SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.09677 · NeurIPS · 2022

GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks

Rex Ying, Ce Zhang, Kenza Amara, Zitao Zhang, Zhichao Han, Yinan Shan, Ulrik Brandes, Sebastian Schemm

arXiv · PDF · Open in the Atlas

Code that ran

8 of 8 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; 4 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 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/2206.09677.json · badge: /api/ran/2206.09677.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
graphframex/graphframex canonical (classifier label)
classifier basis: classifier_2025
7 ran · 0 no recorded run
ebay/xfraud canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
apply_edge Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ebay/xfraud/xfraud/run_explainer.py
code served (permissive licence) · get_code("8277286490ed976b")
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) and returned DataFrame. 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 pandas as pd
import numpy as np

# Create a small dataframe with the required columns
df = pd.DataFrame({
    'source': [1, 2, 3, 4],
    'target': [10, 20, 30, 40],
    'label': ['type-A', 'type-B', 'type-A', 'type-C'],
    'propertiesSeed': [1, 0, 0, 1]
})

# Create a dataframe for v with id and propertiesSeed columns
v = pd.DataFrame({
    'id': [1, 2, 3, 4],
    'propertiesSeed': [1, 0, 0, 0]
})

# Create a mapping dictionary for node types
map_node = {
    'A': 'node_type_A',
    'B': 'node_type_B',
    'C': 'node_type_C'
}

ARGS = {
    'df': df,
    'v': v,
    'map_node': map_node
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
avg_scores Ran
ran; our contract draft was wrong, not the code
graphframex/graphframex/code/explain.py
pointer only (licence: NONE) · get_code("d3af88953f877ca1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, graphframex/graphframex 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_avg_max Ran
ran, honoured the contract we drafted
graphframex/graphframex/code/evaluate/mask_utils.py
pointer only (licence: NONE) · get_code("0e47f03afc73a073")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, graphframex/graphframex 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_entropy Ran
ran, honoured the contract we drafted
graphframex/graphframex/code/evaluate/mask_utils.py
pointer only (licence: NONE) · get_code("666c8934355b4dcf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, graphframex/graphframex 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_mask_dir_path Ran
ran; our contract draft was wrong, not the code
graphframex/graphframex/code/explain.py
pointer only (licence: NONE) · get_code("b09babe5c53fc4a9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, graphframex/graphframex 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_mask_properties Ran
ran; our contract draft was wrong, not the code
graphframex/graphframex/code/evaluate/mask_utils.py
pointer only (licence: NONE) · get_code("f976ead5fb746948")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, graphframex/graphframex 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_size Ran
ran, honoured the contract we drafted
graphframex/graphframex/code/evaluate/mask_utils.py
pointer only (licence: NONE) · get_code("219c1b8f1abb611d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, graphframex/graphframex 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_sparsity Ran
ran, honoured the contract we drafted
graphframex/graphframex/code/evaluate/mask_utils.py
pointer only (licence: NONE) · get_code("300eb8be7c13d669")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, graphframex/graphframex 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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 8 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

As one of the most popular machine learning models today, graph neural networks (GNNs) have attracted intense interest recently, and so does their explainability. Unfortunately, today's evaluation frameworks for GNN explainability often rely on few inadequate synthetic datasets, leading to conclusions of limited scope due to a lack of complexity in the problem instances. As GNN models are deployed to more mission-critical applications, we are in dire need for a common evaluation protocol of explainability methods of GNNs. In this paper, we propose, to our best knowledge, the first systematic evaluation framework for GNN explainability GRAPHFRAMEX, considering explainability on three different "user needs". We propose a unique metric, the characterization score, which combines the fidelity measures and classifies explanations based on their quality of being sufficient or necessary. We scope ourselves to node classification tasks and compare the most representative techniques in the field of input-level explainability for GNNs. We found that personalized PageRank has the best performance for synthetic benchmarks, but gradient-based methods outperform for tasks with complex graph structure. However, none dominates the others on all evaluation dimensions and there is always a trade-off. We further apply our evaluation protocol in a case study for frauds explanation on eBay transaction graphs to reflect the production environment.

For agents

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

get_harvested_code_for_paper("2206.09677")
get_code_for_paper("2206.09677")
have("2206.09677")

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

curl https://syntology.ai/api/ran/2206.09677.json

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

[![Syntology run record](https://syntology.ai/api/ran/2206.09677.svg)](https://syntology.ai/paper/2206.09677)

Connect an agent — have() is free.