SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.03329 · 2022

Implicit Graphon Neural Representation

arXiv · PDF · Open in the Atlas

Code that ran

9 of 9 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, 1 violated it and 7 have no contract verdict; 0 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/2211.03329.json · badge: /api/ran/2211.03329.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
mishne-lab/ignr canonical (classifier label)
classifier basis not recorded on the link
9 ran · 0 no recorded run
FunctionStatusWhere it lives
cast_tuple Ran
ran, honoured the contract we drafted
mishne-lab/ignr/IGNR/siren_pytorch.py
pointer only (licence: MIT); the stored copy get_code serves, from marccoru/locationencoder, is pointer only (licence: NONE) · get_code("7bd1641f670e602d")
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 marccoru/locationencoder, 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.

dendro_ind Ran
ran on a synthesized input
mishne-lab/ignr/c-IGNR/data.py
code served (permissive licence) · get_code("16d202fe2a4d2688")
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 1, dtype family int, shape (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 numpy as np
from scipy.spatial.distance import squareform
import scipy.cluster.hierarchy as sch

# Create a small valid adjacency matrix
# The function expects a square matrix where:
# - diagonal will be set to 0
# - it gets converted to distance via 1 - adj
# - squareform expects a condensed distance matrix or a square matrix

# Create a 4x4 adjacency matrix with values in [0, 1]
np.random.seed(0)
adj = np.random.rand(4, 4)
# Make it symmetric (required for valid adjacency/similarity matrix)
adj = (adj + adj.T) / 2
# Ensure diagonal is close to 1 (similarity) or will become 0 (distance)
np.fill_diagonal(adj, 1.0)

ARGS = {
    'adj': adj,
    'meth': 'single'
}
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 ndarray, ndim 1, dtype family int, shape (4,) — shape (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
dendro_ind_D Ran
ran on a synthesized input
mishne-lab/ignr/c-IGNR/data.py
code served (permissive licence) · get_code("60d83f72e5b5a606")
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 1, dtype family int, shape (5,) 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
from scipy.spatial.distance import squareform
import scipy.cluster.hierarchy as sch

# Create a small distance matrix
# The function expects a square distance matrix D
# squareform will convert the condensed distance form, so D should be a square matrix
np.random.seed(0)
n_samples = 5
D = np.random.rand(n_samples, n_samples)
# Make it symmetric (valid distance matrix property)
D = (D + D.T) / 2
# Ensure diagonal is zero (distance to self is 0)
np.fill_diagonal(D, 0.0)

ARGS = {
    'D': D,
    'meth': 'single'
}
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 ndarray, ndim 1, dtype family int, shape (5,) — shape (5,) 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
exists Ran
ran, violated the contract we drafted
mishne-lab/ignr/IGNR/siren_pytorch.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
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 ThomasMrY/VCT, 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.

get_emb Ran
ran on a synthesized input
mishne-lab/ignr/c-IGNR/evaluation.py
code served (permissive licence) · get_code("b444e94d464426b5")
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, 8) 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 torch.nn as nn

torch.manual_seed(0)

# Create a minimal model that implements encode method
class MinimalGNNModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 8)
    
    def encode(self, x, edge_index, batch):
        # Simple encoding: just pass through linear layer
        return self.linear(x)
    
    def eval(self):
        super().eval()
        return self

# Create a minimal data object with required attributes
class MinimalData:
    def __init__(self):
        self.x = torch.randn(2, 4)  # 2 nodes, 4 features
        self.edge_index = torch.tensor([[0, 1], [1, 0]], dtype=torch.int64)
        self.batch = torch.tensor([0, 1], dtype=torch.int64)

# Create a minimal args object with required attributes
class Args:
    def __init__(self):
        self.feature = 'attr_real'
        self.device = 'cpu'

# Create the test loader (list of batches)
test_loader = [MinimalData()]

# Create model instance
model = MinimalGNNModel()

# Create args instance
args = Args()

# Define ARGS dict
ARGS = {
    'args': args,
    'model': model,
    'test_loader': test_loader
}
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 ndarray, ndim 2, dtype family float, shape (2, 8) — shape (2, 8) 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
gw_cost Ran
ran on a synthesized input
mishne-lab/ignr/IGNR/helper.py
code served (permissive licence) · get_code("d295f075ab8e6f9c")
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 (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 numpy as np

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

# Define dimensions
n_s = 4  # number of source nodes
n_t = 3  # number of target nodes

# Create cost matrices
cost_s = np.random.rand(n_s, n_s)
cost_t = np.random.rand(n_t, n_t)

# Create probability distributions (node distributions)
p_s = np.random.rand(n_s, 1)
p_s = p_s / p_s.sum()  # normalize to sum to 1

p_t = np.random.rand(n_t, 1)
p_t = p_t / p_t.sum()  # normalize to sum to 1

# Create transport matrix (optimal transport between graphs)
trans = np.random.rand(n_s, n_t)
trans = trans / trans.sum()  # normalize to be a valid transport matrix

