SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1909.12201 · 2019

Overlapping Community Detection with Graph Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

12 of 12 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 12 have no contract verdict; 0 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/1909.12201.json · badge: /api/ran/1909.12201.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
shchur/overlapping-community-detection canonical (classifier label)
classifier basis: census
12 ran · 0 no recorded run
FunctionStatusWhere it lives
clustering_coef Ran
ran on a synthesized input
shchur/overlapping-community-detection/nocd/metrics/unsupervised.py
code served (permissive licence) · get_code("63aac8f5f179202d")
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 float64, ndim 0, 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 numpy as np

# Create a small adjacency matrix (undirected, weighted)
# 4 nodes, represented as a 4x4 symmetric matrix
adj = np.array([
    [0, 1, 1, 0],
    [1, 0, 1, 1],
    [1, 1, 0, 1],
    [0, 1, 1, 0]
], dtype=float)

# Create a community assignment matrix Z_pred
# Shape: (n_nodes, n_communities) = (4, 3)
# Each row is a node, each column is a community
# Soft assignments that will be converted to boolean
Z_pred = np.array([
    [0.9, 0.1, 0.0],
    [0.8, 0.2, 0.0],
    [0.1, 0.9, 0.0],
    [0.0, 0.1, 0.9]
], dtype=float)

ARGS = {
    'Z_pred': Z_pred,
    'adj': adj
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
collate_fn Ran
ran on a synthesized input
shchur/overlapping-community-detection/nocd/sampler.py
code served (permissive licence) · get_code("320644b201489839")
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 tuple. 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)

# The function expects batch[0] to be a tuple of (edges, nonedges)
# batch is a list-like structure where we can index it with [0]
edges = torch.randn(2, 4)
nonedges = torch.randn(3, 4)

batch = [(edges, nonedges)]

ARGS = {
    "batch": batch
}
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 tuple — a tuple 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
coms_list_to_matrix Ran
ran on a synthesized input
shchur/overlapping-community-detection/nocd/utils.py
code served (permissive licence) · get_code("8ccaf8d33fe9b54c")
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 2, dtype family float, shape (5, 3) 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 communities list where we have 3 communities
# Community 0: nodes [0, 1]
# Community 1: nodes [2, 4]
# Community 2: nodes [1, 3]
communities_list = [
    [0, 1],
    [2, 4],
    [1, 3]
]

# num_nodes is explicitly set to ensure the matrix has correct shape
# even if some nodes are isolated
num_nodes = 5

ARGS = {
    "communities_list": communities_list,
    "num_nodes": num_nodes
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 2, dtype family float, shape (5, 3) — shape (5, 3) 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
coverage Ran
ran on a synthesized input
shchur/overlapping-community-detection/nocd/metrics/unsupervised.py
code served (permissive licence) · get_code("1a89f3b438368b8c")
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 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.

import torch
import scipy.sparse as sp
import numpy as np

torch.manual_seed(0)

# Create a small graph with 4 nodes
num_nodes = 4
num_communities = 2

# Z_pred: Binary community affiliation matrix (num_nodes x num_communities)
# Each row indicates which communities a node belongs to
Z_pred = torch.tensor([
    [1, 0],
    [1, 1],
    [0, 1],
    [1, 0]
], dtype=torch.float32)

# adj: Sparse adjacency matrix (unweighted, symmetric)
# Create a simple undirected graph
rows = np.array([0, 1, 1, 2, 2, 3, 3, 0])
cols = np.array([1, 0, 2, 1, 3, 2, 0, 3])
data = np.ones(len(rows))
adj = sp.csr_matrix((data, (rows, cols)), shape=(num_nodes, num_nodes))

ARGS = {
    "Z_pred": Z_pred,
    "adj": adj
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, 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
evaluate_unsupervised Ran
ran on a synthesized input
shchur/overlapping-community-detection/nocd/metrics/unsupervised.py
code served (permissive licence) · get_code("9cf1d122d1665d09")
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 dict. 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
from scipy import sparse

# Create a small graph with 5 nodes
n_nodes = 5
n_communities = 2

# Create a simple sparse adjacency matrix (symmetric, unweighted)
# Edges: 0-1, 1-2, 2-3, 3-4, 0-4 (forming a cycle-like structure)
row = np.array([0, 1, 1, 2, 2, 3, 3, 4, 0, 4])
col = np.array([1, 0, 2, 1, 3, 2, 4, 3, 4, 0])
data = np.ones(len(row))
adj = sparse.csr_matrix((data, (row, col)), shape=(n_nodes, n_nodes))

