SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.16883 · ICML · 2024

GLAD: Improving Latent Graph Generative Modeling with Simple Quantization

Alexandros Kalousis, Van Nguyen, Yoann Boget, Frantzeska Lavda

arXiv · PDF · Open in the Atlas

Code that ran

7 of 12 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 1 has no contract verdict; 4 failures of our instrument; 5 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2403.16883.json · badge: /api/ran/2403.16883.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
v18nguye/glad canonical (classifier label)
classifier basis: classifier_2025
4 ran · 5 no recorded run
notani/python-glad reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
logsigmoid Ran
ran, honoured the contract we drafted
notani/python-glad/glad.py
pointer only (licence: NONE) · get_code("d098860dfa1b0f92")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, notani/python-glad 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.

NodeEdgeBlock Ran
ran on a synthesized input · constructed an object; no result was computed
v18nguye/glad/src/model/model.py
code served (permissive licence) · get_code("3dbc7263bfe57a8b")
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, NodeEdgeBlock: 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

torch.manual_seed(0)

# Small values for distinct dimensions
batch_size = 2
num_nodes = 3
dx = 4  # node feature dimension
de = 6  # edge feature dimension
dy = 8  # global feature dimension
n_head = 2  # number of attention heads

# Create input tensors
X = torch.randn(batch_size, num_nodes, dx)
E = torch.randn(batch_size, num_nodes, num_nodes, de)
y = torch.randn(batch_size, dy)
node_mask = torch.ones(batch_size, num_nodes)

ARGS = {
    'dx': dx,
    'de': de,
    'dy': dy,
    'n_head': n_head,
}
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 NodeEdgeBlock — 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 NodeEdgeBlock 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
load_data Ran
ran; our contract draft was wrong, not the code
notani/python-glad/glad.py
pointer only (licence: NONE) · get_code("2212ba7b63f46344")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, notani/python-glad 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.

load_dataset Ran
ran; our contract draft was wrong, not the code
v18nguye/glad/data/data_generators.py
code served (permissive licence) · get_code("57dc39b4d123cc5e")
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. 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 pickle
import tempfile
import networkx as nx

# Create a temporary directory for the test
temp_dir = tempfile.mkdtemp()

# Create a small mock graph list
mock_graph_list = [
    nx.Graph([(0, 1), (1, 2)]),
    nx.Graph([(0, 1), (1, 2), (2, 3)])
]

# Write the mock data to a pickle file
test_file_name = 'test_graphs'
test_file_path = os.path.join(temp_dir, test_file_name + '.pkl')
with open(test_file_path, 'wb') as f:
    pickle.dump(mock_graph_list, f)

# Define ARGS dict with all parameters
ARGS = {
    'data_dir': temp_dir,
    'file_name': test_file_name,
    'need_set': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
networkx, numpy, scipy — 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
n_community Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
v18nguye/glad/data/data_generators.py
code served (permissive licence) · get_code("05cc7a74eb054f12")
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 Graph. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import networkx as nx

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

# Define arguments for n_community function
ARGS = {
    "num_communities": 3,
    "max_nodes": 30,
    "p_inter": 0.05
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
networkx, numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Graph — a Graph output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Graph output the recorded ndim 1 and dtype family int 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
pow_tensor Ran
ran; our contract draft was wrong, not the code
v18nguye/glad/src/model/model.py
code served (permissive licence) · get_code("b052f8db069c0168")
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 4, dtype family float, shape (2, 3, 4, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Construct arguments for pow_tensor
# x: a 3D tensor (batch, seq_len, feat_dim)
# cnum: number of iterations

x = torch.randn(2, 4, 4)  # batch=2, seq_len=4, feat_dim=4
cnum = 3

ARGS = {
    "x": x,
    "cnum": cnum,
}
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 4, dtype family float, shape (2, 3, 4, 4) — shape (2, 3, 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
sigmoid Ran
ran, honoured the contract we drafted
notani/python-glad/glad.py
pointer only (licence: NONE) · get_code("6c965eb305670ea0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, notani/python-glad 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.

DriftModel Not yet run
unverified (harvested, no recorded run)
v18nguye/glad/src/model/model.py
code served (permissive licence) · get_code("14881ad433c02715")
How it ran

no invocation recorded.

LatentBridge Not yet run
unverified (harvested, no recorded run)
v18nguye/glad/src/model/model.py
code served (permissive licence) · get_code("e4d8014b68323839")
How it ran

no invocation recorded.

XEyTransformerLayer Not yet run
unverified (harvested, no recorded run)
v18nguye/glad/src/model/model.py
code served (permissive licence) · get_code("d22e6a304e01d4ff")
How it ran

no invocation recorded.

assert_correctly_masked Not yet run
unverified (harvested, no recorded run)
v18nguye/glad/src/model/model.py
code served (permissive licence) · get_code("84daca3054ed0237")
How it ran

no invocation recorded.

gen_graph_list Not yet run
unverified (harvested, no recorded run)
v18nguye/glad/data/data_generators.py
code served (permissive licence) · get_code("08c20dce91a5032a")
How it ran

no invocation recorded. this sample carries JSON test cases instead of a setup block; get_reference_implementation serves them with the level they back.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 later) and 10 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
sigmoid 12 other papers
8 dated earlier, 4 later · 1 only as an assembly brick
1506.02640 (2015-06)
You Only Look Once: Unified, Real-Time Object Detection
1602.01783 (2016-02)
Asynchronous Methods for Deep Reinforcement Learning
2106.12930 (2021-06)
VinDr-SpineXR: A deep learning framework for spinal lesions detection and classification from radiographs
and 9 more not named here
XEyTransformerLayer
brick of this paper's assembly: helper
2 other papers
1 dated earlier, 1 later
2209.14734 (2022-09)
DiGress: Discrete Denoising diffusion for graph generation
2605.07048 (2026-05)
Unlocking High-Fidelity Molecular Generation from Mass Spectra via Dual-Stream Line Graph Diffusion

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

Learning graph generative models over latent spaces has received less attention compared to models that operate on the original data space and has so far demonstrated lacklustre performance. We present GLAD a latent space graph generative model. Unlike most previous latent space graph generative models, GLAD operates on a discrete latent space that preserves to a significant extent the discrete nature of the graph structures making no unnatural assumptions such as latent space continuity. We learn the prior of our discrete latent space by adapting diffusion bridges to its structure. By operating over an appropriately constructed latent space we avoid relying on decompositions that are often used in models that operate in the original data space. We present experiments on a series of graph benchmark datasets that demonstrates GLAD as the first equivariant latent graph generative method achieves competitive performance with the state of the art baselines.

For agents

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

get_harvested_code_for_paper("2403.16883")
get_code_for_paper("2403.16883")
have("2403.16883")

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

curl https://syntology.ai/api/ran/2403.16883.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.16883.svg)](https://syntology.ai/paper/2403.16883)

Connect an agent — have() is free.