SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.11079 · NeurIPS · 2020

Graph Random Neural Networks for Semi-Supervised Learning on Graphs

Wenzheng Feng, Jie Zhang, Yuxiao Dong, Yu Han, Huanbo Luan, Qian Xu, Qiang Yang, Evgeny Kharlamov, Jie Tang, Webank Co

arXiv · PDF · Open in the Atlas

Code that ran

15 of 22 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 7 failures of our instrument; 7 no recorded run), measured 2026-11-21; 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/2005.11079.json · badge: /api/ran/2005.11079.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
Grand20/grand canonical (classifier label)
classifier basis: census
2 ran · 2 no recorded run
junzhuang-code/lindt community (classifier label)
classifier basis not recorded on the link
7 ran · 1 no recorded run
junzhuang-code/graphss community
Papers with Code archive
5 ran · 3 no recorded run
vapene/Graph-Random-Neural-Networks-for-Semi-Supervised-Learning-on-Graphs community
Papers with Code archive
1 ran · 1 no recorded run
FunctionStatusWhere it lives
BayesSelfSupervision Ran
ran on a synthesized input · constructed an object; no result was computed
junzhuang-code/graphss/graphSS/models_SS.py
code served (permissive licence) · get_code("991b5ce9d0230b0b")
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, BayesSelfSupervision: 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
import numpy as np
from torch import nn

torch.manual_seed(0)

ARGS = {
    'ALPHA': 1.0
}
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 BayesSelfSupervision — 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 BayesSelfSupervision 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
compute_accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
junzhuang-code/graphss/graphSS/models_SS.py
code served (permissive licence) · get_code("d22f6a0cb53e22bc")
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 float, 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 for testing
batch_size = 2
num_classes = 4

# logits: shape (batch_size, num_classes) - raw model outputs
logits = torch.randn(batch_size, num_classes)

# labels: shape (batch_size,) - ground truth class indices
labels = torch.randint(0, num_classes, (batch_size,))

# mask: shape (batch_size,) - boolean mask to select which samples to evaluate
mask = torch.tensor([True, False])

ARGS = {
    "logits": logits,
    "labels": labels,
    "mask": mask
}
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 float, 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
compute_alpha Ran
ran on a synthesized input
junzhuang-code/lindt/src/baselines/nettack/nettack.py
code served (permissive licence) · get_code("3dfa8f8448457f20")
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

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

# Case 1: scalar inputs
n_scalar = 100
S_d_scalar = 450.5
d_min_scalar = 2

# Case 2: array inputs
n_array = np.array([50, 100, 150])
S_d_array = np.array([200.3, 450.5, 750.2])
d_min_array = 2

# Create ARGS dict with scalar values
ARGS = {
    "n": n_scalar,
    "S_d": S_d_scalar,
    "d_min": d_min_scalar
}
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
connected_after Ran
ran on a synthesized input
junzhuang-code/lindt/src/baselines/nettack/nettack.py
code served (permissive licence) · get_code("e76a55dd6370c052")
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 bool, 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 numpy as np

torch.manual_seed(0)

# Analyzing the function:
# - u: integer (compared with v and checked against -1 implicitly through delta)
# - v: integer (compared with u)
# - connected_before: boolean (returned when u != v)
# - delta: integer (compared with -1)

ARGS = {
    "u": 0,
    "v": 1,
    "connected_before": True,
    "delta": 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numba, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, 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
encode_onehot Ran
ran; our contract draft was wrong, not the code
Grand20/grand/pygcn/utils.py
code served (permissive licence) · get_code("3ab88254add4c192")
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 (6, 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

# The function encode_onehot takes labels as input
# labels should be an array-like of class labels (integers, strings, etc.)
# The function creates a one-hot encoding mapping for unique classes

# Create sample labels with multiple distinct classes
labels = np.array([0, 1, 2, 1, 0, 2], dtype=int)

ARGS = {
    "labels": labels
}
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 (6, 3) — shape (6, 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
largest_connected_components Ran
ran, honoured the contract we drafted
junzhuang-code/lindt/src/baselines/nettack/utils.py
code served (permissive licence) · get_code("f18b6a502c85b70f")
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 int; 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
from scipy.sparse import csr_matrix

# Create a simple sparse adjacency matrix
# We'll create a graph with some connected components
# Component 1: nodes 0-2 (size 3)
# Component 2: nodes 3-4 (size 2)
# Component 3: node 5 (size 1)
row = np.array([0, 0, 1, 1, 2, 2, 3, 3, 4, 4])
col = np.array([1, 2, 0, 2, 0, 1, 4, 4, 3, 3])
data = np.ones(len(row))
adj = csr_matrix((data, (row, col)), shape=(6, 6))

