SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.14092 · 2022

Capturing Graphs with Hypo-Elliptic Diffusions

arXiv · PDF · Open in the Atlas

Code that ran

1 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 1 has no contract verdict; 0 failures of our instrument; 2 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/2205.14092.json · badge: /api/ran/2205.14092.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
tgcsaba/graph2tens canonical (classifier label)
classifier basis not recorded on the link
1 ran · 2 no recorded run
FunctionStatusWhere it lives
graph_attn_prob Ran
ran on a synthesized input
tgcsaba/graph2tens/nn_ops/algorithms.py
code served (permissive licence) · get_code("4fe9b89e21b38de9")
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 EagerTensor, ndim 2, dtype family float, shape (6, 1) 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 tensorflow as tf
import numpy as np

# Set seed for reproducibility
tf.random.set_seed(0)

# Define small tensors and parameters for the function

# Non-batch mode: inp is 2D (n_nodes, n_dim)
n_nodes = 5
n_dim = 4
inp = tf.constant(np.random.randn(n_nodes, n_dim), dtype=tf.float64)

# Edge indices for non-batch mode: (source_node, target_node)
n_edges = 6
edge_idx = tf.constant([
    [0, 1],
    [0, 2],
    [1, 2],
    [1, 3],
    [2, 3],
    [3, 4]
], dtype=tf.int64)

# Kernels for src and trg projections
# They should project from n_dim to 1 (attention scores are scalar)
src_kernel = tf.constant(np.random.randn(n_dim, 1), dtype=tf.float64)
trg_kernel = tf.constant(np.random.randn(n_dim, 1), dtype=tf.float64)

# Optional edge features and edge kernel
edge_feat = tf.constant(np.random.randn(n_edges, 3), dtype=tf.float64)
edge_kernel = tf.constant(np.random.randn(3, 1), dtype=tf.float64)

# Dropout rate
dropout = 0.1

# Dtype
dtype = tf.float64

ARGS = {
    "inp": inp,
    "edge_idx": edge_idx,
    "src_kernel": src_kernel,
    "trg_kernel": trg_kernel,
    "edge_feat": edge_feat,
    "edge_kernel": edge_kernel,
    "dropout": dropout,
    "dtype": dtype
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float, shape (6, 1) — shape (6, 1) 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
graph_sig_attn_network Not yet run
unverified (harvested, no recorded run)
tgcsaba/graph2tens/nn_ops/algorithms.py
code served (permissive licence) · get_code("deaa0521dd147817")
How it ran

no invocation recorded.

graph_sig_network Not yet run
unverified (harvested, no recorded run)
tgcsaba/graph2tens/nn_ops/algorithms.py
code served (permissive licence) · get_code("c21ef96cac760d1b")
How it ran

no invocation recorded.

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, 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 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.

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

Convolutional layers within graph neural networks operate by aggregating information about local neighbourhood structures; one common way to encode such substructures is through random walks. The distribution of these random walks evolves according to a diffusion equation defined using the graph Laplacian. We extend this approach by leveraging classic mathematical results about hypo-elliptic diffusions. This results in a novel tensor-valued graph operator, which we call the hypo-elliptic graph Laplacian. We provide theoretical guarantees and efficient low-rank approximation algorithms. In particular, this gives a structured approach to capture long-range dependencies on graphs that is robust to pooling. Besides the attractive theoretical properties, our experiments show that this method competes with graph transformers on datasets requiring long-range reasoning but scales only linearly in the number of edges as opposed to quadratically in nodes.

For agents

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

get_harvested_code_for_paper("2205.14092")
get_code_for_paper("2205.14092")
have("2205.14092")

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

curl https://syntology.ai/api/ran/2205.14092.json

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

[![Syntology run record](https://syntology.ai/api/ran/2205.14092.svg)](https://syntology.ai/paper/2205.14092)

Connect an agent — have() is free.