SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.09844 · 2021

E(n) Equivariant Graph Neural Networks

Max Welling, Emiel Hoogeboom, Victor Satorras

arXiv · PDF · Open in the Atlas

Code that ran

15 of 15 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (7 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 8 have no contract verdict; 6 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/2102.09844.json · badge: /api/ran/2102.09844.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
stdereka/egnn community
Papers with Code archive
6 ran · 0 no recorded run
lucidrains/egnn-pytorch community
Papers with Code archive
5 ran · 0 no recorded run
oumarkaba/channels_egnn community
Papers with Code archive
3 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
CoorsNorm Ran
ran on a synthesized input · constructed an object; no result was computed
lucidrains/egnn-pytorch/egnn_pytorch/egnn_pytorch.py
code served (permissive licence) · get_code("ffaef7e169a747f9")
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, CoorsNorm: 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
from torch import nn

torch.manual_seed(0)

class CoorsNorm(nn.Module):

    def __init__(self, eps=1e-08, scale_init=1.0):
        super().__init__()
        self.eps = eps
        scale = torch.zeros(1).fill_(scale_init)
        self.scale = nn.Parameter(scale)

    def forward(self, coors):
        norm = coors.norm(dim=-1, keepdim=True)
        normed_coors = coors / norm.clamp(min=self.eps)
        return normed_coors * self.scale

# Create small input tensor: batch_size=2, feature_dim=4
coors = torch.randn(2, 4)

ARGS = {
    'eps': 1e-08,
    'scale_init': 1.0
}
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 CoorsNorm — 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 CoorsNorm 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
EGNN Ran
ran on a synthesized input · constructed an object; no result was computed
oumarkaba/channels_egnn/models/egnn_clean/egnn_clean.py
code served (permissive licence) · get_code("13bfce0047d020a5")
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, EGNN: the run constructed the object and did not call it, so no result was computed. 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 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
from torch import nn

torch.manual_seed(0)

ARGS = {
    'in_node_nf': 4,
    'hidden_nf': 8,
    'out_node_nf': 4,
    'in_edge_nf': 3,
    'device': 'cpu',
    'act_fn': nn.SiLU(),
    'n_layers': 2,
    'residual': True,
    'attention': False,
    'normalize': False,
    'tanh': False
}
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 EGNN — 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 EGNN 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
EGNN Ran
ran on a synthesized input · constructed an object; no result was computed
lucidrains/egnn-pytorch/egnn_pytorch/egnn_pytorch.py
code served (permissive licence) · get_code("417dea916987b70b")
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, EGNN: 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 torch.nn as nn
from torch import einsum, broadcast_tensors
from einops import rearrange, repeat

torch.manual_seed(0)

# Define ARGS dictionary with all EGNN parameters
ARGS = {
    'dim': 4,
    'edge_dim': 2,
    'm_dim': 8,
    'fourier_features': 2,
    'num_nearest_neighbors': 0,
    'dropout': 0.1,
    'init_eps': 0.001,
    'norm_feats': False,
    'norm_coors': False,
    'norm_coors_scale_init': 0.01,
    'update_feats': True,
    'update_coors': True,
    'only_sparse_neighbors': False,
    'valid_radius': float('inf'),
    'm_pool_method': 'sum',
    'soft_edges': False,
    'coor_weights_clamp_value': None,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EGNN — 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 EGNN 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
E_GCL Ran
ran on a synthesized input · constructed an object; no result was computed
oumarkaba/channels_egnn/models/egnn_clean/egnn_clean.py
code served (permissive licence) · get_code("1e061bf006a92838")
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, E_GCL: 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 torch.nn as nn

torch.manual_seed(0)

# Define ARGS dictionary with all parameters for E_GCL
ARGS = {
    'input_nf': 4,
    'output_nf': 3,
    'hidden_nf': 8,
    'edges_in_d': 2,
    'act_fn': nn.SiLU(),
    'residual': True,
    'attention': False,
    'normalize': False,
    'coords_agg': 'mean',
    'tanh': False
}
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 E_GCL — 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 E_GCL 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
EquivariantGNN Ran
ran on a synthesized input · constructed an object; no result was computed
stdereka/egnn/src/egnn/model/gnn.py
pointer only (licence: NONE) · get_code("bc84667b27c8cd1c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, stdereka/egnn when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

EquivariantGraphConvolution Ran
ran on a synthesized input · constructed an object; no result was computed
stdereka/egnn/src/egnn/model/gnn.py
pointer only (licence: NONE) · get_code("1c02f9fc1ecdc6a7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, stdereka/egnn when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ResidualMLP Ran
ran on a synthesized input · constructed an object; no result was computed
stdereka/egnn/src/egnn/model/gnn.py
pointer only (licence: NONE) · get_code("70eef633a4bb2e21")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, stdereka/egnn when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Swish_ Ran
ran on a synthesized input
lucidrains/egnn-pytorch/egnn_pytorch/egnn_pytorch.py
code served (permissive licence) · get_code("bfa2a8ec7cf892d8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 2, 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
from torch import nn

