SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.12875 · 2022

A Survey of Deep Graph Clustering: Taxonomy, Challenge, Application, and Open Resource

arXiv · PDF · Open in the Atlas

Code that ran

14 of 15 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 11 have no contract verdict; 3 failures of our instrument; 1 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/2211.12875.json · badge: /api/ran/2211.12875.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
marigoldwu/a-unified-framework-for-deep-attribute-graph-clustering canonical (classifier label)
classifier basis not recorded on the link
14 ran · 1 no recorded run
FunctionStatusWhere it lives
aux_objective Ran
ran on a synthesized input
marigoldwu/a-unified-framework-for-deep-attribute-graph-clustering/pydgc/models/dgcluster.py
code served (permissive licence) · get_code("4905baed41d3c5f6")
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

torch.manual_seed(0)

# Create small tensors with distinct dimensions
batch_size = 2
num_classes = 3
output_dim = 4

# output: tensor indexed by s, should have shape (total_samples, output_dim)
output = torch.randn(5, output_dim)

# s: sample indices, should be a 1D tensor of indices
s = torch.tensor([0, 2])

# oh_labels: one-hot labels, should have shape (total_samples, num_classes)
oh_labels = torch.zeros(5, num_classes)
oh_labels[0, 0] = 1
oh_labels[1, 1] = 1
oh_labels[2, 2] = 1
oh_labels[3, 0] = 1
oh_labels[4, 1] = 1

ARGS = {
    "output": output,
    "s": s,
    "oh_labels": oh_labels,
}
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
clustering Ran
ran on a synthesized input
marigoldwu/a-unified-framework-for-deep-attribute-graph-clustering/pydgc/models/magi.py
code served (permissive licence) · get_code("4d1191671cba756b")
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. 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
import numpy as np

torch.manual_seed(0)

# Create small feature tensor (batch_size=2, feature_dim=4)
feature = torch.randn(2, 4)

# Number of clusters
n_clusters = 2

# True labels tensor
true_labels = torch.tensor([0, 1])

# Device for kmeans
kmeans_device = 'cpu'

# Batch size
batch_size = 100000

# Tolerance
tol = 0.0001

# Device (CPU only)
device = torch.device('cpu')

# Whether to use spectral clustering
spectral_clustering = False

ARGS = {
    'feature': feature,
    'n_clusters': n_clusters,
    'true_labels': true_labels,
    'kmeans_device': kmeans_device,
    'batch_size': batch_size,
    'tol': tol,
    'device': device,
    'spectral_clustering': spectral_clustering,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, 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
comprehensive_similarity Ran
ran on a synthesized input
marigoldwu/a-unified-framework-for-deep-attribute-graph-clustering/pydgc/models/hsan.py
code served (permissive licence) · get_code("67cedfe88192fd2f")
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 (4, 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 small tensors for the function arguments
# Z1 and Z2 are latent representations from first and second views
# E1 and E2 are also latent representations (possibly from encoders)
# Using batch_size=2, latent_dim=4 for Z tensors and E tensors

Z1 = torch.randn(2, 4)  # shape (2, 4)
Z2 = torch.randn(2, 4)  # shape (2, 4)
E1 = torch.randn(2, 4)  # shape (2, 4)
E2 = torch.randn(2, 4)  # shape (2, 4)
alpha = 0.7  # float weight parameter

ARGS = {
    "Z1": Z1,
    "Z2": Z2,
    "E1": E1,
    "E2": E2,
    "alpha": alpha,
}
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 (4, 4) — shape (4, 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
convert_scipy_torch_sp Ran
ran on a synthesized input
marigoldwu/a-unified-framework-for-deep-attribute-graph-clustering/pydgc/models/dgcluster.py
code served (permissive licence) · get_code("35b4899c9c2538c7")
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. 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 scipy.sparse as sp

torch.manual_seed(0)

# Create a small scipy sparse matrix (CSR format)
# 4x3 matrix with a few non-zero elements
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])
sp_adj = sp.csr_matrix((data, (row, col)), shape=(4, 3))

ARGS = {
    "sp_adj": sp_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, 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
hard_sample_aware_infoNCE Ran
ran on a synthesized input
marigoldwu/a-unified-framework-for-deep-attribute-graph-clustering/pydgc/models/hsan.py
code served (permissive licence) · get_code("47733477ce73f39c")
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

torch.manual_seed(0)

