SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.09953 · ICLR · 2024

Online GNN Evaluation Under Test-time Graph Distribution Shifts

Shirui Pan, Qingsong Wen, Bo Du, Xin Zheng, Dongjin Song

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 1 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2403.09953.json · badge: /api/ran/2403.09953.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
amanda-zheng/lebed canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
FunctionStatusWhere it lives
param_diff Ran
ran; our contract draft was wrong, not the code
amanda-zheng/lebed/LEBED-tempo-arxiv/pretrain-gnn-arxiv.py
code served (permissive licence) · get_code("ca11d25cae87fa03")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned float32, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T02:51:27Z). If your copy returns the same type, ndim and shape 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 torch
import numpy as np

torch.manual_seed(0)

# Create two small parameter tensors with distinct dimensions
param1 = torch.randn(4, 3, dtype=torch.float32)
param2 = torch.randn(4, 3, dtype=torch.float32)

ARGS = {
    "param1": param1,
    "param2": param2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float32, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
Graph_Editer Ran
ran on a synthesized input · constructed an object; no result was computed
amanda-zheng/lebed/LEBED-tempo-arxiv/model.py
code served (permissive licence) · get_code("3dd564c20f38d931")
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, through the batch API) and returned an instance of its own class, Graph_Editer: the run constructed the object and did not call it, so no result was computed. 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 torch
import torch.nn as nn
from torch_geometric.utils import to_dense_adj, dense_to_sparse

torch.manual_seed(0)

# Parameters for Graph_Editer.__init__
K = 3  # number of parameter matrices
n = 4  # number of nodes
device = torch.device('cpu')

# Create edge_index for forward pass
# Small graph with 4 nodes and a few edges
edge_index = torch.tensor([
    [0, 1, 2, 3],
    [1, 2, 3, 0]
], dtype=torch.long)

# Parameters for forward pass
num_sample = 2  # number of samples for multinomial
k = 1  # which of the K matrices to use (must be < K)

ARGS = {
    'K': K,
    'n': n,
    'device': device,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torch_geometric — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Graph_Editer — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Graph_Editer output the recorded ndim 0 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
Model Not yet run
unverified (harvested, no recorded run)
amanda-zheng/lebed/LEBED-tempo-arxiv/model.py
code served (permissive licence) · get_code("3cafbc0876b6edf3")
How it ran

no invocation 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

Evaluating the performance of well-trained GNN models on real-world graphs is a pivotal step for reliable GNN online deployment and serving. Due to a lack of test node labels and unknown potential training-test graph data distribution shifts, conventional model evaluation encounters limitations in calculating performance metrics (e.g., test error) and measuring graph data-level discrepancies, particularly when the training graph used for developing GNNs remains unobserved during test time. In this paper, we study a new research problem, online GNN evaluation, which aims to provide valuable insights into the well-trained GNNs' ability to effectively generalize to real-world unlabeled graphs under the test-time graph distribution shifts. Concretely, we develop an effective LEarning BEhavior Discrepancy score, dubbed LEBED, to estimate the test-time generalization errors of well-trained GNN models. Through a novel GNN re-training strategy with a parameter-free optimality criterion, the proposed LEBED comprehensively integrates learning behavior discrepancies from both node prediction and structure reconstruction perspectives. This enables the effective evaluation of the well-trained GNNs' ability to capture test node semantics and structural representations, making it an expressive metric for estimating the generalization error in online GNN evaluation. Extensive experiments on real-world test graphs under diverse graph distribution shifts could verify the effectiveness of the proposed method, revealing its strong correlation with ground-truth test errors on various well-trained GNN models. 1

For agents

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

get_harvested_code_for_paper("2403.09953")
get_code_for_paper("2403.09953")
have("2403.09953")

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

curl https://syntology.ai/api/ran/2403.09953.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.09953.svg)](https://syntology.ai/paper/2403.09953)

Connect an agent — have() is free.