SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.01196 · NeurIPS · 2023

Combating Bilateral Edge Noise for Robust Link Prediction

Bo Han, Liang Wang, Quanming Yao, Bo Zheng, Jiangchao Yao, Li He, Xiawei Guo, Zhanke Zhou, Jiaxu Liu

arXiv · PDF · Open in the Atlas

Code that ran

20 of 34 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 4 honoured the contract we drafted, 3 violated it and 3 have no contract verdict; 10 failures of our instrument; 14 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/2311.01196.json · badge: /api/ran/2311.01196.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
flyingdoog/PTDNet canonical (classifier label)
classifier basis: census
7 ran · 4 no recorded run
tmlr-group/RGIB canonical (classifier label)
classifier basis: census
2 ran · 4 no recorded run
snap-stanford/GIB canonical (classifier label)
classifier basis: census
2 ran · 1 no recorded run
bhanML/Co-teaching canonical (classifier label)
classifier basis: census
2 ran · 0 no recorded run
HobbitLong/SupContrast canonical (classifier label)
classifier basis not recorded on the link
1 ran · 2 no recorded run
DSE-MSU/DeepRobust community
Papers with Code archive
3 ran · 0 no recorded run
tmlr-group/rgib reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
SJYuCNEL/PRI-Graphs community
Papers with Code archive
0 ran · 2 no recorded run
RingBDStack/VIB-GSL community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
GGCL_D Ran
ran on a synthesized input · constructed an object; no result was computed
DSE-MSU/DeepRobust/deeprobust/graph/defense/r_gcn.py
code served (permissive licence) · get_code("ba76b03db9248946")
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, GGCL_D: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from torch.nn.parameter import Parameter

torch.manual_seed(0)

# Create a small instance of GGCL_D
in_features = 4
out_features = 3
dropout = 0.5

model = nn.Module()

# Create input tensors
# miu: batch_size x in_features
miu = torch.randn(2, 4)
# sigma: batch_size x in_features
sigma = torch.randn(2, 4)

# Create adjacency matrices
# adj_norm1 and adj_norm2: should be node_count x node_count
# We'll use 2 nodes (matching batch size)
adj_norm1 = torch.randn(2, 2)
adj_norm2 = torch.randn(2, 2)

# gamma parameter
gamma = 1

ARGS = {
    'in_features': in_features,
    'out_features': out_features,
    'dropout': dropout,
}
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 GGCL_D — 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 GGCL_D 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
GGCL_F Ran
ran on a synthesized input
DSE-MSU/DeepRobust/deeprobust/graph/defense/r_gcn.py
code served (permissive licence) · get_code("2bc8cab5c6ba3c6d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned 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
import torch.nn as nn
from torch.nn.parameter import Parameter
from torch.nn.modules.module import Module
import torch.nn.functional as F

class GGCL_F(Module):
    """Graph Gaussian Convolution Layer (GGCL) when the input is feature"""

    def __init__(self, in_features, out_features, dropout=0.6):
        super(GGCL_F, self).__init__()
        self.in_features = in_features
        self.out_features = out_features
        self.dropout = dropout
        self.weight_miu = Parameter(torch.FloatTensor(in_features, out_features))
        self.weight_sigma = Parameter(torch.FloatTensor(in_features, out_features))
        self.reset_parameters()

    def reset_parameters(self):
        torch.nn.init.xavier_uniform_(self.weight_miu)
        torch.nn.init.xavier_uniform_(self.weight_sigma)

    def forward(self, features, adj_norm1, adj_norm2, gamma=1):
        features = F.dropout(features, self.dropout, training=self.training)
        self.miu = F.elu(torch.mm(features, self.weight_miu))
        self.sigma = F.relu(torch.mm(features, self.weight_sigma))
        Att = torch.exp(-gamma * self.sigma)
        miu_out = adj_norm1 @ (self.miu * Att)
        sigma_out = adj_norm2 @ (self.sigma * Att * Att)
        return (miu_out, sigma_out)


