SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.10408 · 2020

PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions

arXiv · PDF · Open in the Atlas

Code that ran

2 of 7 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, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 5 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/2007.10408.json · badge: /api/ran/2007.10408.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
shenzy08/PDO-eConvs canonical (classifier label)
classifier basis: census
1 ran · 4 no recorded run
Roderickzzc/Pdo-econv-pytorch community (classifier label)
classifier basis not recorded on the link
1 ran · 1 no recorded run
FunctionStatusWhere it lives
get_coef Ran
ran on a synthesized input
shenzy08/PDO-eConvs/cifar.py
code served (permissive licence) · get_code("3153f50b8445e277")
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 EagerTensor, ndim 3, dtype family float, shape (3, 3, 9) 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 tensorflow as tf
import numpy as np

# Create a weight tensor with shape [num_inputs, num_outputs, ...]
# The function expects get_shape().as_list()[:2] to give [num_inputs, num_outputs]
# and later reshapes to [-1, 9], so total elements must be divisible by 9
num_inputs = 3
num_outputs = 3
weight = tf.constant(np.random.randn(num_inputs, num_outputs, 9).astype(np.float32))

# Create partial array
# The function indexes it as partial[[0, 1, 2, 3, 4, 5, 7, 8, 12], 1:4, 1:4]
# So we need at least 13 rows (indices 0-12), and at least 4 columns (slicing 1:4)
# Shape: [13, 4, 4] to be safe
partial = np.random.randn(13, 4, 4).astype(np.float32)

ARGS = {
    "weight": weight,
    "partial": partial,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 3, dtype family float, shape (3, 3, 9) — shape (3, 3, 9) 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_coef Ran
ran on a synthesized input
Roderickzzc/Pdo-econv-pytorch/mwpdo_layers.py
code served (permissive licence) · get_code("06968f8c3bffb773")
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, 9) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

# The function uses:
# - weight: reshaped to (-1, 9), then matrix multiplied with inv_transformation
# - num_inputs: used to reshape output to (num_inputs, num_outputs, 9)
# - num_outputs: used to reshape output to (num_inputs, num_outputs, 9)

# The weight tensor needs to be reshapeable to (-1, 9)
# If num_inputs=2 and num_outputs=3, then weight should have 2*3*9 = 54 elements
weight = torch.randn(2, 3, 9)

num_inputs = 2
num_outputs = 3

ARGS = {
    "weight": weight,
    "num_inputs": num_inputs,
    "num_outputs": num_outputs,
}
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 3, dtype family float, shape (2, 3, 9) — shape (2, 3, 9) 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
open_conv2d Not yet run
unverified (harvested, no recorded run)
shenzy08/PDO-eConvs/cifar.py
code served (permissive licence) · get_code("b9b3b78f58c55579")
How it ran

no invocation recorded.

open_conv2d Not yet run
unverified (harvested, no recorded run)
shenzy08/PDO-eConvs/mnist.py
code served (permissive licence) · get_code("dd086cf5b7056f44")
How it ran

no invocation recorded.

subsample Not yet run
unverified (harvested, no recorded run)
shenzy08/PDO-eConvs/cifar.py
code served (permissive licence) · get_code("ea673d7294c57b2c")
How it ran

no invocation recorded.

z2_kernel Not yet run
unverified (harvested, no recorded run)
shenzy08/PDO-eConvs/mnist.py
code served (permissive licence) · get_code("df1d3f2c0fe8b762")
How it ran

no invocation recorded.

z2_kernel Not yet run
unverified (harvested, no recorded run)
Roderickzzc/Pdo-econv-pytorch/mwpdo_layers.py
code served (permissive licence) · get_code("1885497fb2dacd6c")
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

Recent research has shown that incorporating equivariance into neural network architectures is very helpful, and there have been some works investigating the equivariance of networks under group actions. However, as digital images and feature maps are on the discrete meshgrid, corresponding equivariance-preserving transformation groups are very limited. In this work, we deal with this issue from the connection between convolutions and partial differential operators (PDOs). In theory, assuming inputs to be smooth, we transform PDOs and propose a system which is equivariant to a much more general continuous group, the $n$-dimension Euclidean group. In implementation, we discretize the system using the numerical schemes of PDOs, deriving approximately equivariant convolutions (PDO-eConvs). Theoretically, the approximation error of PDO-eConvs is of the quadratic order. It is the first time that the error analysis is provided when the equivariance is approximate. Extensive experiments on rotated MNIST and natural image classification show that PDO-eConvs perform competitively yet use parameters much more efficiently. Particularly, compared with Wide ResNets, our methods result in better results using only 12.6% parameters.

For agents

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

get_harvested_code_for_paper("2007.10408")
get_code_for_paper("2007.10408")
have("2007.10408")

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

curl https://syntology.ai/api/ran/2007.10408.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.10408.svg)](https://syntology.ai/paper/2007.10408)

Connect an agent — have() is free.