SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.03990 · 2020

The general theory of permutation equivarant neural networks and higher order graph variational encoders

arXiv · PDF · Open in the Atlas

Code that ran

8 of 17 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; 1 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 0 failures of our instrument; 9 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/2004.03990.json · badge: /api/ran/2004.03990.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
HyTruongSon/InvariantGraphNetworks-Pytorch community (classifier label)
classifier basis not recorded on the link
8 ran · 9 no recorded run
FunctionStatusWhere it lives
contractions_1_to_2 Ran
ran on a synthesized input
HyTruongSon/InvariantGraphNetworks-Pytorch/layers/equivariant_linear_pytorch.py
code served (permissive licence) · get_code("4113e73b8e651245")
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. 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

torch.manual_seed(0)

# Create a small input tensor
# Shape: (batch=2, features=4, dim=3)
# The function sums over dim=2, so we need at least 3 dimensions
inputs = torch.randn(2, 4, 3)

# The dim parameter is used for concatenation repetitions
dim = 5

# normalization is a string parameter
normalization = 'inf'

# normalization_val is a float parameter
normalization_val = 1.0

ARGS = {
    'inputs': inputs,
    'dim': dim,
    'normalization': normalization,
    'normalization_val': normalization_val
}
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 list — a list 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
contractions_2_to_1 Ran
ran on a synthesized input
HyTruongSon/InvariantGraphNetworks-Pytorch/layers/equivariant_linear_pytorch.py
code served (permissive licence) · get_code("41b894391f32ef3f")
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. 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

torch.manual_seed(0)

# Create a 4D input tensor with shape (batch=2, channel=3, height=4, width=5)
# The function expects inputs to have dims 2 and 3 for diagonal operations
inputs = torch.randn(2, 3, 4, 5)

# dim parameter - used to control repetition in concatenations
dim = 4

# normalization parameter - can be 'inf' or None
normalization = 'inf'

# normalization_val parameter - scaling factor (not used in function body but defined)
normalization_val = 1.0

ARGS = {
    'inputs': inputs,
    'dim': dim,
    'normalization': normalization,
    'normalization_val': normalization_val,
}
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 list — a list 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
contractions_2_to_2 Ran
ran on a synthesized input
HyTruongSon/InvariantGraphNetworks-Pytorch/layers/equivariant_linear_pytorch.py
code served (permissive licence) · get_code("99dea333f1ce36a4")
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. 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

torch.manual_seed(0)

# Analyze the function to determine required tensor shape
# inputs is used with:
# - torch.diagonal(inputs, dim1=2, dim2=3) -> needs at least 4 dims
# - torch.sum(inputs, dim=3) -> needs at least 4 dims
# - torch.sum(inputs, dim=2) -> needs at least 4 dims
# The function expects inputs to be 4D tensor

# Create a small 4D tensor: (batch, channels, height, width) = (2, 3, 4, 5)
inputs = torch.randn(2, 3, 4, 5)

# dim parameter is used in loops: for d in range(dim)
# So dim should be a small positive integer
dim = 3

# normalization parameter is checked as string 'inf' or None
normalization = 'inf'

# normalization_val is provided but not used in the function body
normalization_val = 1.0

ARGS = {
    'inputs': inputs,
    'dim': dim,
    'normalization': normalization,
    'normalization_val': normalization_val
}
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 list — a list 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
create_dirs Ran
ran, honoured the contract we drafted
HyTruongSon/InvariantGraphNetworks-Pytorch/utils/dirs.py
code served (permissive licence) · get_code("dbb32e482cdfa29f")
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 int, ndim 0, dtype family int, 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 os
import tempfile
import shutil

# Create temporary directories for testing
temp_base = tempfile.mkdtemp()
test_dirs = [
    os.path.join(temp_base, 'dir1'),
    os.path.join(temp_base, 'dir2'),
    os.path.join(temp_base, 'nested', 'dir3')
]

ARGS = {
    'dirs': test_dirs
}
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 int, ndim 0, dtype family int, 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
create_experiment_results_plot Ran
ran on a synthesized input
HyTruongSon/InvariantGraphNetworks-Pytorch/utils/doc_utils.py
code served (permissive licence) · get_code("3f8d0c8cb6a5095a")
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 str. 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 os
import pandas as pd
import matplotlib.pyplot as plt

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

# Create a sample exp_summary.csv file with the required columns
data = {
    'epoch': [1, 2, 3, 4, 5],
    'train_loss': [0.5, 0.4, 0.3, 0.2, 0.15],
    'test_loss': [0.55, 0.45, 0.35, 0.25, 0.2],
    'train_accuracy': [0.6, 0.7, 0.8, 0.85, 0.9],
    'test_accuracy': [0.55, 0.65, 0.75, 0.8, 0.85]
}

df = pd.DataFrame(data)
csv_path = os.path.join(temp_dir, 'exp_summary.csv')
df.to_csv(csv_path, index=False)

ARGS = {
    'title': 'Training Results',
    'parameter': 'loss',
    'dir': temp_dir,
    'log': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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_config_from_json Ran
ran on a synthesized input
HyTruongSon/InvariantGraphNetworks-Pytorch/utils/config.py
code served (permissive licence) · get_code("bbc60ae90dd59aa6")
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 EasyDict. 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 json
import tempfile
import os
from easydict import EasyDict

# Create a temporary JSON file with valid config data
temp_dir = tempfile.mkdtemp()
json_file_path = os.path.join(temp_dir, "config.json")

config_data = {
    "model_name": "test_model",
    "learning_rate": 0.001,
    "batch_size": 32,
    "epochs": 10,
    "optimizer": "adam",
    "layers": [64, 128, 256],
    "dropout": 0.5
}

with open(json_file_path, 'w') as f:
    json.dump(config_data, f)