INIT_ARGS = {
    'in_features': 4,
    'out_features': 3,
    'dropout': 0.5,
}

num_nodes = 5
ARGS = {
    'features': torch.randn(num_nodes, 4),
    'adj_norm1': torch.randn(num_nodes, num_nodes),
    'adj_norm2': torch.randn(num_nodes, num_nodes),
    'gamma': 1.0,
}

model = GGCL_F(**INIT_ARGS)
model.eval()
output = model(**ARGS)
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
RGCN Ran
ran on a synthesized input · constructed an object; no result was computed
DSE-MSU/DeepRobust/deeprobust/graph/defense/r_gcn.py
code served (permissive licence) · get_code("113eaa2f60b75746")
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, RGCN: 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 torch.nn as nn
from torch.nn.parameter import Parameter
from torch.distributions.multivariate_normal import MultivariateNormal

torch.manual_seed(0)

# Small stand-in values for RGCN constructor
nnodes = 2
nfeat = 4
nhid = 8
nclass = 3
gamma = 1.0
beta1 = 0.0005
beta2 = 0.0005
lr = 0.01
dropout = 0.6
device = 'cpu'

ARGS = {
    'nnodes': nnodes,
    'nfeat': nfeat,
    'nhid': nhid,
    'nclass': nclass,
    'gamma': gamma,
    'beta1': beta1,
    'beta2': beta2,
    'lr': lr,
    'dropout': dropout,
    'device': device
}
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 RGCN — 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 RGCN 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
call_bn Ran
ran; our contract draft was wrong, not the code
bhanML/Co-teaching/model.py
pointer only (licence: NONE); the stored copy get_code serves, from yeachan-kr/pytorch-coteaching, is pointer only (licence: NONE) · get_code("7937f88152d63f61")
How it ran

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

dot Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
flyingdoog/PTDNet/NeuralSparse/layers.py
pointer only (licence: NONE) · get_code("4dbcacad67a07f0e")
How it ran

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

generateNoisyEdges Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
tmlr-group/rgib/code/mixed-noise-generation.py
code served (permissive licence) · get_code("409c3864b5df44a2")
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 Tensor, ndim 2, dtype family int, 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 numpy as np
import torch

torch.manual_seed(0)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# Create a small distance matrix
# The function checks if distance_matrix[head, tail] >= 2
# So we need values >= 2 in the matrix
distance_matrix = np.array([
    [0, 1, 3, 2],
    [1, 0, 2, 3],
    [3, 2, 0, 1],
    [2, 3, 1, 0]
], dtype=np.float32)

num_noisy_edges = 2

filter_mask = None

ARGS = {
    "distance_matrix": distance_matrix,
    "num_noisy_edges": num_noisy_edges,
    "filter_mask": filter_mask
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 int, 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
getDistanceMatrix Ran
ran; our contract draft was wrong, not the code
tmlr-group/rgib/code/mixed-noise-generation.py
code served (permissive licence) · get_code("d473d7ce4815a1f2")
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 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 networkx as nx
import numpy as np

# Create a small graph with 4 nodes
G = nx.Graph()
G.add_nodes_from([0, 1, 2, 3])
G.add_edges_from([(0, 1), (1, 2), (2, 3)])

ARGS = {
    "G": G
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
networkx, 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
get_layer_uid Ran
ran, honoured the contract we drafted
flyingdoog/PTDNet/NeuralSparse/layers.py
pointer only (licence: NONE); the stored copy get_code serves, from thumlp/tensorgcn, is pointer only (licence: NONE) · get_code("b82968db452628fd")
How it ran

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

get_reparam_num_neurons Ran
ran, honoured the contract we drafted
snap-stanford/GIB/util.py
code served (permissive licence) · get_code("01e22d114b1da6d8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Test case 1: reparam_mode is None
out_channels_1 = 16
reparam_mode_1 = None

