SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.04963 · ICML · 2024

Learning Divergence Fields for Shift-Robust Graph Representations

Qitian Wu, Junchi Yan, Chenxiao Yang, Fan Nie

arXiv · PDF · Open in the Atlas

Code that ran

5 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 3 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/2406.04963.json · badge: /api/ran/2406.04963.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
fannie1208/GLIND canonical (classifier label)
classifier basis: census
5 ran · 3 no recorded run
FunctionStatusWhere it lives
batch_repeat Ran
ran; our contract draft was wrong, not the code
fannie1208/GLIND/observed/difformer.py
pointer only (licence: NONE) · get_code("137fd20bed7ac88a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fannie1208/GLIND 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.

load_fixed_splits Ran
ran; our contract draft was wrong, not the code
fannie1208/GLIND/observed/data_utils.py
pointer only (licence: NONE) · get_code("8af7081a7caceae1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fannie1208/GLIND 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.

rand_splits Ran
ran; our contract draft was wrong, not the code
fannie1208/GLIND/observed/data_utils.py
pointer only (licence: NONE) · get_code("f7d2020636698e09")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fannie1208/GLIND 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.

to_block Ran
ran; our contract draft was wrong, not the code
fannie1208/GLIND/observed/difformer.py
pointer only (licence: NONE) · get_code("02289063bb2416ef")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fannie1208/GLIND 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.

unpack_block Ran
ran; our contract draft was wrong, not the code
fannie1208/GLIND/observed/difformer.py
pointer only (licence: NONE) · get_code("e87d8f83c5841328")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fannie1208/GLIND 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.

even_quantile_labels Not yet run
unverified (harvested, no recorded run)
fannie1208/GLIND/observed/data_utils.py
pointer only (licence: NONE) · get_code("711b5792cfdf73cf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fannie1208/GLIND 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.

load_arxiv_dataset Not yet run
unverified (harvested, no recorded run)
fannie1208/GLIND/observed/dataset.py
pointer only (licence: NONE) · get_code("2cf31b6d1b1db7fc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fannie1208/GLIND 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.

load_twitch_dataset Not yet run
unverified (harvested, no recorded run)
fannie1208/GLIND/observed/dataset.py
pointer only (licence: NONE) · get_code("345bcfffc570655c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fannie1208/GLIND 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 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, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 3 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
even_quantile_labels 5 other papers
4 dated earlier, 1 later
2110.14446 (2021-10)
Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
2310.00800 (2023-10)
GRAPHPATCHER: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation
2402.08907 (2024-02)
Subgraph Pooling: Tackling Negative Transfer on Graphs
and 2 more not named here
load_fixed_splits 2 other papers
1 dated earlier, 1 later
2402.11494 (2024-02)
Graph Out-of-Distribution Generalization via Causal Intervention
2504.13429 (2025-04)
Bounded and Uniform Energy-based Out-of-distribution Detection for Graphs
rand_splits 2 other papers
1 dated earlier, 1 later
2402.11494 (2024-02)
Graph Out-of-Distribution Generalization via Causal Intervention
2504.13429 (2025-04)
Bounded and Uniform Energy-based Out-of-distribution Detection for Graphs
load_arxiv_dataset 1 other paper
1 dated earlier
2402.11494 (2024-02)
Graph Out-of-Distribution Generalization via Causal Intervention

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

Real-world data generation often involves certain geometries (e.g., graphs) that induce instancelevel interdependence. This characteristic makes the generalization of learning models more difficult due to the intricate interdependent patterns that impact data-generative distributions and can vary from training to testing. In this work, we propose a geometric diffusion model with learnable divergence fields for the challenging generalization problem with interdependent data. We generalize the diffusion equation with stochastic diffusivity at each time step, which aims to capture the multi-faceted information flows among interdependent data. Furthermore, we derive a new learning objective through causal inference, which can guide the model to learn generalizable patterns of interdependence that are insensitive across domains. Regarding practical implementation, we introduce three model instantiations that can be considered as the generalized versions of GCN, GAT, and Transformers, respectively, which possess advanced robustness against distribution shifts. We demonstrate their promising efficacy for out-ofdistribution generalization on diverse real-world datasets. Source codes are available at https: //github.com/fannie1208/GLIND.

For agents

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

get_harvested_code_for_paper("2406.04963")
get_code_for_paper("2406.04963")
have("2406.04963")

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

curl https://syntology.ai/api/ran/2406.04963.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.04963.svg)](https://syntology.ai/paper/2406.04963)

Connect an agent — have() is free.