SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2503.09008 · ICLR · 2025

Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurement

Michael Bronstein, Xiaowen Dong, Huidong Liang, Haitz Sáez De Ocáriz Borde, Baskaran Sripathmanathan

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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 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/2503.09008.json · badge: /api/ran/2503.09008.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
leonresearch/city-networks canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
jacobian_l1 Ran
ran, honoured the contract we drafted
leonresearch/city-networks/influence/influence.py
pointer only (licence: NONE) · get_code("3fcb47df1cd821d3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, leonresearch/city-networks 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.

k_hop_subsets_exact Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
leonresearch/city-networks/influence/influence.py
pointer only (licence: NONE) · get_code("c7329955ef54debb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, leonresearch/city-networks 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.

k_hop_subsets_rough Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
leonresearch/city-networks/influence/influence.py
pointer only (licence: NONE) · get_code("d69d53cccdbbd6ad")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, leonresearch/city-networks 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.

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

Long-range dependencies are critical for effective graph representation learning, yet most existing datasets focus on small graphs tailored to inductive tasks, offering limited insight into long-range interactions. Current evaluations primarily compare models employing global attention (e.g., graph transformers) with those using local neighborhood aggregation (e.g., message-passing neural networks) without a direct measurement of long-range dependency. In this work, we introduce City-Networks, a novel large-scale transductive learning dataset derived from real-world city road networks. This dataset features graphs with over 10 5 nodes and significantly larger diameters than those in existing benchmarks, naturally embodying long-range information. We annotate the graphs based on local node eccentricities, ensuring that the classification task inherently requires information from distant nodes. Furthermore, we propose a generic measurement based on the Jacobians of neighbors from distant hops, offering a principled quantification of long-range dependencies. Finally, we provide theoretical justifications for both our dataset design and the proposed measurement-particularly by focusing on over-smoothing and influence score dilution, which establishes a robust foundation for further exploration of long-range interactions in graph neural networks. Our dataset and measurement are available on PyTorch Geometric, and the code for reproducing the experimental results can be found at github.com/LeonResearch/City-Networks.

For agents

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

get_harvested_code_for_paper("2503.09008")
get_code_for_paper("2503.09008")
have("2503.09008")

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

curl https://syntology.ai/api/ran/2503.09008.json

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

[![Syntology run record](https://syntology.ai/api/ran/2503.09008.svg)](https://syntology.ai/paper/2503.09008)

Connect an agent — have() is free.