# Test case 2: reparam_mode is 'diag'
out_channels_2 = 8
reparam_mode_2 = 'diag'

# Test case 3: reparam_mode is 'full'
out_channels_3 = 4
reparam_mode_3 = 'full'

# We'll use the first test case for ARGS
ARGS = {
    'out_channels': 16,
    'reparam_mode': None
}
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 int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
jensen_shannon_distance Ran
ran, violated the contract we drafted
tmlr-group/RGIB/code/utils.py
code served (permissive licence) · get_code("8eb2022e63f3cdeb")
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

# The function takes two probability distributions p and q
# and computes the Jensen-Shannon distance between them.
# Both parameters should be array-like objects (lists or numpy arrays)
# that represent probability distributions.

# Create two small valid probability distributions
p = [0.1, 0.2, 0.3, 0.4]  # sums to 1.0
q = [0.25, 0.25, 0.25, 0.25]  # uniform distribution

ARGS = {
    "p": p,
    "q": q,
}
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 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
loss_coteaching Ran
ran; our contract draft was wrong, not the code
bhanML/Co-teaching/loss.py
pointer only (licence: NONE) · get_code("4bb8724aa829258e")
How it ran

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

lunif Ran
ran; our contract draft was wrong, not the code
tmlr-group/RGIB/code/loss.py
code served (permissive licence) · get_code("4515b40a239b4ddc")
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 lunif computes a loss based on pairwise distances
# It takes:
# - x: a tensor of shape (n, d) where n is batch size and d is dimension
# - t: a scalar temperature parameter (default 2)

# Create a small tensor with batch size 2 and dimension 4
x = torch.randn(2, 4)

# Set t to the default value
t = 2

ARGS = {
    "x": x,
    "t": t,
}
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
masked_sigmoid_cross_entropy Ran
ran, violated the contract we drafted
flyingdoog/PTDNet/metrics.py
pointer only (licence: NONE) · get_code("dfee757e2af344c6")
How it ran

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

parse_index_file Ran
ran, honoured the contract we drafted
flyingdoog/PTDNet/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from DSL-Lab/Specformer, is pointer only (licence: GPL-3.0) · get_code("c1d6392f89c5e495")
How it ran

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

sample_lognormal Ran
ran; our contract draft was wrong, not the code
snap-stanford/GIB/util.py
code served (permissive licence) · get_code("62508539722283e0")
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 small tensors
mean = torch.randn(2, 4)
sigma = torch.randn(2, 4)

ARGS = {
    "mean": mean,
    "sigma": sigma,
    "sigma0": 1.0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type 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
sample_mask Ran
ran, violated the contract we drafted
flyingdoog/PTDNet/utils.py
pointer only (licence: NONE) · get_code("b32fd748b4bbe3bf")
How it ran

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

sampling_MI Ran
ran; our contract draft was wrong, not the code
tmlr-group/rgib/code/RGIB-rep-training.py
code served (permissive licence) · get_code("ab6aec3ea2b97d07")
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 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 probability tensor (batch_size=2, features=4)
# Values should be between 0 and 1 for valid probabilities
prob = torch.rand(2, 4)

ARGS = {
    'prob': prob,
    'tau': 0.8,
    'reduction': 'none'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
set_optimizer Ran
ran; our contract draft was wrong, not the code
HobbitLong/SupContrast/util.py
pointer only (licence: BSD-2-Clause); the stored copy get_code serves, from deeplearning-wisc/haloscope, is pointer only (licence: NONE) · get_code("a44a1925c2c778ba")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-2-Clause), but get_code serves the stored copy, first harvested from deeplearning-wisc/haloscope, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sigmoid_cross_entropy Ran
ran, honoured the contract we drafted
flyingdoog/PTDNet/metrics.py
pointer only (licence: NONE) · get_code("a2f118a9c3aab3ec")
How it ran

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

zeros Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
flyingdoog/PTDNet/inits.py
pointer only (licence: NONE) · get_code("b190ef9c60b2629a")
How it ran