# Analyze the function to understand what's needed:
# - S: similarity matrix, used in torch.exp(S * pos_neg_weight) and torch.diag(S, node_num)
# - M: mask matrix, same shape as S, used in element-wise multiplication
# - pos_neg_weight: float, scalar weight
# - pos_weight: float, scalar weight
# - node_num: int, used to extract diagonals and compute final loss

# torch.diag(S, node_num) extracts the k-th diagonal
# torch.diag(S, -node_num) extracts the -k-th diagonal
# For this to work, S must be at least (2*node_num) x (2*node_num)
# Let's use node_num=2, so S should be at least 4x4

node_num = 2
batch_size = 4  # S should be (batch_size, batch_size) at minimum

# Create S as a 4x4 similarity matrix
S = torch.randn(4, 4)

# Create M as a mask matrix with same shape, with 1s and 0s
# Set diagonal to 0 (mask out positive pairs if needed)
M = torch.ones(4, 4)
M[torch.eye(4, dtype=torch.bool)] = 0

pos_neg_weight = 0.5
pos_weight = 1.0

ARGS = {
    "S": S,
    "M": M,
    "pos_neg_weight": pos_neg_weight,
    "pos_weight": pos_weight,
    "node_num": node_num,
}
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
new_graph Ran
ran on a synthesized input
marigoldwu/a-unified-framework-for-deep-attribute-graph-clustering/pydgc/models/agcdrr.py
code served (permissive licence) · get_code("c5b6b75a2ae78c26")
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. 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 edge_index as a 2D tensor with shape (2, 4)
# First row: source nodes, second row: target nodes
edge_index = torch.tensor([[0, 1, 2, 1],
                           [1, 2, 3, 0]], dtype=torch.long)

# Create weight tensor corresponding to edges
weight = torch.tensor([0.5, 0.3, 0.8, 0.2], dtype=torch.float32)

# Number of nodes
n = 4

# Device
device = torch.device('cpu')

ARGS = {
    'edge_index': edge_index,
    'weight': weight,
    'n': n,
    'device': device
}
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, shape (4, 4) — shape (4, 4) 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
normalize Ran
ran on a synthesized input
marigoldwu/a-unified-framework-for-deep-attribute-graph-clustering/pydgc/models/agcdrr.py
code served (permissive licence) · get_code("e16f86b431e93340")
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 csr_matrix. 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

# Create a small sparse matrix for testing
# Create a 4x3 sparse matrix (distinct dimensions for clarity)
row = np.array([0, 0, 1, 2, 2, 3])
col = np.array([0, 2, 2, 0, 1, 1])
data = np.array([1.0, 2.0, 3.0, 4.0, 5.0, 6.0])
mx = sp.csr_matrix((data, (row, col)), shape=(4, 3))

ARGS = {
    "mx": mx
}
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 csr_matrix — a csr_matrix output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a csr_matrix 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
normalize_adj Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
marigoldwu/a-unified-framework-for-deep-attribute-graph-clustering/pydgc/models/dcrn.py
code served (permissive licence) · get_code("c4e018bdf71a1f35")
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 (4, 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 numpy as np

# Create a small adjacency matrix (4x4)
# Using distinct sizes to make it clear: 4 nodes
adj = np.array([
    [0, 1, 1, 0],
    [1, 0, 1, 1],
    [1, 1, 0, 1],
    [0, 1, 1, 0]
], dtype=np.float32)

ARGS = {
    "adj": adj,
    "self_loop": True,
    "symmetry": False,
}
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 (4, 4) — shape (4, 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
numpy_to_torch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
marigoldwu/a-unified-framework-for-deep-attribute-graph-clustering/pydgc/models/dcrn.py
code served (permissive licence) · get_code("d860dca965128863")
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 numpy as np

torch.manual_seed(0)

# Create a small numpy array for testing
numpy_array = np.random.randn(2, 4).astype(np.float32)

ARGS = {
    "a": numpy_array,
    "sparse": False
}
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 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
regularization Ran
ran on a synthesized input
marigoldwu/a-unified-framework-for-deep-attribute-graph-clustering/pydgc/models/dgcluster.py
code served (permissive licence) · get_code("e82410e993da99a0")
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

torch.manual_seed(0)

