SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.17341 · NeurIPS · 2024

Generative Modelling of Structurally Constrained Graphs

Pascal Frossard, Manuel Madeira

arXiv · PDF · Open in the Atlas

Code that ran

4 of 7 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 3 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/2406.17341.json · badge: /api/ran/2406.17341.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
manuelmlmadeira/ConStruct canonical (classifier label)
classifier basis: census
4 ran · 3 no recorded run
FunctionStatusWhere it lives
effective_batch_size Ran
ran, honoured the contract we drafted
manuelmlmadeira/ConStruct/ConStruct/datasets/adaptive_loader.py
code served (permissive licence) · get_code("6dcb1a7a685a56a3")
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 math

def effective_batch_size(max_size, reference_batch_size, reference_size=20, sampling=False):
    x = reference_batch_size * (reference_size / max_size) ** 2
    return math.floor(1.8 * x) if sampling else math.floor(x)

ARGS = {
    "max_size": 100,
    "reference_batch_size": 32,
    "reference_size": 20,
    "sampling": False
}
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 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
l2 Ran
ran, honoured the contract we drafted
manuelmlmadeira/ConStruct/ConStruct/analysis/dist_helper.py
pointer only (licence: MIT); the stored copy get_code serves, from lf-wen/hgdm, is pointer only (licence: NONE) · get_code("039fc6561a9516bc")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from lf-wen/hgdm, 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.

load_pickle Ran
ran; our contract draft was wrong, not the code
manuelmlmadeira/ConStruct/ConStruct/datasets/dataset_utils.py
code served (permissive licence) · get_code("70db7c9cbe9e680d")
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 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 file with pickled data
temp_dir = tempfile.mkdtemp()
temp_path = os.path.join(temp_dir, "test.pkl")

# Create some sample data to pickle
sample_data = {
    "key1": "value1",
    "key2": [1, 2, 3],
    "key3": {"nested": "dict"}
}

# Write the pickled data to the temporary file
with open(temp_path, 'wb') as f:
    pickle.dump(sample_data, f)

ARGS = {
    "path": temp_path
}
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 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
setup_wandb Ran
ran; our contract draft was wrong, not the code
manuelmlmadeira/ConStruct/ConStruct/utils.py
code served (permissive licence) · get_code("727a5e6e5f9f6115")
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 DictConfig. 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.

from omegaconf import OmegaConf
import os

class MockConfig:
    def __init__(self):
        self.general = type('obj', (object,), {
            'name': 'test_experiment',
            'wandb': 'offline',
            'local_dir': '/tmp'
        })()
        self.dataset = type('obj', (object,), {
            'name': 'qm9',
            'remove_h': False
        })()

cfg = MockConfig()
cfg_dict = {
    'general': {
        'name': 'test_experiment',
        'wandb': 'offline',
        'local_dir': os.getcwd()
    },
    'dataset': {
        'name': 'qm9',
        'remove_h': False
    }
}

cfg_omega = OmegaConf.create(cfg_dict)

ARGS = {
    'cfg': cfg_omega
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
omegaconf, wandb — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DictConfig — a DictConfig output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DictConfig output the recorded ndim 1 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
masked_softmax Not yet run
unverified (harvested, no recorded run)
manuelmlmadeira/ConStruct/ConStruct/models/layers.py
code served (permissive licence) · get_code("1717b7476aced94e")
How it ran

no invocation recorded.

remove_hydrogens Not yet run
unverified (harvested, no recorded run)
manuelmlmadeira/ConStruct/ConStruct/datasets/dataset_utils.py
code served (permissive licence) · get_code("4b879d076b7285c0")
How it ran

no invocation recorded.

to_dense Not yet run
unverified (harvested, no recorded run)
manuelmlmadeira/ConStruct/ConStruct/utils.py
code served (permissive licence) · get_code("110db6be0f991435")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 2 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
l2 10 other papers
7 dated earlier, 3 later
1910.00760 (2019-10)
Efficient Graph Generation with Graph Recurrent Attention Networks
2204.01613 (2022-04)
SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators
2305.19337 (2023-05)
HiGen: Hierarchical Graph Generative Networks
and 7 more not named here
load_pickle 9 other papers
7 dated earlier, 2 later
1907.00456 (2019-07)
Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog
2005.03545 (2020-05)
MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis
and 6 more not named here
masked_softmax 3 other papers
3 dated earlier
2209.14734 (2022-09)
DiGress: Discrete Denoising diffusion for graph generation
2402.16302 (2024-02)
Graph Diffusion Policy Optimization
2405.11416 (2024-05)
Discrete-state Continuous-time Diffusion for Graph Generation
effective_batch_size 1 other paper
1 dated earlier
2302.09048 (2023-02)
MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

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

Abstract

Graph diffusion models have emerged as state-of-the-art techniques in graph generation; yet, integrating domain knowledge into these models remains challenging. Domain knowledge is particularly important in real-world scenarios, where invalid generated graphs hinder deployment in practical applications. Unconstrained and conditioned graph diffusion models fail to guarantee such domain-specific structural properties. We present ConStruct, a novel framework that enables graph diffusion models to incorporate hard constraints on specific properties, such as planarity or acyclicity. Our approach ensures that the sampled graphs remain within the domain of graphs that satisfy the specified property throughout the entire trajectory in both the forward and reverse processes. This is achieved by introducing an edge-absorbing noise model and a new projector operator. ConStruct demonstrates versatility across several structural and edge-deletion invariant constraints and achieves state-of-the-art performance for both synthetic benchmarks and attributed real-world datasets. For example, by incorporating planarity constraints in digital pathology graph datasets, the proposed method outperforms existing baselines, improving data validity by up to 71.1 percentage points.

For agents

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

get_harvested_code_for_paper("2406.17341")
get_code_for_paper("2406.17341")
have("2406.17341")

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

curl https://syntology.ai/api/ran/2406.17341.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.17341.svg)](https://syntology.ai/paper/2406.17341)

Connect an agent — have() is free.