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

VIBGSL Not yet run
unverified (harvested, no recorded run)
RingBDStack/VIB-GSL/gsl.py
pointer only (licence: NONE) · get_code("681b733b07691df9")
How it ran

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

accuracy Not yet run
unverified (harvested, no recorded run)
HobbitLong/SupContrast/util.py
pointer only (licence: BSD-2-Clause); the stored copy get_code serves, from boone891214/MEST, is pointer only (licence: NONE) · get_code("913d82af53065418")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-2-Clause), but get_code serves the stored copy, first harvested from boone891214/MEST, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

entropy_loss Not yet run
unverified (harvested, no recorded run)
SJYuCNEL/PRI-Graphs/graph_sparse.py
pointer only (licence: NONE) · get_code("ebac4362ac395e38")
How it ran

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

getDataset Not yet run
unverified (harvested, no recorded run)
tmlr-group/RGIB/code/utils.py
code served (permissive licence) · get_code("2b30a97cae58f081")
How it ran

no invocation recorded.

getGNNArch_tmp Not yet run
unverified (harvested, no recorded run)
tmlr-group/RGIB/code/RGIB-rep-training.py
code served (permissive licence) · get_code("04403559a70cb189")
How it ran

no invocation recorded.

glorot Not yet run
unverified (harvested, no recorded run)
flyingdoog/PTDNet/inits.py
pointer only (licence: NONE); the stored copy get_code serves, from nju-websoft/OpenEA, is pointer only (licence: GPL-3.0) · get_code("1b491f3f784b7cb0")
How it ran

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

load_data Not yet run
unverified (harvested, no recorded run)
flyingdoog/PTDNet/utils.py
pointer only (licence: NONE) · get_code("7e7158e6b82fa608")
How it ran

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

scatter_sample Not yet run
unverified (harvested, no recorded run)
snap-stanford/GIB/util.py
code served (permissive licence) · get_code("eb83ba63e3393a08")
How it ran

no invocation recorded.

set_loader Not yet run
unverified (harvested, no recorded run)
HobbitLong/SupContrast/main_ce.py
pointer only (licence: BSD-2-Clause); the stored copy get_code serves, from dongguanting/dpa-rag, is pointer only (licence: NONE) · get_code("2297ed2ca4911b7c")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-2-Clause), but get_code serves the stored copy, first harvested from dongguanting/dpa-rag, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

sparse_dropout Not yet run
unverified (harvested, no recorded run)
flyingdoog/PTDNet/NeuralSparse/layers.py
pointer only (licence: NONE) · get_code("107e7afdd93ee0b4")
How it ran

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

standard_train_trial Not yet run
unverified (harvested, no recorded run)
tmlr-group/RGIB/code/RGIB-rep-training.py
code served (permissive licence) · get_code("b7a7eb6330cc4bb7")
How it ran

no invocation recorded.

standard_train_trial Not yet run
unverified (harvested, no recorded run)
tmlr-group/RGIB/code/standard-training.py
code served (permissive licence) · get_code("c4135a809c5eb290")
How it ran

no invocation recorded.

uniform Not yet run
unverified (harvested, no recorded run)
flyingdoog/PTDNet/inits.py
pointer only (licence: NONE) · get_code("b0d1b78daecde7e9")
How it ran

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

vn_entropy Not yet run
unverified (harvested, no recorded run)
SJYuCNEL/PRI-Graphs/graph_sparse.py
pointer only (licence: NONE) · get_code("0672693e7656212b")
How it ran