ARGS = {
    "json_file": json_file_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
easydict — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EasyDict — a EasyDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a EasyDict 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_folders_list Ran
ran on a synthesized input
HyTruongSon/InvariantGraphNetworks-Pytorch/utils/doc_utils.py
code served (permissive licence) · get_code("cafbbd753bd6b8ef")
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 os
import tempfile
import shutil

# Create a temporary directory structure for testing
temp_dir = tempfile.mkdtemp()
os.makedirs(os.path.join(temp_dir, "subdir1"), exist_ok=True)
os.makedirs(os.path.join(temp_dir, "subdir2"), exist_ok=True)
os.makedirs(os.path.join(temp_dir, "subdir3", "nested"), exist_ok=True)

ARGS = {
    "directory": temp_dir
}
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 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
process_config Ran
ran on a synthesized input
HyTruongSon/InvariantGraphNetworks-Pytorch/utils/config.py
code served (permissive licence) · get_code("cc544ec1bdf41536")
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 EasyDict. 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 json
import tempfile
import os
from easydict import EasyDict

# Create a temporary JSON config file
temp_config = {
    "dataset_name": "MUTAG",
    "exp_name": "10fold_cross_validation",
    "gpu": "0"
}

# Write to a temporary file
with tempfile.NamedTemporaryFile(mode='w', suffix='.json', delete=False) as f:
    json.dump(temp_config, f)
    temp_json_path = f.name

try:
    ARGS = {
        "json_file": temp_json_path
    }
finally:
    # Clean up will happen after function execution
    pass
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
easydict — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EasyDict — a EasyDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a EasyDict 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
diag_offdiag_maxpool Not yet run
unverified (harvested, no recorded run)
HyTruongSon/InvariantGraphNetworks-Pytorch/layers/layers_tensorflow.py
code served (permissive licence) · get_code("b637b741fdd6538e")
How it ran

no invocation recorded.

equi_1_to_2 Not yet run
unverified (harvested, no recorded run)
HyTruongSon/InvariantGraphNetworks-Pytorch/layers/equivariant_linear_tensorflow.py
code served (permissive licence) · get_code("c089ca28caf1a6a0")
How it ran

no invocation recorded.

equi_2_to_1 Not yet run
unverified (harvested, no recorded run)
HyTruongSon/InvariantGraphNetworks-Pytorch/layers/equivariant_linear_tensorflow.py
code served (permissive licence) · get_code("4e2c13b0790eec98")
How it ran

no invocation recorded.

equi_2_to_2 Not yet run
unverified (harvested, no recorded run)
HyTruongSon/InvariantGraphNetworks-Pytorch/layers/equivariant_linear_tensorflow.py
code served (permissive licence) · get_code("4cd16870808e812e")
How it ran

no invocation recorded.

get_parameter_split Not yet run
unverified (harvested, no recorded run)
HyTruongSon/InvariantGraphNetworks-Pytorch/data_loader/data_helper.py
code served (permissive licence) · get_code("1374773c3779cad4")
How it ran

no invocation recorded.

get_train_val_indexes Not yet run
unverified (harvested, no recorded run)
HyTruongSon/InvariantGraphNetworks-Pytorch/data_loader/data_helper.py
code served (permissive licence) · get_code("b1c9223c4b465f96")
How it ran

no invocation recorded.

load_dataset Not yet run
unverified (harvested, no recorded run)
HyTruongSon/InvariantGraphNetworks-Pytorch/data_loader/data_helper.py
code served (permissive licence) · get_code("55e50ba79f0412ba")
How it ran

no invocation recorded.

spatial_dropout Not yet run
unverified (harvested, no recorded run)
HyTruongSon/InvariantGraphNetworks-Pytorch/layers/layers_tensorflow.py
code served (permissive licence) · get_code("362c182fd87c2f6d")
How it ran

no invocation recorded.

spatial_dropout_imp Not yet run
unverified (harvested, no recorded run)
HyTruongSon/InvariantGraphNetworks-Pytorch/layers/layers_tensorflow.py
code served (permissive licence) · get_code("2e78228460e2c02f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 1 later) and 15 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
create_dirs 3 other papers
2 dated earlier, 1 later
1905.11136 (2019-05)
Provably Powerful Graph Networks
1907.10915 (2019-07)
Self-supervised Domain Adaptation for Computer Vision Tasks
2410.11181 (2024-10)
DARNet: Dual Attention Refinement Network with Spatiotemporal Construction for Auditory Attention Detection
get_config_from_json 1 other paper
1 dated earlier
1905.11136 (2019-05)
Provably Powerful Graph Networks

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

Previous work on symmetric group equivariant neural networks generally only considered the case where the group acts by permuting the elements of a single vector. In this paper we derive formulae for general permutation equivariant layers, including the case where the layer acts on matrices by permuting their rows and columns simultaneously. This case arises naturally in graph learning and relation learning applications. As a specific case of higher order permutation equivariant networks, we present a second order graph variational encoder, and show that the latent distribution of equivariant generative models must be exchangeable. We demonstrate the efficacy of this architecture on the tasks of link prediction in citation graphs and molecular graph generation.

For agents

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

get_harvested_code_for_paper("2004.03990")
get_code_for_paper("2004.03990")
have("2004.03990")

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

curl https://syntology.ai/api/ran/2004.03990.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.03990.svg)](https://syntology.ai/paper/2004.03990)

Connect an agent — have() is free.