SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.03633 · 2020

Simplicial Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 3 have no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-21; 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/2010.03633.json · badge: /api/ran/2010.03633.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
stefaniaebli/simplicial_neural_networks canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
assemble Ran
ran on a synthesized input
stefaniaebli/simplicial_neural_networks/scnn/chebyshev.py
code served (permissive licence) · get_code("cdc955f6a378c94e")
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, 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 torch

torch.manual_seed(0)

# K: number of Chebyshev polynomial terms
K = 3

# L: matrix used in matrix multiplications (should be square)
# The function expects L.shape[0] == L.shape[1] == M
M = 4
L = torch.randn(M, M)

# x: input tensor of shape (B, C_in, M)
B = 2
C_in = 3
x = torch.randn(B, C_in, M)

ARGS = {
    "K": K,
    "L": L,
    "x": x,
}
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, 3) — shape (2, 3, 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
coo2tensor Ran
ran on a synthesized input
stefaniaebli/simplicial_neural_networks/scnn/scnn.py
code served (permissive licence) · get_code("f5b07715ddf4e242")
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. 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
import scipy.sparse as sp

torch.manual_seed(0)

# Create a small COO sparse matrix
# The function expects a scipy.sparse COO matrix
rows = np.array([0, 1, 2, 1], dtype=np.int32)
cols = np.array([0, 1, 2, 2], dtype=np.int32)
data = np.array([1.0, 2.0, 3.0, 4.0], dtype=np.float32)

# Construct COO matrix with shape 4x3
A = sp.coo_matrix((data, (rows, cols)), shape=(4, 3))

ARGS = {
    "A": A
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, shape (4, 3) — shape (4, 3) as a later run recorded it
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
normalize Ran
ran on a synthesized input
stefaniaebli/simplicial_neural_networks/scnn/chebyshev.py
code served (permissive licence) · get_code("b19ebdd6550ba3a9")
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 csr_matrix. 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 scipy.sparse as sp
import numpy as np

# Create a small sparse matrix L
# The function expects a square sparse matrix and computes its largest eigenvalue
M = 5
# Create a simple sparse symmetric matrix (required for eigsh)
row = np.array([0, 1, 2, 3, 4, 0, 1, 2, 3])
col = np.array([0, 1, 2, 3, 4, 1, 2, 3, 4])
data = np.array([2.0, 3.0, 2.5, 1.5, 2.0, 1.0, 1.0, 1.0, 0.5])
L = sp.csr_matrix((data, (row, col)), shape=(M, M))

# Ensure it's symmetric for eigsh to work properly
L = L + L.T - sp.diags(L.diagonal())

ARGS = {
    "L": L,
    "half_interval": False
}
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 csr_matrix — a csr_matrix output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a csr_matrix 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 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 2 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
coo2tensor 1 other paper
1 later
2302.02941 (2023-02)
On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology

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 2026-11-21.

Repositories linked to this paper

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

Abstract

We present simplicial neural networks (SNNs), a generalization of graph neural networks to data that live on a class of topological spaces called simplicial complexes. These are natural multi-dimensional extensions of graphs that encode not only pairwise relationships but also higher-order interactions between vertices - allowing us to consider richer data, including vector fields and $n$-fold collaboration networks. We define an appropriate notion of convolution that we leverage to construct the desired convolutional neural networks. We test the SNNs on the task of imputing missing data on coauthorship complexes.

For agents

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

get_harvested_code_for_paper("2010.03633")
get_code_for_paper("2010.03633")
have("2010.03633")

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

curl https://syntology.ai/api/ran/2010.03633.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.03633.svg)](https://syntology.ai/paper/2010.03633)

Connect an agent — have() is free.