# Create a community assignment matrix (binary)
# Node assignments to communities
# Community 0: nodes 0, 1, 2
# Community 1: nodes 3, 4
Z_pred = np.array([
    [1, 0],  # node 0 -> community 0
    [1, 0],  # node 1 -> community 0
    [1, 0],  # node 2 -> community 0
    [0, 1],  # node 3 -> community 1
    [0, 1],  # node 4 -> community 1
], dtype=np.float64)

ARGS = {
    'Z_pred': Z_pred,
    'adj': adj
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
generate_bigclam Ran
ran on a synthesized input
shchur/overlapping-community-detection/nocd/generate.py
code served (permissive licence) · get_code("598df91b8ace4a02")
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 2, dtype family int, shape (5, 5) 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

# Set random seed for reproducibility
np.random.seed(0)

# Number of nodes and communities
N = 5  # number of nodes
K = 3  # number of communities

# F: community affiliation matrix [N, K]
# Nonnegative values indicating how much each node belongs to each community
F = np.array([
    [0.8, 0.2, 0.0],
    [0.0, 0.9, 0.1],
    [0.7, 0.0, 0.3],
    [0.1, 0.1, 0.8],
    [0.5, 0.5, 0.0]
], dtype=float)

# B: compatibility matrix [K, K]
# Nonnegative values indicating edge probability between communities
B = np.array([
    [1.0, 0.5, 0.2],
    [0.5, 1.0, 0.6],
    [0.2, 0.6, 1.0]
], dtype=float)

# D: degree vector [N]
# Nonnegative values for node degree scaling
D = np.array([2.0, 3.0, 1.5, 2.5, 2.0], dtype=float)

# p_no_comm: background edge probability (float between 0 and 1)
p_no_comm = 0.01

# seed: random seed for reproducibility
seed = 42

ARGS = {
    'F': F,
    'B': B,
    'D': D,
    'p_no_comm': p_no_comm,
    'seed': seed
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 2, dtype family int, shape (5, 5) — shape (5, 5) 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_edge_sampler Ran
ran on a synthesized input
shchur/overlapping-community-detection/nocd/sampler.py
code served (permissive licence) · get_code("a510f83ef3a1c71a")
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 DataLoader. 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
import torch
import torch.utils.data as data_utils
from scipy import sparse

torch.manual_seed(0)
np.random.seed(0)

# Create a small sparse adjacency matrix
# 5 nodes, some edges
rows = np.array([0, 1, 2, 3, 4, 0, 2])
cols = np.array([1, 2, 3, 4, 0, 3, 1])
data = np.ones(len(rows))
A = sparse.csr_matrix((data, (rows, cols)), shape=(5, 5))

ARGS = {
    "A": A,
    "num_pos": 10,
    "num_neg": 10,
    "num_workers": 0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataLoader — a DataLoader output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataLoader 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
l2_reg_loss Ran
ran on a synthesized input
shchur/overlapping-community-detection/nocd/utils.py
code served (permissive licence) · get_code("9cad3e633573874e")
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 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.

import torch
import torch.nn as nn

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def get_weights(self):
        """Return all weight parameters as a list of tensors."""
        weights = []
        for param in self.parameters():
            weights.append(param)
        return weights
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

ARGS = {
    "model": model,
    "scale": 1e-05
}
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 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
load_dataset Ran
ran on a synthesized input
shchur/overlapping-community-detection/nocd/data.py
code served (permissive licence) · get_code("5998125a3750334b")
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 dict. 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
import scipy.sparse as sp
import tempfile
import os

# Create a temporary npz file with the required data
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_graph.npz")

# Create small sparse matrices for adjacency, attributes, and labels
num_nodes = 5
num_attrs = 3
num_classes = 2

# Adjacency matrix (sparse)
A_data = np.array([1, 1, 1, 1], dtype=np.float32)
A_indices = np.array([1, 2, 0, 3], dtype=np.int32)
A_indptr = np.array([0, 2, 3, 3, 4, 4], dtype=np.int32)
A_shape = (num_nodes, num_nodes)

# Attribute matrix (sparse)
X_data = np.array([1, 1, 1, 1, 1], dtype=np.float32)
X_indices = np.array([0, 1, 2, 0, 1], dtype=np.int32)
X_indptr = np.array([0, 2, 3, 4, 5, 5], dtype=np.int32)
X_shape = (num_nodes, num_attrs)

# Labels matrix (sparse)
Z_data = np.array([1, 1, 1, 1], dtype=np.float32)
Z_indices = np.array([0, 1, 0, 1], dtype=np.int32)
Z_indptr = np.array([0, 1, 2, 3, 4, 4], dtype=np.int32)
Z_shape = (num_nodes, num_classes)

