SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.09258 · 2026

Generalizing GNNs with Tokenized Mixture of Experts

Jundong Li, Kaize Ding, Chuxu Zhang, Jiazheng Li, Zehong Wang, Qi Yang, Xiaoguang Guo, Shawn Spitzel

arXiv · PDF · Open in the Atlas

Code that ran

11 of 12 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, 2 violated it and 0 have no contract verdict; 8 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2602.09258.json · badge: /api/ran/2602.09258.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
GXG-CS/STEM-GNN canonical (classifier label)
classifier basis: census
11 ran · 1 no recorded run
FunctionStatusWhere it lives
ArxivFSSplitter Ran
ran; our contract draft was wrong, not the code
GXG-CS/STEM-GNN/STEM-GNN/dataset/task_constructor.py
pointer only (licence: NONE) · get_code("5f925b34de0a38cb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GXG-CS/STEM-GNN 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.

CiteSplitter Ran
ran; our contract draft was wrong, not the code
GXG-CS/STEM-GNN/STEM-GNN/dataset/task_constructor.py
pointer only (licence: NONE) · get_code("840cce4bf1e34557")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GXG-CS/STEM-GNN 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.

binary_apr_func Ran
ran; our contract draft was wrong, not the code
GXG-CS/STEM-GNN/STEM-GNN/dataset/data_utils.py
pointer only (licence: NONE) · get_code("352a58f5914509ef")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GXG-CS/STEM-GNN 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.

binary_single_auc_func Ran
ran; our contract draft was wrong, not the code
GXG-CS/STEM-GNN/STEM-GNN/dataset/data_utils.py
pointer only (licence: NONE) · get_code("c06eaa1bc9d830c1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GXG-CS/STEM-GNN 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_multitask_loss Ran
ran; our contract draft was wrong, not the code
GXG-CS/STEM-GNN/STEM-GNN/model/ft_model.py
pointer only (licence: NONE) · get_code("0e93238dcf40f058")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GXG-CS/STEM-GNN 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.

default Ran
ran, violated the contract we drafted
GXG-CS/STEM-GNN/STEM-GNN/model/vq.py
pointer only (licence: NONE); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("60fff7c3c400d7ff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GXG-CS/STEM-GNN 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.

exists Ran
ran, violated the contract we drafted
GXG-CS/STEM-GNN/STEM-GNN/model/vq.py
pointer only (licence: NONE); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GXG-CS/STEM-GNN 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.

filter_unnecessary_attrs Ran
ran; our contract draft was wrong, not the code
GXG-CS/STEM-GNN/STEM-GNN/dataset/process_datasets.py
pointer only (licence: NONE) · get_code("6aa000a9e1b10057")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GXG-CS/STEM-GNN 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.

identity Ran
ran, honoured the contract we drafted
GXG-CS/STEM-GNN/STEM-GNN/model/vq.py
pointer only (licence: NONE) · get_code("f3232418205f7cbd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GXG-CS/STEM-GNN 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.

refine_dataset Ran
ran; our contract draft was wrong, not the code
GXG-CS/STEM-GNN/STEM-GNN/dataset/process_datasets.py
pointer only (licence: NONE) · get_code("58d48991c9718144")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GXG-CS/STEM-GNN 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.

span_node_and_edge_idx Ran
ran; our contract draft was wrong, not the code
GXG-CS/STEM-GNN/STEM-GNN/dataset/process_datasets.py
pointer only (licence: NONE) · get_code("fe5ac93ea96ea352")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GXG-CS/STEM-GNN 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.