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

Also present in other papers' code

Of 34 samples lifted from this paper's linked repositories, 34 carry a function identity and 0 do not. Of the 34 distinct functions with an identity, 12 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 2 the same month, 8 later) and 22 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
accuracy 80 other papers
70 dated earlier, 2 the same month, 8 later
1307.0414 (2013-07)
Challenges in Representation Learning: A report on three machine learning contests
1412.6553 (2014-12)
Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition
1503.02531 (2015-03)
Distilling the Knowledge in a Neural Network
and 77 more not named here
parse_index_file 53 other papers
47 dated earlier, 1 the same month, 5 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
get_layer_uid 33 other papers
32 dated earlier, 1 later · 5 only as an assembly brick
1603.08861 (2016-03)
Revisiting Semi-Supervised Learning with Graph Embeddings
1606.09375 (2016-06)
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
1609.02907 (2016-09)
Semi-Supervised Classification with Graph Convolutional Networks
and 30 more not named here
sample_mask 28 other papers
27 dated earlier, 1 later
1603.08861 (2016-03)
Revisiting Semi-Supervised Learning with Graph Embeddings
1710.10568 (2017-10)
Stochastic Training of Graph Convolutional Networks with Variance Reduction
1710.10903 (2017-10)
Graph Attention Networks
and 25 more not named here
zeros 18 other papers
18 dated earlier
1603.08861 (2016-03)
Revisiting Semi-Supervised Learning with Graph Embeddings
1804.00823 (2018-04)
Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
1804.01654 (2018-04)
Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images
and 15 more not named here
uniform 17 other papers
17 dated earlier
1603.08861 (2016-03)
Revisiting Semi-Supervised Learning with Graph Embeddings
1804.00823 (2018-04)
Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
1804.01654 (2018-04)
Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images
and 14 more not named here
glorot 16 other papers
16 dated earlier
1603.08861 (2016-03)
Revisiting Semi-Supervised Learning with Graph Embeddings
1804.00823 (2018-04)
Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
1804.01654 (2018-04)
Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images
and 13 more not named here
set_optimizer 9 other papers
4 dated earlier, 4 later, 1 same year, order not determinable
1901.07659 (2019-01)
A Machine Learning Benchmark for Facies Classification
1906.05849 (2019-06)
Contrastive Multiview Coding
2004.11362 (2020-04)
Supervised Contrastive Learning
and 6 more not named here
call_bn 3 other papers
3 dated earlier
1804.06872 (2018-04)
Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels
2106.10891 (2021-06)
Open-set Label Noise Can Improve Robustness Against Inherent Label Noise
2207.13378 (2022-07)
Identifying Hard Noise in Long-Tailed Sample Distribution
set_loader 3 other papers
2 dated earlier, 1 later
2004.11362 (2020-04)
Supervised Contrastive Learning
2308.10239 (2023-08)
From Global to Local: Multi-scale Out-of-distribution Detection
2406.18676 (2024-06)
Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation
get_reparam_num_neurons 1 other paper
1 later
2402.06716 (2024-02)
Dynamic Graph Information Bottleneck
sample_lognormal 1 other paper
1 later
2402.06716 (2024-02)
Dynamic Graph Information Bottleneck

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

Although link prediction on graphs has achieved great success with the development of graph neural networks (GNNs), the potential robustness under the edge noise is still less investigated. To close this gap, we first conduct an empirical study to disclose that the edge noise bilaterally perturbs both input topology and target label, yielding severe performance degradation and representation collapse. To address this dilemma, we propose an information-theory-guided principle, Robust Graph Information Bottleneck (RGIB), to extract reliable supervision signals and avoid representation collapse. Different from the basic information bottleneck, RGIB further decouples and balances the mutual dependence among graph topology, target labels, and representation, building new learning objectives for robust representation against the bilateral noise. Two instantiations, RGIB-SSL and RGIB-REP, are explored to leverage the merits of different methodologies, i.e., self-supervised learning and data reparameterization, for implicit and explicit data denoising, respectively. Extensive experiments on six datasets and three GNNs with diverse noisy scenarios verify the effectiveness of our RGIB instantiations. The code is publicly available at: https://github.com/tmlr-group/RGIB.

For agents

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

get_harvested_code_for_paper("2311.01196")
get_code_for_paper("2311.01196")
have("2311.01196")

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

curl https://syntology.ai/api/ran/2311.01196.json

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

[![Syntology run record](https://syntology.ai/api/ran/2311.01196.svg)](https://syntology.ai/paper/2311.01196)

Connect an agent — have() is free.