SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.07643 · ICML · 2022

Lie Point Symmetry Data Augmentation for Neural PDE Solvers

Max Welling, Johannes Brandstetter, Daniel Worrall

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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, 2 violated it and 1 has 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/2202.07643.json · badge: /api/ran/2202.07643.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
brandstetter-johannes/LPSDA canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
brandstetter-johannes/lpsda marked official in Papers with Code
Papers with Code archive
3 ran · 0 no recorded run
FunctionStatusWhere it lives
Subalgebra Ran
ran on a synthesized input · constructed an object; no result was computed
brandstetter-johannes/lpsda/common/augmentation.py
code served (permissive licence) · get_code("fc3e2cc1f2a5c56f")
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, Subalgebra: 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 numpy as np

torch.manual_seed(0)

# Create small heat equation solution tensors
# Shape: [spatial_points, batch, time_steps]
batch_size = 2
spatial_points = 4
time_steps = 3

# psi1: solution to heat equation
psi1 = torch.randn(spatial_points, batch_size, time_steps, dtype=torch.float32)

# X: spatial coordinate grid
# Shape: [spatial_points, batch, 2] where last dim is [x_coord, x_coord]
X = torch.zeros(spatial_points, batch_size, 2, dtype=torch.float32)
for i in range(spatial_points):
    X[i, :, 0] = i * 0.25  # x coordinates
    X[i, :, 1] = i * 0.25  # x coordinates (repeated for consistency)

heat_sample1 = (psi1, X)

# Create second heat sample for testing
psi2 = torch.randn(spatial_points, batch_size, time_steps, dtype=torch.float32)
heat_sample2 = (psi2, X)

# Parameters for Subalgebra
nu = 0.1  # diffusion coefficient
alpha = 0.5  # convex interpolation coefficient

ARGS = {
    "nu": nu,
    "alpha": alpha,
}
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 Subalgebra — 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 Subalgebra 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 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
brandstetter-johannes/lpsda/common/augmentation.py
code served (permissive licence) · get_code("a8116d784d2fe070")
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 test tensor with shape [batch=2, t=3, x=4]
# This matches the expected shape [batch, t, x] mentioned in the docstring
u = torch.randn(2, 3, 4, dtype=torch.float32)

# eps: shift parameter (float)
eps = 0.1

# dim: dimension for shifting (int, must be negative per assert)
dim = -1

# order: derivative order (int)
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, 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
heat_to_burgers Ran
ran, violated the contract we drafted
brandstetter-johannes/lpsda/common/augmentation.py
code served (permissive licence) · get_code("e51676f5d6db9974")
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 for heat equation trajectory
# Shape: [batch, time, spatial] = [2, 3, 4]
psi = torch.randn(2, 3, 4, dtype=torch.float32)

# Ensure psi is not all zeros/constant to avoid division issues
psi = psi + 0.5

# Define parameters
nu = 0.1  # diffusion coefficient
L = 1.0   # length of spatial domain

ARGS = {
    "psi": psi,
    "nu": nu,
    "L": L
}
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
initial_conditions Ran
ran; our contract draft was wrong, not the code
brandstetter-johannes/LPSDA/generate/generate_data.py
code served (permissive licence) · get_code("6f3679c95a69e758")
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 function. 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

# Create small test arrays for the parameters
A = np.array([1.0, 0.5, 0.3])  # amplitude of 3 sine waves
phi = np.array([0.0, np.pi/4, np.pi/2])  # phase shifts for 3 sine waves
l = np.array([1, 2, 3])  # frequencies for 3 sine waves
L = 10.0  # length of spatial domain

ARGS = {
    "A": A,
    "phi": phi,
    "l": l,
    "L": L
}
Setup block drafted by
a language model, Claude Haiku 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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
inv_cole_hopf Ran
ran, violated the contract we drafted
brandstetter-johannes/LPSDA/generate/generate_data.py
code served (permissive licence) · get_code("bf15b8379a0e75b5")
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 ndarray, ndim 1, dtype family float, shape (6,) 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

# Create a small numpy array for psi0
# The function expects an ndarray and performs operations like:
# - np.amin(psi0)
# - np.amax(psi0)
# - arithmetic operations
# So we need a simple array with some variation

psi0 = np.array([1.0, 2.5, 3.2, 1.8, 4.1, 2.3])

scale = 10.0

ARGS = {
    "psi0": psi0,
    "scale": scale,
}
Setup block drafted by
a language model, Claude Haiku 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 (6,) — shape (6,) 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 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 5 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 networks are increasingly being used to solve partial differential equations (PDEs), replacing slower numerical solvers. However, a critical issue is that neural PDE solvers require highquality ground truth data, which usually must come from the very solvers they are designed to replace. Thus, we are presented with a proverbial chicken-and-egg problem. In this paper, we present a method, which can partially alleviate this problem, by improving neural PDE solver sample complexity-Lie point symmetry data augmentation (LPSDA). In the context of PDEs, it turns out that we are able to quantitatively derive an exhaustive list of data transformations, based on the Lie point symmetry group of the PDEs in question, something not possible in other application areas. We present this framework and demonstrate how it can easily be deployed to improve neural PDE solver sample complexity by an order of magnitude.

For agents

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

get_harvested_code_for_paper("2202.07643")
get_code_for_paper("2202.07643")
have("2202.07643")

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

curl https://syntology.ai/api/ran/2202.07643.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.07643.svg)](https://syntology.ai/paper/2202.07643)

Connect an agent — have() is free.