SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.06716 · 2024

Dynamic Graph Information Bottleneck

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2402.06716.json · badge: /api/ran/2402.06716.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
ringbdstack/dgib canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
FunctionStatusWhere it lives
get_reparam_num_neurons Ran
ran, honoured the contract we drafted
ringbdstack/dgib/DGIB/util_IB.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
recursive_index Ran
ran; our contract draft was wrong, not the code
ringbdstack/dgib/DGIB/pytorch_net/util.py
code served (permissive licence) · get_code("9e275404aa5e3c6a")
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. 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)

# The function recursively indexes into nested data structures.
# It expects:
# - data: a list/tuple of elements where each element is either:
#   - a tuple (which triggers recursive call)
#   - an indexable object like a tensor or list (which gets indexed with idx)
# - idx: an integer index to apply to non-tuple elements

# Create some indexable objects (tensors)
tensor1 = torch.randn(5, 4)  # 5 samples, 4 features
tensor2 = torch.randn(5, 3)  # 5 samples, 3 features
tensor3 = torch.randn(5, 2)  # 5 samples, 2 features

# Create a nested structure with tuples and tensors
# This tests both the tuple recursion and the indexing
data = [
    tensor1,
    (tensor2, tensor3),
    tensor2
]

idx = 0

ARGS = {
    "data": data,
    "idx": idx
}
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 list — a list 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
sample_lognormal Ran
ran; our contract draft was wrong, not the code
ringbdstack/dgib/DGIB/util_IB.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
scatter_sample Ran
ran; our contract draft was wrong, not the code
ringbdstack/dgib/DGIB/util_IB.py
code served (permissive licence) · get_code("f7fd106f26391f2e")
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 1, dtype family float, shape (6,) 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
from torch_geometric.utils import degree, softmax, subgraph

torch.manual_seed(0)

# Construct valid arguments for scatter_sample
# src: tensor of probabilities/scores
# index: tensor mapping each element to a node index
# temperature: float controlling the softmax temperature
# num_nodes: optional int for number of nodes

src = torch.rand(6)  # 6 probability values
index = torch.tensor([0, 0, 1, 1, 2, 2])  # map to 3 nodes
temperature = 0.5  # control softness of sampling
num_nodes = 3  # number of target nodes

ARGS = {
    "src": src,
    "index": index,
    "temperature": temperature,
    "num_nodes": num_nodes,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torch_geometric — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (6,) — shape (6,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
to_Boolean Ran
ran; our contract draft was wrong, not the code
ringbdstack/dgib/DGIB/pytorch_net/util.py
code served (permissive licence) · get_code("4f1b3efb75f70e1b")
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 to pass to to_Boolean
# The function will call .bool() or .byte() on it depending on PyTorch version
tensor = torch.randn(2, 4)

ARGS = {
    "tensor": tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
to_Variable_recur Ran
ran; our contract draft was wrong, not the code
ringbdstack/dgib/DGIB/pytorch_net/util.py
code served (permissive licence) · get_code("0c7516590985e454")
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 torch
import numpy as np

torch.manual_seed(0)

# Test with a nested structure containing numpy arrays, dicts, and tuples
test_numpy_array = np.array([[1.5, 2.3, 3.1], [4.2, 5.0, 6.7]])
test_dict = {
    'a': np.array([1.0, 2.0, 3.0, 4.0]),
    'b': np.array([[1, 2], [3, 4]]),
}
test_tuple = (np.array([7, 8, 9, 10]), np.array([11, 12, 13, 14]))
test_nested = {
    'x': (np.array([1.0, 2.0]), np.array([3.0, 4.0])),
    'y': np.array([[5.0, 6.0, 7.0, 8.0]]),
}

ARGS = {
    'item': test_nested,
    'type': 'float',
}
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 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

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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
get_reparam_num_neurons 1 other paper
1 dated earlier
2311.01196 (2023-11)
Combating Bilateral Edge Noise for Robust Link Prediction
recursive_index 1 other paper
1 dated earlier
2401.09323 (2024-01)
BENO: Boundary-embedded Neural Operators for Elliptic PDEs
sample_lognormal 1 other paper
1 dated earlier
2311.01196 (2023-11)
Combating Bilateral Edge Noise for Robust Link Prediction

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

Dynamic Graphs widely exist in the real world, which carry complicated spatial and temporal feature patterns, challenging their representation learning. Dynamic Graph Neural Networks (DGNNs) have shown impressive predictive abilities by exploiting the intrinsic dynamics. However, DGNNs exhibit limited robustness, prone to adversarial attacks. This paper presents the novel Dynamic Graph Information Bottleneck (DGIB) framework to learn robust and discriminative representations. Leveraged by the Information Bottleneck (IB) principle, we first propose the expected optimal representations should satisfy the Minimal-Sufficient-Consensual (MSC) Condition. To compress redundant as well as conserve meritorious information into latent representation, DGIB iteratively directs and refines the structural and feature information flow passing through graph snapshots. To meet the MSC Condition, we decompose the overall IB objectives into DGIB$_{MS}$ and DGIB$_C$, in which the DGIB$_{MS}$ channel aims to learn the minimal and sufficient representations, with the DGIB$_{MS}$ channel guarantees the predictive consensus. Extensive experiments on real-world and synthetic dynamic graph datasets demonstrate the superior robustness of DGIB against adversarial attacks compared with state-of-the-art baselines in the link prediction task. To the best of our knowledge, DGIB is the first work to learn robust representations of dynamic graphs grounded in the information-theoretic IB principle.

For agents

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

get_harvested_code_for_paper("2402.06716")
get_code_for_paper("2402.06716")
have("2402.06716")

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

curl https://syntology.ai/api/ran/2402.06716.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.06716.svg)](https://syntology.ai/paper/2402.06716)

Connect an agent — have() is free.