# The function expects:
# - output: a torch.Tensor that can be indexed with [s, :] where s are indices
# - s: a torch.Tensor of indices (used for indexing and len())

# Create a small output tensor (batch_size=5, feature_dim=4)
output = torch.randn(5, 4)

# Create sample indices as a tensor
# s is used with: output[s, :], len(s), and s is passed to len()
# s should be a 1D tensor or list of indices
s = torch.tensor([0, 2, 4])

ARGS = {
    "output": output,
    "s": s,
}
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
remove_edge Ran
ran on a synthesized input
marigoldwu/a-unified-framework-for-deep-attribute-graph-clustering/pydgc/models/dcrn.py
code served (permissive licence) · get_code("1a7f3fbaa1bd6d17")
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 (4, 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 numpy as np

torch.manual_seed(0)

# Create a small adjacency matrix (4x4)
n_nodes = 4
A = np.array([
    [0, 1, 1, 0],
    [1, 0, 1, 1],
    [1, 1, 0, 1],
    [0, 1, 1, 0]
], dtype=np.float32)

# Create a similarity matrix (4x4) with values in [0, 1]
similarity = torch.FloatTensor([
    [1.0, 0.8, 0.6, 0.2],
    [0.8, 1.0, 0.7, 0.3],
    [0.6, 0.7, 1.0, 0.5],
    [0.2, 0.3, 0.5, 1.0]
])

ARGS = {
    'A': A,
    'similarity': similarity,
    'remove_rate': 0.25,
    'device': 'cpu'
}
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 2, dtype family float, shape (4, 4) — shape (4, 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
scale Ran
ran on a synthesized input
marigoldwu/a-unified-framework-for-deep-attribute-graph-clustering/pydgc/models/magi.py
code served (permissive licence) · get_code("410bc97745f4b297")
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 a small latent representation tensor
# Shape: (batch_size=2, latent_dim=4)
z = torch.randn(2, 4)

ARGS = {
    "z": z
}
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
square_euclid_distance Ran
ran on a synthesized input
marigoldwu/a-unified-framework-for-deep-attribute-graph-clustering/pydgc/models/hsan.py
code served (permissive licence) · get_code("143d99fb8b6fb704")
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, 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 torch
import numpy as np

torch.manual_seed(0)

# Create small tensor arguments
# Z: latent representation with shape (batch_size, latent_dim)
Z = torch.randn(2, 4)

# center: clustering centers with shape (num_centers, latent_dim)
center = torch.randn(3, 4)

ARGS = {
    "Z": Z,
    "center": center,
}
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 2, dtype family float, shape (2, 3) — shape (2, 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
target_distribution Ran
ran; our contract draft was wrong, not the code
marigoldwu/a-unified-framework-for-deep-attribute-graph-clustering/pydgc/models/dfcn.py
code served (permissive licence) · get_code("d9d1d0c203d5cf1b")
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 a small tensor with shape (batch=2, dim=4)
# The function performs operations: q ** 2, q.sum(0), .t(), weight.sum(1)
# So we need a 2D tensor where sum(0) and sum(1) both make sense
q = torch.rand(2, 4)

ARGS = {
    "q": q,
}
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
init_clustering Not yet run
unverified (harvested, no recorded run)
marigoldwu/a-unified-framework-for-deep-attribute-graph-clustering/pydgc/models/ccgc.py
code served (permissive licence) · get_code("22bf7799b5b320ab")
How it ran