flat_auc Not yet run
unverified (harvested, no recorded run)
GXG-CS/STEM-GNN/STEM-GNN/dataset/data_utils.py
pointer only (licence: NONE) · get_code("1ae9c9bd82345553")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GXG-CS/STEM-GNN 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 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 11 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 2 the same month, 3 later) and 1 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
exists 486 other papers
468 dated earlier, 7 the same month, 9 later, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
default 163 other papers
159 dated earlier, 2 the same month, 1 later, 1 undated · 27 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1810.00825 (2018-10)
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
1907.01470 (2019-07)
Augmenting Self-attention with Persistent Memory
and 160 more not named here
identity 21 other papers
19 dated earlier, 1 later, 1 undated · 2 only as an assembly brick
2011.10043 (2020-11)
Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning
2203.08913 (2022-03)
Memorizing Transformers
2302.04761 (2023-02)
Toolformer: Language Models Can Teach Themselves to Use Tools
and 18 more not named here
ArxivFSSplitter 2 other papers
2 dated earlier
2310.00149 (2023-10)
One for All: Towards Training One Graph Model for All Classification Tasks
2411.06070 (2024-11)
GFT: Graph Foundation Model with Transferable Tree Vocabulary
CiteSplitter 2 other papers
2 dated earlier
2310.00149 (2023-10)
One for All: Towards Training One Graph Model for All Classification Tasks
2411.06070 (2024-11)
GFT: Graph Foundation Model with Transferable Tree Vocabulary
binary_apr_func 2 other papers
2 dated earlier
2310.00149 (2023-10)
One for All: Towards Training One Graph Model for All Classification Tasks
2411.06070 (2024-11)
GFT: Graph Foundation Model with Transferable Tree Vocabulary
binary_single_auc_func 2 other papers
2 dated earlier
2310.00149 (2023-10)
One for All: Towards Training One Graph Model for All Classification Tasks
2411.06070 (2024-11)
GFT: Graph Foundation Model with Transferable Tree Vocabulary
flat_auc 2 other papers
2 dated earlier
2310.00149 (2023-10)
One for All: Towards Training One Graph Model for All Classification Tasks
2411.06070 (2024-11)
GFT: Graph Foundation Model with Transferable Tree Vocabulary
filter_unnecessary_attrs 1 other paper
1 dated earlier
2411.06070 (2024-11)
GFT: Graph Foundation Model with Transferable Tree Vocabulary
refine_dataset 1 other paper
1 dated earlier
2411.06070 (2024-11)
GFT: Graph Foundation Model with Transferable Tree Vocabulary
span_node_and_edge_idx 1 other paper
1 dated earlier
2411.06070 (2024-11)
GFT: Graph Foundation Model with Transferable Tree Vocabulary

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

Deployed graph neural networks (GNNs) operate as frozen snapshots, yet must simultaneously fit clean data, generalize under distribution shifts, and remain stable against input perturbations-three goals that are difficult to satisfy at once with a single fixed model. We first show theoretically that a single fixed inference rule can create a stability-generalization tradeoff: making the model insensitive to perturbations can also suppress task-relevant signals needed to fit and generalize. Input-dependent routing-assigning different computation paths to different inputs-can relax this tension, but brings new fragility: distribution shifts may mislead routing decisions, and perturbations can destabilize routing, compounding downstream errors. We formalize these effects through two risk decompositions that separate (i) how well the available paths cover diverse test conditions from how accurately the router selects among them, and (ii) how sensitive each fixed path is from how much routing fluctuation amplifies that sensitivity. Guided by these analyses, we propose STEM-GNN: Stable TokEnized Mixture-of-Experts GNN, a pretrain-then-finetune framework that couples a mixture-of-experts encoder providing diverse computation paths to cover heterogeneous test conditions, a vector-quantized token interface that maps encoder outputs to a discrete codebook to absorb small representation drift induced by input perturbations and routing fluctuations before downstream layers, and a Lipschitz-regularized prediction head that bounds how much the output can amplify residual upstream variation. Across eight node, link, and graph benchmarks, STEM-GNN maintains strong clean performance; on representative node benchmarks, it improves the three-way balance under degree/homophily shifts and feature/edge perturbations. The code and data are available at https://github.com/GXG-CS/STEM-GNN.

For agents

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

get_harvested_code_for_paper("2602.09258")
get_code_for_paper("2602.09258")
have("2602.09258")

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

curl https://syntology.ai/api/ran/2602.09258.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.09258.svg)](https://syntology.ai/paper/2602.09258)

Connect an agent — have() is free.