SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2503.19476 · ICLR · 2025

LogicXGNN: Grounded Logical Rules for Explaining Graph Neural Networks

Ziyu Zhao, Xujie Si, Chuqin Geng, Zhaoyue Wang, Haolin Ye, Yuhe Jiang

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 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 0 have no contract verdict; 6 failures of our instrument; 1 no recorded run), measured 2026-11-21; 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/2503.19476.json · badge: /api/ran/2503.19476.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
allengeng123/LogicXGNN community
Papers with Code archive
6 ran · 1 no recorded run
FunctionStatusWhere it lives
create_expanded_encoding Ran
ran; our contract draft was wrong, not the code
allengeng123/LogicXGNN/grounding.py
pointer only (licence: NONE) · get_code("0fb0f8056142c95e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, allengeng123/LogicXGNN 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.

handle_no_unique_nodes_case Ran
ran; our contract draft was wrong, not the code
allengeng123/LogicXGNN/grounding.py
pointer only (licence: NONE) · get_code("97c2b59861e2f6e1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, allengeng123/LogicXGNN 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.

merge_orbits_by_distance_with_paths Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
allengeng123/LogicXGNN/grounding.py
pointer only (licence: NONE) · get_code("f3b276758079b08a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, allengeng123/LogicXGNN 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.

plot_k_hop_subgraph Ran
ran; our contract draft was wrong, not the code
allengeng123/LogicXGNN/grounding.py
pointer only (licence: NONE) · get_code("97073fdd8279a8e5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, allengeng123/LogicXGNN 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.

predicate_features_z Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
allengeng123/LogicXGNN/grounding.py
pointer only (licence: NONE) · get_code("702455ee1909aa03")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, allengeng123/LogicXGNN 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.

stable_orbits_with_anchor Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
allengeng123/LogicXGNN/grounding.py
pointer only (licence: NONE) · get_code("5c6a2fbe120a6d53")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, allengeng123/LogicXGNN 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.

get_the_rule_iso_z Not yet run
unverified (harvested, no recorded run)
allengeng123/LogicXGNN/grounding.py
pointer only (licence: NONE) · get_code("4140724d77297ee2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, allengeng123/LogicXGNN 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. No invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 7 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 2026-11-21.

Repositories linked to this paper

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

Abstract

Existing rule-based explanations for Graph Neural Networks (GNNs) provide global interpretability but often optimize and assess fidelity in an intermediate, uninterpretable concept space, overlooking grounding quality for end users in the final subgraph explanations. This gap yields explanations that may appear faithful yet be unreliable in practice. To this end, we propose LOGICXGNN, a post-hoc framework that constructs logical rules over reliable predicates explicitly designed to capture the GNN's message-passing structure, thereby ensuring effective grounding. We further introduce data-grounded fidelity (Fid D ), a realistic metric that evaluates explanations in their final-graph form, along with complementary utility metrics such as coverage and validity. Across extensive experiments, LOGICXGNN improves Fid D by over 20% on average relative to state-of-the-art methods while being 10-100× faster. With strong scalability and utility performance, LOGICXGNN produces explanations that are faithful to the model's logic and reliably grounded in observable data. Our code is available at https://github.com/allengeng123/LogicXGNN.

For agents

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

get_harvested_code_for_paper("2503.19476")
get_code_for_paper("2503.19476")
have("2503.19476")

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

curl https://syntology.ai/api/ran/2503.19476.json

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

[![Syntology run record](https://syntology.ai/api/ran/2503.19476.svg)](https://syntology.ai/paper/2503.19476)

Connect an agent — have() is free.