ARGS = {
    'adj': adj,
    'n_components': 2
}
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 list, ndim 1, dtype family int — 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
load_checkpoint Ran
ran; our contract draft was wrong, not the code
junzhuang-code/graphss/graphSS/models_SS.py
code served (permissive licence) · get_code("f0de9371020525dc")
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, 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 torch
import torch.nn as nn
import tempfile
import os

torch.manual_seed(0)

# Create a simple model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create model and optimizer
model = SimpleModel()
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

# Create a temporary checkpoint file
with tempfile.NamedTemporaryFile(mode='wb', delete=False, suffix='.pt') as f:
    checkpoint_fpath = f.name
    checkpoint = {
        'state_dict': model.state_dict(),
        'optimizer': optimizer.state_dict(),
        'best_acc': 0.95,
        'epoch': 5
    }
    torch.save(checkpoint, checkpoint_fpath)

# Create fresh model and optimizer for loading
model_fresh = SimpleModel()
optimizer_fresh = torch.optim.SGD(model_fresh.parameters(), lr=0.01)

ARGS = {
    'checkpoint_fpath': checkpoint_fpath,
    'model': model_fresh,
    'optimizer': optimizer_fresh
}
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, ndim 1, dtype family float — a tuple 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
load_npz Ran
ran on a synthesized input
junzhuang-code/lindt/src/baselines/nettack/utils.py
code served (permissive licence) · get_code("3a0244a98c124e9a")
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 scipy.sparse as sp
import numpy as np
import tempfile
import os

# Create a temporary directory and file for the npz
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_graph.npz")

# Create sparse matrix data for adjacency matrix (4x4)
adj_data = np.array([1, 2, 3, 4], dtype=np.float32)
adj_indices = np.array([0, 1, 2, 3], dtype=np.int32)
adj_indptr = np.array([0, 1, 2, 3, 4], dtype=np.int32)
adj_shape = (4, 4)

# Create sparse matrix data for attribute matrix (4x3)
attr_data = np.array([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], dtype=np.float32)
attr_indices = np.array([0, 1, 2, 0, 1, 2], dtype=np.int32)
attr_indptr = np.array([0, 2, 4, 6, 6], dtype=np.int32)
attr_shape = (4, 3)

# Create labels
labels = np.array([0, 1, 0, 1], dtype=np.int32)

# Save to npz file
np.savez(
    temp_file,
    adj_data=adj_data,
    adj_indices=adj_indices,
    adj_indptr=adj_indptr,
    adj_shape=adj_shape,
    attr_data=attr_data,
    attr_indices=attr_indices,
    attr_indptr=attr_indptr,
    attr_shape=attr_shape,
    labels=labels
)

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 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
parse_index_file Ran
ran, honoured the contract we drafted
Grand20/grand/pygcn/utils.py
code served (permissive licence) · get_code("5c3fa9402a9405bc")
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) and returned list, ndim 1, dtype family int; 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 tempfile
import os

# Create a temporary file with index data
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("0\n")
temp_file.write("1\n")
temp_file.write("5\n")
temp_file.write("3\n")
temp_file.close()

ARGS = {
    "filename": temp_file.name
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 int — 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
prediction Ran
ran; our contract draft was wrong, not the code
junzhuang-code/graphss/graphSS/models_SS.py
code served (permissive licence) · get_code("3bce344d99820bd8")
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 torch
import torch.nn as nn
import networkx as nx
import tempfile
import os

torch.manual_seed(0)

# Build a minimal GCN model that satisfies the function's usage
class MinimalGCN(nn.Module):
    def __init__(self, input_dim, output_dim):
        super().__init__()
        self.linear = nn.Linear(input_dim, output_dim)
        self.g = None
    
    def forward(self, feat):
        return self.linear(feat)
    
    def eval(self):
        super().eval()
        return self

# Create model
model = MinimalGCN(input_dim=4, output_dim=3)

# Create optimizer
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)

# Create a temporary checkpoint file
with tempfile.TemporaryDirectory() as tmpdir:
    checkpoint_fpath = os.path.join(tmpdir, "checkpoint.pt")
    
    # Save a checkpoint
    checkpoint = {
        'state_dict': model.state_dict(),
        'optimizer': optimizer.state_dict(),
        'epoch': 10,
        'best_acc': 0.95
    }
    torch.save(checkpoint, checkpoint_fpath)
    
