SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.03671 · ICML · 2024

PANDA: Expanded Width-Aware Message Passing Beyond Rewiring

Noseong Park, Jeongwhan Choi, Sung-Bae Cho, Hyowon Wi, Sumin Park

arXiv · PDF · Open in the Atlas

Code that ran

7 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; 2 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 4 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/2406.03671.json · badge: /api/ran/2406.03671.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
jeongwhanchoi/panda canonical (classifier label)
classifier basis: census
7 ran · 2 no recorded run
FunctionStatusWhere it lives
add_edge Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jeongwhanchoi/panda/preprocessing/fosr.py
pointer only (licence: MIT); the stored copy get_code serves, from kedar2/FoSR, is pointer only (licence: NONE) · get_code("8253415b0d9f44f0")
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 kedar2/FoSR, 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.

choose_edge_to_add Ran
ran, honoured the contract we drafted
jeongwhanchoi/panda/preprocessing/fosr.py
pointer only (licence: MIT); the stored copy get_code serves, from kedar2/FoSR, is pointer only (licence: NONE) · get_code("063fa9897760a77f")
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 kedar2/FoSR, 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.

compute_degrees Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jeongwhanchoi/panda/preprocessing/fosr.py
pointer only (licence: MIT); the stored copy get_code serves, from kedar2/FoSR, is pointer only (licence: NONE) · get_code("64f9409122eaca34")
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 kedar2/FoSR, 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.

dirichlet_energy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jeongwhanchoi/panda/measure_smoothing.py
code served (permissive licence) · get_code("2aa246a3970f8113")
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 float, ndim 0, dtype family float, 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 numpy as np

# X is a node feature matrix with shape (n_nodes, n_features)
# edge_index is a tuple of two arrays representing edges: (source_nodes, target_nodes)

X = np.array([
    [1.0, 2.0, 3.0, 4.0],
    [5.0, 6.0, 7.0, 8.0]
], dtype=np.float64)

# edge_index: tuple of (source_indices, target_indices)
# Creating a simple graph with 2 nodes and 3 edges
edge_index = (
    np.array([0, 0, 1], dtype=np.int64),
    np.array([1, 1, 0], dtype=np.int64)
)

ARGS = {
    "X": X,
    "edge_index": edge_index
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numba, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, 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
get_adj_matrix Ran
ran, honoured the contract we drafted
jeongwhanchoi/panda/preprocessing/digl.py
code served (permissive licence) · get_code("522df9dc671b43ec")
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 (5, 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 torch
import numpy as np

torch.manual_seed(0)

class SimpleDataset:
    def __init__(self, x, edge_index):
        self.x = x
        self.edge_index = edge_index

# Create a small dataset with 5 nodes
num_nodes = 5
x = torch.randn(num_nodes, 4)  # 5 nodes with 4 features each

# Create edge_index as a 2 x num_edges tensor
# Format: [source_nodes, target_nodes]
edge_index = torch.tensor([
    [0, 1, 2, 3, 4],  # source nodes
    [1, 2, 3, 4, 0]   # target nodes
], dtype=torch.long)

dataset = SimpleDataset(x=x, edge_index=edge_index)

ARGS = {
    "dataset": dataset
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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 (5, 5) — shape (5, 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
get_ppr_matrix Ran
ran, violated the contract we drafted
jeongwhanchoi/panda/preprocessing/digl.py
code served (permissive licence) · get_code("60f2d5a22cd623c3")
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, 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

# Create a small adjacency matrix for a graph with 4 nodes
# Use a simple connected graph structure
adj_matrix = np.array([
    [0, 1, 1, 0],
    [1, 0, 1, 1],
    [1, 1, 0, 1],
    [0, 1, 1, 0]
], dtype=np.float64)

alpha = 0.1

ARGS = {
    "adj_matrix": adj_matrix,
    "alpha": alpha
}
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, 4) — shape (4, 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
load_centrality Ran
ran; our contract draft was wrong, not the code
jeongwhanchoi/panda/preprocessing/panda.py
code served (permissive licence) · get_code("55fec0a00b6ca04c")
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 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 os
import pickle
import tempfile

# Create a temporary file with some pickled data
temp_dir = tempfile.mkdtemp()
temp_filename = os.path.join(temp_dir, "test_centrality.pkl")

# Create some sample data to pickle
sample_data = {
    "centrality_scores": [0.1, 0.2, 0.3, 0.4],
    "node_ids": [0, 1, 2, 3]
}

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

ARGS = {
    "filename": temp_filename
}
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 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
dirichlet_normalized Not yet run
unverified (harvested, no recorded run)
jeongwhanchoi/panda/measure_smoothing.py
code served (permissive licence) · get_code("57e036a3b1857000")
How it ran

no invocation recorded.

get_top_k_matrix Not yet run
unverified (harvested, no recorded run)
jeongwhanchoi/panda/preprocessing/digl.py
code served (permissive licence) · get_code("685534c936bc9f51")
How it ran

no invocation recorded.

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, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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
dirichlet_energy 3 other papers
3 dated earlier
2211.15779 (2022-11)
Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvature
2309.09384 (2023-09)
Mitigating Over-Smoothing and Over-Squashing using Augmentations of Forman-Ricci Curvature
2311.14864 (2023-11)
Effective Structural Encodings via Local Curvature Profiles
dirichlet_normalized 3 other papers
3 dated earlier
2211.15779 (2022-11)
Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvature
2309.09384 (2023-09)
Mitigating Over-Smoothing and Over-Squashing using Augmentations of Forman-Ricci Curvature
2311.14864 (2023-11)
Effective Structural Encodings via Local Curvature Profiles
add_edge 1 other paper
1 dated earlier
2210.11790 (2022-10)
FoSR: First-order spectral rewiring for addressing oversquashing in GNNs
choose_edge_to_add 1 other paper
1 dated earlier
2210.11790 (2022-10)
FoSR: First-order spectral rewiring for addressing oversquashing in GNNs
compute_degrees 1 other paper
1 dated earlier
2210.11790 (2022-10)
FoSR: First-order spectral rewiring for addressing oversquashing in GNNs

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

Recent research in the field of graph neural network (GNN) has identified a critical issue known as "over-squashing," resulting from the bottleneck phenomenon in graph structures, which impedes the propagation of long-range information. Prior works have proposed a variety of graph rewiring concepts that aim at optimizing the spatial or spectral properties of graphs to promote the signal propagation. However, such approaches inevitably deteriorate the original graph topology, which may lead to a distortion of information flow. To address this, we introduce an expanded width-aware (PANDA) message passing, a new message passing paradigm where nodes with high centrality, a potential source of over-squashing, are selectively expanded in width to encapsulate the growing influx of signals from distant nodes. Experimental results show that our method outperforms existing rewiring methods, suggesting that selectively expanding the hidden state of nodes can be a compelling alternative to graph rewiring for addressing the over-squashing.

For agents

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

get_harvested_code_for_paper("2406.03671")
get_code_for_paper("2406.03671")
have("2406.03671")

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

curl https://syntology.ai/api/ran/2406.03671.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.03671.svg)](https://syntology.ai/paper/2406.03671)

Connect an agent — have() is free.