonyzhou-1/mae-pdes/data_gen/1D_advection.py
code served (permissive licence) · get_code("8b47079ecbaffc32")
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 ndarray, ndim 1, dtype family float, shape (5,) 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
import numpy as np
from scipy.stats import uniform

class Args:
    def __init__(self, equation, num_samples):
        self.equation = equation
        self.num_samples = num_samples

ARGS = {
    'args': Args(equation='Advection', num_samples=5)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, torch — 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 (5,) — shape (5,) 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
linear_shift Ran
ran; our contract draft was wrong, not the code
anthonyzhou-1/mae-pdes/common/augmentation.py
code served (permissive licence) · get_code("6a63bbc1fe96d843")
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 Tensor, ndim 3, dtype family float, shape (2, 3, 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 torch
import numpy as np

torch.manual_seed(0)

# Create a small input tensor with shape [batch, t, x]
# batch=2, t=3, x=4 to have distinct dimensions
u = torch.randn(2, 3, 4)

# eps: shift parameter (float)
eps = 0.3

# dim: dimension which is used for shifting (int, must be negative per assertion)
dim = -1

ARGS = {
    "u": u,
    "eps": eps,
    "dim": dim,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 3, 4) — shape (2, 3, 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
process_dict Ran
ran; our contract draft was wrong, not the code
anthonyzhou-1/mae-pdes/common/utils.py
code served (permissive licence) · get_code("55c5fc2140b8cefa")
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 dict. 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 numpy as np
from collections import OrderedDict

torch.manual_seed(0)

# Create a sample state_dict with OrderedDict
# The function partitions keys by a prefix and removes it
state_dict = OrderedDict([
    ('module.layer1.weight', torch.randn(4, 3)),
    ('module.layer1.bias', torch.randn(4)),
    ('module.layer2.weight', torch.randn(5, 4)),
    ('other.param', torch.randn(2, 2)),
])

prefix = 'module'

ARGS = {
    'state_dict': state_dict,
    'prefix': prefix,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
fourier_shift Not yet run
unverified (harvested, no recorded run)
anthonyzhou-1/mae-pdes/common/augmentation.py
code served (permissive licence) · get_code("9039ba9307537e8b")
How it ran

no invocation recorded.

fourier_shift Not yet run
unverified (harvested, no recorded run)
anthonyzhou-1/mae-pdes/common/augmentation2D.py
code served (permissive licence) · get_code("ec6beb26dca70c73")
How it ran

no invocation recorded.

fourier_shift_batched Not yet run
unverified (harvested, no recorded run)
anthonyzhou-1/mae-pdes/common/augmentation2D.py
code served (permissive licence) · get_code("d6123591d47c90f9")
How it ran

no invocation recorded.

linear_shift Not yet run
unverified (harvested, no recorded run)
anthonyzhou-1/mae-pdes/common/augmentation2D.py
code served (permissive licence) · get_code("fc07943c48faf31c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 8 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.

FunctionAlso present inEarliest-datedOthers named
process_dict 1 other paper
1 later
2406.08473 (2024-06)
Strategies for Pretraining Neural Operators

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 solvers for partial differential equations (PDEs) have great potential to generate fast and accurate physics solutions, yet their practicality is currently limited by their generalizability. PDEs evolve over broad scales and exhibit diverse behaviors; predicting these phenomena will require learning representations across a wide variety of inputs which may encompass different coefficients, boundary conditions, resolutions, or even equations. As a step towards generalizable PDE modeling, we adapt masked pretraining for physics problems. Through self-supervised learning across PDEs, masked autoencoders can consolidate heterogeneous physics to learn rich latent representations. We show that learned representations can generalize to a limited set of unseen equations or parameters and are meaningful enough to regress PDE coefficients or the classify PDE features. Furthermore, conditioning neural solvers on learned latent representations can improve time-stepping and super-resolution performance across a variety of coefficients, discretizations, or boundary conditions, as well as on certain unseen PDEs. We hope that masked pretraining can emerge as a unifying method across large, unlabeled, and heterogeneous datasets to learn latent physics at scale.

For agents

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

get_harvested_code_for_paper("2403.17728")
get_code_for_paper("2403.17728")
have("2403.17728")

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

curl https://syntology.ai/api/ran/2403.17728.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.17728.svg)](https://syntology.ai/paper/2403.17728)

Connect an agent — have() is free.