    # Create a simple graph
    graph = nx.Graph()
    graph.add_nodes_from([0, 1])
    
    # Create feature matrix matching number of nodes
    feat = torch.randn(2, 4)
    
    ARGS = {
        'model': model,
        'optimizer': optimizer,
        'path': checkpoint_fpath,
        'graph': graph,
        'feat': feat
    }
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
networkx, torch — 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
preprocess_graph Ran
ran; our contract draft was wrong, not the code
junzhuang-code/lindt/src/baselines/nettack/utils.py
code served (permissive licence) · get_code("fc3b508e487bb7c6")
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 scipy.sparse as sp
import numpy as np

# Create a small sparse adjacency matrix
# The function expects a scipy sparse matrix
n_nodes = 4
# Create a simple sparse graph as CSR matrix
row = np.array([0, 1, 2, 3, 0, 2])
col = np.array([1, 2, 3, 0, 3, 1])
data = np.array([1, 1, 1, 1, 1, 1], dtype=float)
adj = sp.csr_matrix((data, (row, col)), shape=(n_nodes, n_nodes))

ARGS = {
    '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 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
propagate Ran
ran; our contract draft was wrong, not the code
vapene/Graph-Random-Neural-Networks-for-Semi-Supervised-Learning-on-Graphs/train_grand.py
code served (permissive licence) · get_code("5087e50651937e1a")
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, 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

torch.manual_seed(0)

# feature: a dense tensor that will be multiplied with sparse matrix A
# and accumulated into y
# shape: (num_nodes, num_features)
feature = torch.randn(4, 3, dtype=torch.float32)

# A: sparse matrix for graph propagation
# shape: (num_nodes, num_nodes) - must be square for spmm with feature
# Create a sparse tensor in COO format
indices = torch.tensor([[0, 1, 2, 3], [1, 2, 3, 0]], dtype=torch.long)
values = torch.tensor([0.5, 0.5, 0.5, 0.5], dtype=torch.float32)
A = torch.sparse_coo_tensor(indices, values, (4, 4), dtype=torch.float32)

# order: number of propagation steps
order = 2

ARGS = {
    "feature": feature,
    "A": A,
    "order": order,
}
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, 3) — shape (4, 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
read_pickle Ran
ran on a synthesized input
junzhuang-code/lindt/src/utils.py
code served (permissive licence) · get_code("aec7eb44fa04447e")
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 pickle
import tempfile
import os

# Create a temporary pickle file with sample data
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_data.pkl")

# Write sample data to the pickle file
sample_data = {
    "key1": "value1",
    "key2": [1, 2, 3],
    "key3": {"nested": "data"}
}

with open(temp_file, 'wb') as f:
    pickle.dump(sample_data, f)

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
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 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
read_yaml_file Ran
ran on a synthesized input
junzhuang-code/lindt/src/utils.py
code served (permissive licence) · get_code("50cce9ad0aedf824")
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 os
import yaml
import tempfile

# Create a temporary directory and a valid yaml file for testing
temp_dir = tempfile.mkdtemp()
test_yaml_path = os.path.join(temp_dir, 'test_config.yaml')

# Write a sample yaml file
sample_yaml_content = """
model:
  name: test_model
  layers: 3
  hidden_dim: 128
training:
  epochs: 100
  learning_rate: 0.001
"""

with open(test_yaml_path, 'w') as f:
    f.write(sample_yaml_content)

# Define arguments for the function
ARGS = {
    'path': temp_dir,
    'file_name': 'test_config'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — 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
tensor2array Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
junzhuang-code/graphss/graphSS/models_SS.py
code served (permissive licence) · get_code("c05480a878ada1cf")
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 (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 tensor on CPU
tensor = torch.randn(2, 4)

# gpu parameter: negative value means CPU, non-negative means GPU
gpu = -1

ARGS = {
    "tensor": tensor,
    "gpu": gpu
}
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 ndarray, 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
compute_new_a_hat_uv Not yet run
unverified (harvested, no recorded run)
junzhuang-code/lindt/src/baselines/nettack/nettack.py
code served (permissive licence) · get_code("f7fada718dfb80fa")
How it ran

no invocation recorded.

dump_pickle Not yet run
unverified (harvested, no recorded run)
junzhuang-code/graphss/graphSS/models_SS.py
code served (permissive licence) · get_code("9217cd111831be29")
How it ran

no invocation recorded.

load_data Not yet run
unverified (harvested, no recorded run)
Grand20/grand/pygcn/utils.py
code served (permissive licence) · get_code("b7b41445fcb56b5e")
How it ran

no invocation recorded.

