SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.12906 · NeurIPS · 2023

Curvature Filtrations for Graph Generative Model Evaluation

Michael Bronstein, Bastian Rieck, Joshua Southern, Jeremy Wayland

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; 0 honoured the contract we drafted, 0 violated it and 6 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/2301.12906.json · badge: /api/ran/2301.12906.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
aidos-lab/CFGGME canonical (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
FunctionStatusWhere it lives
balanced_forman_curvature Ran
ran on a synthesized input
aidos-lab/CFGGME/scott/geometry/measures/forman.py
code served (permissive licence) · get_code("d72691518cef9bc1")
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 float, 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 networkx as nx
import numpy as np

# Create a small test graph
G = nx.DiGraph()
G.add_edges_from([(0, 1), (1, 2), (2, 0), (1, 0)])

# Add weights to edges
for u, v in G.edges():
    G[u][v]['weight'] = np.random.rand()

ARGS = {
    'G': G,
    'weight': 'weight',
    'n_jobs': 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
joblib, 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 1, dtype family float, 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
forman_curvature Ran
ran on a synthesized input
aidos-lab/CFGGME/scott/geometry/measures/forman.py
code served (permissive licence) · get_code("9c5cc047b628463e")
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 float, 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 networkx as nx
import numpy as np

# Create a simple undirected graph for testing
G = nx.Graph()
G.add_edges_from([(0, 1), (1, 2), (2, 0), (1, 3)])

# For weighted case, create a graph with edge and node weights
G_weighted = nx.Graph()
G_weighted.add_edge(0, 1, weight=2.0)
G_weighted.add_edge(1, 2, weight=3.0)
G_weighted.add_edge(2, 0, weight=2.5)
G_weighted.add_edge(1, 3, weight=1.5)

# Add node weights
nx.set_node_attributes(G_weighted, {0: 1.0, 1: 1.5, 2: 1.2, 3: 0.8}, 'weight')

ARGS = {
    'G': G,
    'weight': None,
    'n_jobs': 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
joblib, 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 1, dtype family float, 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
ollivier_ricci_curvature Ran
ran on a synthesized input
aidos-lab/CFGGME/scott/geometry/measures/ollivier.py
code served (permissive licence) · get_code("0cd95603a579a946")
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 float, 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 networkx as nx
import numpy as np

# Create a simple test graph
G = nx.Graph()
G.add_edges_from([(0, 1), (1, 2), (2, 0), (2, 3)])

# Define a custom probability function (optional)
def custom_prob_fn(G, node, node_to_index):
    """Custom probability measure function."""
    values = np.zeros(len(G.nodes))
    degree = G.degree(node)
    if degree > 0:
        for neighbor in G.neighbors(node):
            values[node_to_index[neighbor]] = 1.0 / degree
    else:
        values[node_to_index[node]] = 1.0
    return values

# Define arguments dictionary
ARGS = {
    "G": G,
    "alpha": 0.1,
    "weight": None,
    "prob_fn": None,
    "n_jobs": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
joblib, networkx, numpy, ot — 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 float, 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
prob_rw Ran
ran on a synthesized input
aidos-lab/CFGGME/scott/geometry/measures/ollivier.py
code served (permissive licence) · get_code("f8bbd1f24fb3de13")
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 float, 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 networkx as nx
import numpy as np
import scipy as sp

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

# Create node_to_index mapping
node_to_index = {node: idx for idx, node in enumerate(G.nodes())}

# Select a node from the graph
node = 0

ARGS = {
    "G": G,
    "node": node,
    "node_to_index": node_to_index,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 ndarray, ndim 1, dtype family float, 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
prob_two_hop Ran
ran on a synthesized input
aidos-lab/CFGGME/scott/geometry/measures/ollivier.py
code served (permissive licence) · get_code("fdf8dc2c7d28a85e")
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 float, shape (7,) 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 for testing
G = nx.Graph()
G.add_edges_from([
    (0, 1),
    (1, 2),
    (2, 3),
    (3, 4),
    (0, 5),
    (5, 6)
])

# Create a mapping from nodes to indices
node_to_index = {node: idx for idx, node in enumerate(G.nodes())}

# Define the node we want to compute the probability measure for
node = 0

# Construct the ARGS dictionary
ARGS = {
    'G': G,
    'node': node,
    'node_to_index': node_to_index
}
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 ndarray, ndim 1, dtype family float, shape (7,) — shape (7,) 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
resistance_curvature Ran
ran on a synthesized input
aidos-lab/CFGGME/scott/geometry/measures/resistance.py
code served (permissive licence) · get_code("35a3ec5b92988e33")
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 float, 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 networkx as nx
import numpy as np

# Create a simple test graph
G = nx.Graph()
G.add_edges_from([(0, 1), (1, 2), (2, 3), (3, 0), (1, 3)])

# Add weights to edges for the weighted test case
for u, v in G.edges():
    G[u][v]['weight'] = 1.0

ARGS = {
    'G': G,
    'weight': None,
    'n_jobs': 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
joblib, 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 1, dtype family float, 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

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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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.

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 generative model evaluation necessitates understanding differences between graphs on the distributional level. This entails being able to harness salient attributes of graphs in an efficient manner. Curvature constitutes one such property that has recently proved its utility in characterising graphs. Its expressive properties, stability, and practical utility in model evaluation remain largely unexplored, however. We combine graph curvature descriptors with emerging methods from topological data analysis to obtain robust, expressive descriptors for evaluating graph generative models.

For agents

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

get_harvested_code_for_paper("2301.12906")
get_code_for_paper("2301.12906")
have("2301.12906")

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

curl https://syntology.ai/api/ran/2301.12906.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.12906.svg)](https://syntology.ai/paper/2301.12906)

Connect an agent — have() is free.