SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.17616 · 2024

Pretraining a Neural Operator in Lower Dimensions

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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; 0 honoured the contract we drafted, 1 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/2407.17616.json · badge: /api/ran/2407.17616.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
baratilab/prelowd canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
exact_2d_adv_solver Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
baratilab/prelowd/gen_new_data.py
code served (permissive licence) · get_code("ebdd54d1511661ad")
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 3, dtype family float, shape (3, 5, 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 numpy as np
from scipy.interpolate import RegularGridInterpolator

# Create small domain for 2D advection
x = np.linspace(0, 1, 5, dtype=np.float32)  # 5 points
y = np.linspace(0, 1, 4, dtype=np.float32)  # 4 points
t = np.array([0.0, 0.1, 0.2], dtype=np.float32)  # 3 time steps

# Create initial condition u0 on the 2D grid (5x4)
X, Y = np.meshgrid(x, y, indexing='ij')
u0 = np.sin(2 * np.pi * X) * np.cos(2 * np.pi * Y)
u0 = u0.astype(np.float32)

# Advection speed
beta = 0.5

ARGS = {
    'x': x,
    'y': y,
    't': t,
    'u0': u0,
    'beta': beta
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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 float, shape (3, 5, 4) — shape (3, 5, 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
get_data_config_functions Ran
ran; our contract draft was wrong, not the code
baratilab/prelowd/Train_FFNO.py
code served (permissive licence) · get_code("4a48dc57f27f91ca")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

class SimpleArgs:
    def __init__(self):
        self.val_size = 0.2
        self.val_mode = "random"
        self.val_seed = 42
        self.frac_train_data = 0.8
        self.seed = 123

class SimpleDataset:
    def __init__(self):
        self.data = torch.randn(10, 4)
        self.labels = torch.randint(0, 2, (10,))
    
    def config(self, subset, where, reverse, seed, frac, frac_seed):
        pass

ARGS = {
    "args": SimpleArgs(),
    "val_separate": True
}
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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
is_result_or_seed_col Ran
ran, violated the contract we drafted
baratilab/prelowd/Train_FFNO.py
code served (permissive licence) · get_code("b71db3ba53a5c3bc")
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 bool, 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.

def is_result_or_seed_col(col_name):
    """
    used to exclude columns in the results dataframe when grouping
    and indexing the columns based on the parameters of the experiment

    Any columns that are not results or seeds should be ignored when
    dealing with actual experiment parameters
    """
    col = col_name.lower()
    return 'loss' in col or 'time' in col or 'seed' in col


# Test cases for the function
ARGS = {
    'col_name': 'validation_loss'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 bool, 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

There has recently been increasing attention towards developing foundational neural Partial Differential Equation (PDE) solvers and neural operators through large-scale pretraining. However, unlike vision and language models that make use of abundant and inexpensive (unlabeled) data for pretraining, these neural solvers usually rely on simulated PDE data, which can be costly to obtain, especially for high-dimensional PDEs. In this work, we aim to Pretrain neural PDE solvers on Lower Dimensional PDEs (PreLowD) where data collection is the least expensive. We evaluated the effectiveness of this pretraining strategy in similar PDEs in higher dimensions. We use the Factorized Fourier Neural Operator (FFNO) due to having the necessary flexibility to be applied to PDE data of arbitrary spatial dimensions and reuse trained parameters in lower dimensions. In addition, our work sheds light on the effect of the fine-tuning configuration to make the most of this pretraining strategy. Code is available at https://github.com/BaratiLab/PreLowD.

For agents

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

get_harvested_code_for_paper("2407.17616")
get_code_for_paper("2407.17616")
have("2407.17616")

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

curl https://syntology.ai/api/ran/2407.17616.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.17616.svg)](https://syntology.ai/paper/2407.17616)

Connect an agent — have() is free.