# Optional metadata
node_names = np.array(['node_0', 'node_1', 'node_2', 'node_3', 'node_4'], dtype=object)
attr_names = np.array(['attr_0', 'attr_1', 'attr_2'], dtype=object)
class_names = np.array(['class_0', 'class_1'], dtype=object)

# Save as npz file
np.savez(
    temp_file,
    **{
        'adj_matrix.data': A_data,
        'adj_matrix.indices': A_indices,
        'adj_matrix.indptr': A_indptr,
        'adj_matrix.shape': A_shape,
        'attr_matrix.data': X_data,
        'attr_matrix.indices': X_indices,
        'attr_matrix.indptr': X_indptr,
        'attr_matrix.shape': X_shape,
        'labels.data': Z_data,
        'labels.indices': Z_indices,
        'labels.indptr': Z_indptr,
        'labels.shape': Z_shape,
        'node_names': node_names,
        'attr_names': attr_names,
        'class_names': class_names,
    }
)

ARGS = {
    'file_name': temp_file
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
overlapping_nmi Ran
ran on a synthesized input
shchur/overlapping-community-detection/nocd/metrics/supervised.py
code served (permissive licence) · get_code("01c6ec57467bf3c9")
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 float64, ndim 0, 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 numpy as np

# Create two binary matrices for overlapping community detection
# X: shape [N, m] where N=samples, m=communities in first cover
# Y: shape [N, n] where N=samples, n=communities in second cover
# The function will transpose them internally, so we provide them as [N, m]

np.random.seed(0)

# Create small binary matrices
N = 5  # number of samples
m = 3  # number of communities in X
n = 4  # number of communities in Y

# Generate random binary matrices
X = np.random.randint(0, 2, size=(N, m)).astype(np.float64)
Y = np.random.randint(0, 2, size=(N, n)).astype(np.float64)

# Ensure at least some 0s and 1s in each matrix
X[0, 0] = 1
X[1, 1] = 0
Y[0, 0] = 1
Y[1, 1] = 0

ARGS = {
    "X": X,
    "Y": Y,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
sparse_or_dense_dropout Ran
ran on a synthesized input
shchur/overlapping-community-detection/nocd/nn/gcn.py
code served (permissive licence) · get_code("5dea505bf3016662")
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. 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
import torch.nn.functional as F

torch.manual_seed(0)

# Test case 1: dense tensor
dense_tensor = torch.randn(2, 4)

# Test case 2: sparse tensor (CPU only)
indices = torch.tensor([[0, 1], [0, 1]])
values = torch.tensor([1.0, 2.0])
size = torch.Size([2, 4])
sparse_tensor = torch.sparse_coo_tensor(indices, values, size)

ARGS = {
    "x": dense_tensor,
    "p": 0.5,
    "training": 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 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
to_sparse_tensor Ran
ran on a synthesized input
shchur/overlapping-community-detection/nocd/utils.py
code served (permissive licence) · get_code("e5d1964ba1474ffc")
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. 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 numpy as np
import scipy.sparse as sp
import torch

torch.manual_seed(0)

# Create a small scipy sparse matrix (4x3 COO format)
row = np.array([0, 1, 2, 3])
col = np.array([0, 1, 2, 0])
data = np.array([1.0, 2.0, 3.0, 4.0])
sparse_matrix = sp.coo_matrix((data, (row, col)), shape=(4, 3))

ARGS = {
    "matrix": sparse_matrix,
    "cuda": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, shape (4, 3) — shape (4, 3) as a later run recorded it
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 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 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 12 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

Community detection is a fundamental problem in machine learning. While deep learning has shown great promise in many graphrelated tasks, developing neural models for community detection has received surprisingly little attention. The few existing approaches focus on detecting disjoint communities, even though communities in real graphs are well known to be overlapping. We address this shortcoming and propose a graph neural network (GNN) based model for overlapping community detection. Despite its simplicity, our model outperforms the existing baselines by a large margin in the task of community recovery. We establish through an extensive experimental evaluation that the proposed model is effective, scalable and robust to hyperparameter settings. We also perform an ablation study that confirms that GNN is the key ingredient to the power of the proposed model.

For agents

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

get_harvested_code_for_paper("1909.12201")
get_code_for_paper("1909.12201")
have("1909.12201")

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

curl https://syntology.ai/api/ran/1909.12201.json

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

[![Syntology run record](https://syntology.ai/api/ran/1909.12201.svg)](https://syntology.ai/paper/1909.12201)

Connect an agent — have() is free.