ARGS = {
    "cost_s": cost_s,
    "cost_t": cost_t,
    "trans": trans,
    "p_s": p_s,
    "p_t": p_t,
}
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 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
n_community Ran
ran on a synthesized input
mishne-lab/ignr/c-IGNR/data.py
code served (permissive licence) · get_code("30116c4bfed7a89a")
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 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 networkx as nx
import numpy as np

# Set seed for reproducibility
np.random.seed(42)

# Define ARGS with all parameters for n_community function
ARGS = {
    "c_sizes": [5, 4, 3],  # List of community sizes
    "p_inter": 0.01,        # Probability of inter-community edges
    "p_intra": 0.7,         # Probability of intra-community edges
    "flag_perm": False       # Whether to permute the graph
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
networkx, numpy — 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
node_cost_st Ran
ran on a synthesized input
mishne-lab/ignr/IGNR/helper.py
code served (permissive licence) · get_code("ebc0da7c205ad6fc")
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 (3, 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 numpy as np

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

# Create small cost matrices for source and target graphs
n_s = 3  # number of source nodes
n_t = 4  # number of target nodes

# cost_s: (n_s, n_s) symmetric cost matrix for source graph
cost_s = np.array([
    [0.0, 1.5, 2.0],
    [1.5, 0.0, 1.2],
    [2.0, 1.2, 0.0]
], dtype=np.float32)

# cost_t: (n_t, n_t) symmetric cost matrix for target graph
cost_t = np.array([
    [0.0, 0.8, 1.1, 1.5],
    [0.8, 0.0, 0.9, 1.2],
    [1.1, 0.9, 0.0, 1.0],
    [1.5, 1.2, 1.0, 0.0]
], dtype=np.float32)

# p_s: (n_s, 1) probability distribution over source nodes
p_s = np.array([[0.3], [0.4], [0.3]], dtype=np.float32)

# p_t: (n_t, 1) probability distribution over target nodes
p_t = np.array([[0.25], [0.25], [0.25], [0.25]], dtype=np.float32)

ARGS = {
    "cost_s": cost_s,
    "cost_t": cost_t,
    "p_s": p_s,
    "p_t": p_t
}
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 float, shape (3, 4) — shape (3, 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
proximal_ot Ran
ran on a synthesized input
mishne-lab/ignr/IGNR/helper.py
code served (permissive licence) · get_code("692c80456b6b7b60")
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 (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 numpy as np
import copy

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

# Define small dimensions for cost matrix
n1 = 4  # source dimension
n2 = 3  # target dimension

# Create a small cost matrix (n1, n2)
cost = np.random.rand(n1, n2) * 10

# Create source distribution p1 (n1, 1) - must sum to 1
p1 = np.ones((n1, 1)) / n1

# Create target distribution p2 (n2, 1) - must sum to 1
p2 = np.ones((n2, 1)) / n2

# Number of Sinkhorn iterations
iters = 100

# Beta parameter for proximal term weight
beta = 1.0

# Error bound for convergence
error_bound = 1e-10

# Prior transport matrix (optional) - same shape as cost
prior = np.ones((n1, n2)) / (n1 * n2)

ARGS = {
    "cost": cost,
    "p1": p1,
    "p2": p2,
    "iters": iters,
    "beta": beta,
    "error_bound": error_bound,
    "prior": prior
}
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 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

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 2 later) and 7 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
exists 486 other papers
126 dated earlier, 3 the same month, 354 later, 1 same year, order not determinable, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
cast_tuple 8 other papers
3 dated earlier, 5 later · 1 only as an assembly brick
2006.09661 (2020-06)
Implicit Neural Representations with Periodic Activation Functions
2111.00195 (2021-11)
Learning Continuous Representation of Audio for Arbitrary Scale Super Resolution
2210.06823 (2022-10)
Scalable Neural Video Representations with Learnable Positional Features
and 5 more not named here

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

Graphons are general and powerful models for generating graphs of varying size. In this paper, we propose to directly model graphons using neural networks, obtaining Implicit Graphon Neural Representation (IGNR). Existing work in modeling and reconstructing graphons often approximates a target graphon by a fixed resolution piece-wise constant representation. Our IGNR has the benefit that it can represent graphons up to arbitrary resolutions, and enables natural and efficient generation of arbitrary sized graphs with desired structure once the model is learned. Furthermore, we allow the input graph data to be unaligned and have different sizes by leveraging the Gromov-Wasserstein distance. We first demonstrate the effectiveness of our model by showing its superior performance on a graphon learning task. We then propose an extension of IGNR that can be incorporated into an auto-encoder framework, and demonstrate its good performance under a more general setting of graphon learning. We also show that our model is suitable for graph representation learning and graph generation.

For agents

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

get_harvested_code_for_paper("2211.03329")
get_code_for_paper("2211.03329")
have("2211.03329")

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

curl https://syntology.ai/api/ran/2211.03329.json

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

[![Syntology run record](https://syntology.ai/api/ran/2211.03329.svg)](https://syntology.ai/paper/2211.03329)

Connect an agent — have() is free.