rand_prop Not yet run
unverified (harvested, no recorded run)
vapene/Graph-Random-Neural-Networks-for-Semi-Supervised-Learning-on-Graphs/train_grand.py
code served (permissive licence) · get_code("eaeb48eba0a39771")
How it ran

no invocation recorded.

rand_prop Not yet run
unverified (harvested, no recorded run)
Grand20/grand/train_grand.py
code served (permissive licence) · get_code("6fd1050c8370f6bd")
How it ran

no invocation recorded.

save_checkpoint Not yet run
unverified (harvested, no recorded run)
junzhuang-code/graphss/graphSS/models_SS.py
code served (permissive licence) · get_code("5b8f6ae013697a25")
How it ran

no invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
junzhuang-code/graphss/graphSS/models_SS.py
code served (permissive licence) · get_code("433c0da03b15b2fb")
How it ran

no invocation recorded.

Also present in other papers' code

Of 22 samples lifted from this paper's linked repositories, 22 carry a function identity and 0 do not. Of the 21 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 2 the same month, 6 later) and 13 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
parse_index_file 53 other papers
24 dated earlier, 29 later · 1 only as an assembly brick
1603.08861 (2016-03)
Revisiting Semi-Supervised Learning with Graph Embeddings
1611.07308 (2016-11)
Variational Graph Auto-Encoders
1710.10568 (2017-10)
Stochastic Training of Graph Convolutional Networks with Variance Reduction
and 50 more not named here
encode_onehot 12 other papers
5 dated earlier, 7 later
1609.02907 (2016-09)
Semi-Supervised Classification with Graph Convolutional Networks
1710.10903 (2017-10)
Graph Attention Networks
1803.03735 (2018-03)
Attention-based Graph Neural Network for Semi-supervised Learning
and 9 more not named here
largest_connected_components 6 other papers
5 dated earlier, 1 later
1803.00816 (2018-03)
NetGAN: Generating Graphs via Random Walks
1805.07984 (2018-05)
Adversarial Attacks on Neural Networks for Graph Data
1902.08412 (2019-02)
Adversarial Attacks on Graph Neural Networks via Meta Learning
and 3 more not named here
compute_new_a_hat_uv 3 other papers
1 dated earlier, 1 the same month, 1 later
1805.07984 (2018-05)
Adversarial Attacks on Neural Networks for Graph Data
2005.06149 (2020-05)
DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses
2110.14038 (2021-10)
Robustness of Graph Neural Networks at Scale
connected_after 3 other papers
1 dated earlier, 1 the same month, 1 later
1805.07984 (2018-05)
Adversarial Attacks on Neural Networks for Graph Data
2005.06149 (2020-05)
DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses
2110.14038 (2021-10)
Robustness of Graph Neural Networks at Scale
preprocess_graph 3 other papers
3 dated earlier
1805.07984 (2018-05)
Adversarial Attacks on Neural Networks for Graph Data
1902.08412 (2019-02)
Adversarial Attacks on Graph Neural Networks via Meta Learning
2004.13825 (2020-04)
Scalable Attack on Graph Data by Injecting Vicious Nodes
compute_alpha 2 other papers
1 dated earlier, 1 later
1805.07984 (2018-05)
Adversarial Attacks on Neural Networks for Graph Data
2110.14038 (2021-10)
Robustness of Graph Neural Networks at Scale
load_npz 1 other paper
1 dated earlier
1805.07984 (2018-05)
Adversarial Attacks on Neural Networks for Graph Data

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We study the problem of semi-supervised learning on graphs, for which graph neural networks (GNNs) have been extensively explored. However, most existing GNNs inherently suffer from the limitations of over-smoothing [7,27,28,34], non-robustness [54,51], and weak-generalization when labeled nodes are scarce. In this paper, we propose a simple yet effective framework-GRAPH RANDOM NEURAL NETWORKS (GRAND)-to address these issues. In GRAND, we first design a random propagation strategy to perform graph data augmentation. Then we leverage consistency regularization to optimize the prediction consistency of unlabeled nodes across different data augmentations. Extensive experiments on graph benchmark datasets suggest that GRAND significantly outperforms state-ofthe-art GNN baselines on semi-supervised node classification. Finally, we show that GRAND mitigates the issues of over-smoothing and non-robustness, exhibiting better generalization behavior than existing GNNs. The source code of GRAND is publicly available at https://github.com/Grand20/grand.

For agents

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

get_harvested_code_for_paper("2005.11079")
get_code_for_paper("2005.11079")
have("2005.11079")

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

curl https://syntology.ai/api/ran/2005.11079.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.11079.svg)](https://syntology.ai/paper/2005.11079)

Connect an agent — have() is free.