# Swish_ has no __init__ parameters (inherits from nn.Module with no custom __init__)
INIT_ARGS = {}

# forward method takes x as input
ARGS = {
    'x': torch.randn(2, 4)
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 2, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
fourier_encode_dist Ran
ran; our contract draft was wrong, not the code
lucidrains/egnn-pytorch/egnn_pytorch/egnn_pytorch.py
code served (permissive licence) · get_code("970eaf2b4e05bf0b")
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, 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 torch

torch.manual_seed(0)

# Create a small tensor with shape (2, 4) - batch_size=2, feature_dim=4
x = torch.randn(2, 4)

# Define arguments for fourier_encode_dist
ARGS = {
    "x": x,
    "num_encodings": 4,
    "include_self": True,
}
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, 4, 9) — shape (2, 4, 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
pack_node_params Ran
ran, honoured the contract we drafted
stdereka/egnn/src/egnn/model/gnn.py
pointer only (licence: NONE) · get_code("63fe5b745690a4c5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, stdereka/egnn when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

safe_div Ran
ran; our contract draft was wrong, not the code
lucidrains/egnn-pytorch/egnn_pytorch/egnn_pytorch.py
code served (permissive licence) · get_code("d92b80051870e976")
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 (2, 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 torch.nn as nn

torch.manual_seed(0)

# Construct arguments for safe_div(num, den, eps=1e-08)
# The function calls:
# - num.div(den.clamp(min=eps))
# - den == 0
# - res.masked_fill_(den == 0, 0.0)
# So num and den must be torch tensors

num = torch.randn(2, 4)
den = torch.randn(2, 4)

ARGS = {
    "num": num,
    "den": den,
    "eps": 1e-08
}
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 (2, 4) — shape (2, 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
unpack_node_params Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
stdereka/egnn/src/egnn/model/gnn.py
pointer only (licence: NONE) · get_code("f94b0bdff7e41ab4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, stdereka/egnn when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

unsorted_segment_mean Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
oumarkaba/channels_egnn/models/egnn_clean/egnn_clean.py
code served (permissive licence) · get_code("bc66f19be57720e7")
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 (2, 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

torch.manual_seed(0)

# Create sample data tensor with shape (batch_size, feature_dim)
# Using distinct sizes: 2 for batch, 4 for features
data = torch.randn(2, 4)

# Create segment_ids tensor that maps each data point to a segment
# Values should be in range [0, num_segments)
segment_ids = torch.tensor([0, 1])

# Number of segments to aggregate into
num_segments = 2

ARGS = {
    "data": data,
    "segment_ids": segment_ids,
    "num_segments": num_segments,
}
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 (2, 4) — shape (2, 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
unsorted_segment_sum Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from ZhangGroup-MITChemistry/Schake_GNN
pointer only; the stored copy get_code serves, from ZhangGroup-MITChemistry/Schake_GNN, is pointer only (licence: NONE) · get_code("5fb62a78eb65d3d7")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

unsorted_segment_sum Ran
ran; our contract draft was wrong, not the code
stdereka/egnn/src/egnn/model/gnn.py
pointer only (licence: NONE) · get_code("90bd74d59afb1975")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, stdereka/egnn when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 4 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 4 later) and 11 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
unsorted_segment_mean
brick of this paper's assembly: helper
20 other papers
1 dated earlier, 19 later · 1 only as an assembly brick
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
2110.14811 (2021-10)
SE(3) Equivariant Graph Neural Networks with Complete Local Frames
2202.10643 (2022-02)
Equivariant Graph Hierarchy-Based Neural Networks
and 17 more not named here
unsorted_segment_sum
brick of this paper's assembly: helper
19 other papers
2 dated earlier, 17 later · 2 only as an assembly brick
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1906.02547 (2019-06)
Combining Generative and Discriminative Models for Hybrid Inference
2110.14811 (2021-10)
SE(3) Equivariant Graph Neural Networks with Complete Local Frames
and 16 more not named here
fourier_encode_dist
brick of this paper's assembly: helper
1 other paper
1 later
2506.05768 (2025-06)
AANet: Virtual Screening under Structural Uncertainty via Alignment and Aggregation
safe_div
brick of this paper's assembly: helper
1 other paper
1 later
2306.16819 (2023-06)
Graph Denoising Diffusion for Inverse Protein Folding

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

This paper introduces a new model to learn graph neural networks equivariant to rotations, translations, reflections and permutations called E(n)-Equivariant Graph Neural Networks (EGNNs). In contrast with existing methods, our work does not require computationally expensive higher-order representations in intermediate layers while it still achieves competitive or better performance. In addition, whereas existing methods are limited to equivariance on 3 dimensional spaces, our model is easily scaled to higher-dimensional spaces. We demonstrate the effectiveness of our method on dynamical systems modelling, representation learning in graph autoencoders and predicting molecular properties.

For agents

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

get_harvested_code_for_paper("2102.09844")
get_code_for_paper("2102.09844")
have("2102.09844")

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

curl https://syntology.ai/api/ran/2102.09844.json

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

[![Syntology run record](https://syntology.ai/api/ran/2102.09844.svg)](https://syntology.ai/paper/2102.09844)

Connect an agent — have() is free.