no invocation 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, 15 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 15 later) and 0 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
target_distribution 8 other papers
3 dated earlier, 5 later
1906.06532 (2019-06)
Attributed Graph Clustering: A Deep Attentional Embedding Approach
2002.01633 (2020-02)
Structural Deep Clustering Network
2009.11407 (2020-09)
Steering a Historical Disease Forecasting Model Under a Pandemic: Case of Flu and COVID-19
and 5 more not named here
numpy_to_torch 3 other papers
2 later, 1 same year, order not determinable
aaai_20726 (2022 (year only))
Deep Graph Clustering via Dual Correlation Reduction
2309.04694 (2023-09)
Redundancy-Free Self-Supervised Relational Learning for Graph Clustering
2506.05019 (2025-06)
FinMultiTime: A Four-Modal Bilingual Dataset for Financial Time-Series Analysis
normalize_adj 2 other papers
2 later
2309.04694 (2023-09)
Redundancy-Free Self-Supervised Relational Learning for Graph Clustering
2506.05019 (2025-06)
FinMultiTime: A Four-Modal Bilingual Dataset for Financial Time-Series Analysis
aux_objective 1 other paper
1 later
2506.05019 (2025-06)
FinMultiTime: A Four-Modal Bilingual Dataset for Financial Time-Series Analysis
clustering 1 other paper
1 later
2506.05019 (2025-06)
FinMultiTime: A Four-Modal Bilingual Dataset for Financial Time-Series Analysis
comprehensive_similarity 1 other paper
1 later
2506.05019 (2025-06)
FinMultiTime: A Four-Modal Bilingual Dataset for Financial Time-Series Analysis
convert_scipy_torch_sp 1 other paper
1 later
2506.05019 (2025-06)
FinMultiTime: A Four-Modal Bilingual Dataset for Financial Time-Series Analysis
hard_sample_aware_infoNCE 1 other paper
1 later
2506.05019 (2025-06)
FinMultiTime: A Four-Modal Bilingual Dataset for Financial Time-Series Analysis
init_clustering 1 other paper
1 later
2506.05019 (2025-06)
FinMultiTime: A Four-Modal Bilingual Dataset for Financial Time-Series Analysis
new_graph 1 other paper
1 later
2506.05019 (2025-06)
FinMultiTime: A Four-Modal Bilingual Dataset for Financial Time-Series Analysis
normalize 1 other paper
1 later
2506.05019 (2025-06)
FinMultiTime: A Four-Modal Bilingual Dataset for Financial Time-Series Analysis
regularization 1 other paper
1 later
2506.05019 (2025-06)
FinMultiTime: A Four-Modal Bilingual Dataset for Financial Time-Series Analysis
remove_edge 1 other paper
1 later
2506.05019 (2025-06)
FinMultiTime: A Four-Modal Bilingual Dataset for Financial Time-Series Analysis
scale 1 other paper
1 later
2506.05019 (2025-06)
FinMultiTime: A Four-Modal Bilingual Dataset for Financial Time-Series Analysis
square_euclid_distance 1 other paper
1 later
2506.05019 (2025-06)
FinMultiTime: A Four-Modal Bilingual Dataset for Financial Time-Series Analysis

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

Graph clustering, which aims to divide nodes in the graph into several distinct clusters, is a fundamental yet challenging task. Benefiting from the powerful representation capability of deep learning, deep graph clustering methods have achieved great success in recent years. However, the corresponding survey paper is relatively scarce, and it is imminent to make a summary of this field. From this motivation, we conduct a comprehensive survey of deep graph clustering. Firstly, we introduce formulaic definition, evaluation, and development in this field. Secondly, the taxonomy of deep graph clustering methods is presented based on four different criteria, including graph type, network architecture, learning paradigm, and clustering method. Thirdly, we carefully analyze the existing methods via extensive experiments and summarize the challenges and opportunities from five perspectives, including graph data quality, stability, scalability, discriminative capability, and unknown cluster number. Besides, the applications of deep graph clustering methods in six domains, including computer vision, natural language processing, recommendation systems, social network analyses, bioinformatics, and medical science, are presented. Last but not least, this paper provides open resource supports, including 1) a collection (\url{https://github.com/yueliu1999/Awesome-Deep-Graph-Clustering}) of state-of-the-art deep graph clustering methods (papers, codes, and datasets) and 2) a unified framework (\url{https://github.com/Marigoldwu/A-Unified-Framework-for-Deep-Attribute-Graph-Clustering}) of deep graph clustering. We hope this work can serve as a quick guide and help researchers overcome challenges in this vibrant field.

For agents

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

get_harvested_code_for_paper("2211.12875")
get_code_for_paper("2211.12875")
have("2211.12875")

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

curl https://syntology.ai/api/ran/2211.12875.json

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

[![Syntology run record](https://syntology.ai/api/ran/2211.12875.svg)](https://syntology.ai/paper/2211.12875)

Connect an agent — have() is free.