SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.00618 · 2026

Multi-Domain Riemannian Graph Gluing for Building Graph Foundation Models

Philip Yu, Li Sun, Zhenhao Huang, Sen Su, Junda Ye, Silei Chen, Lanxu Yang

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 0 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/2603.00618.json · badge: /api/ran/2603.00618.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
RiemannGraph/GraphGlue canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
add_model_config Ran
ran; our contract draft was wrong, not the code
RiemannGraph/GraphGlue/configs/base_config.py
code served (permissive licence) · get_code("a60b0cdaf07f0d72")
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 ArgumentParser. 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 argparse

torch.manual_seed(0)

ARGS = {
    'parser': argparse.ArgumentParser(description='Test parser'),
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ArgumentParser — a ArgumentParser output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ArgumentParser 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
create_logger Ran
ran; our contract draft was wrong, not the code
RiemannGraph/GraphGlue/utils/logger.py
code served (permissive licence) · get_code("54b3fa9192dac555")
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 RootLogger. 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 logging
import time
import tempfile
from pathlib import Path

ARGS = {
    'filepath': str(Path(tempfile.gettempdir()) / 'test_logger.log'),
    'colored': False,
    'debug': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type RootLogger — a RootLogger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a RootLogger 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
get_latest_checkpoint Ran
ran; our contract draft was wrong, not the code
RiemannGraph/GraphGlue/utils/checkpoints.py
code served (permissive licence) · get_code("b28fab669a843f6a")
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 str. 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 tempfile
from pathlib import Path

# Create a temporary directory with some checkpoint files
temp_dir = tempfile.mkdtemp()
checkpoint_dir = Path(temp_dir)

# Create some mock checkpoint files with the expected naming pattern
(checkpoint_dir / "pretrain_epoch_1.pth").touch()
(checkpoint_dir / "pretrain_epoch_5.pth").touch()
(checkpoint_dir / "pretrain_epoch_10.pth").touch()
(checkpoint_dir / "model_best.pth").touch()  # This should be ignored
(checkpoint_dir / "other_file.pth").touch()  # This should be ignored

ARGS = {
    "checkpoint_dir": temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
load_checkpoint Ran
ran, honoured the contract we drafted
RiemannGraph/GraphGlue/utils/checkpoints.py
code served (permissive licence) · get_code("69f4fa03604e713f")
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 int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. 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 torch.nn as nn
import torch.optim as optim
import tempfile
import os

torch.manual_seed(0)

# Create a simple model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Instantiate model
model = SimpleModel()

# Create optimizer
optimizer = optim.SGD(model.parameters(), lr=0.01)

# Create scheduler
scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=1, gamma=0.1)

# Create a checkpoint file
checkpoint_data = {
    'epoch': 5,
    'state_dict': model.state_dict(),
    'optimizer': optimizer.state_dict(),
    'scheduler': scheduler.state_dict(),
    'config': {'lr': 0.01, 'batch_size': 32}
}

# Save checkpoint to a temporary file
with tempfile.NamedTemporaryFile(delete=False, suffix='.pt') as tmp:
    torch.save(checkpoint_data, tmp.name)
    checkpoint_filepath = tmp.name

ARGS = {
    'filepath': checkpoint_filepath,
    'model': model,
    'optimizer': optimizer,
    'scheduler': scheduler,
    'map_location': 'cpu',
    'return_config': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, 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
load_config_from_yaml Ran
ran; our contract draft was wrong, not the code
RiemannGraph/GraphGlue/configs/base_config.py
code served (permissive licence) · get_code("3f8cbab1022bab94")
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 dict. 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 tempfile
import os
import yaml

# Create a temporary YAML config file
temp_dir = tempfile.mkdtemp()
config_filepath = os.path.join(temp_dir, "test_config.yaml")

# Write a valid YAML config file
config_data = {
    "model": "bert",
    "learning_rate": 0.001,
    "batch_size": 32,
    "epochs": 10,
    "layers": [64, 128, 256],
    "use_dropout": True,
    "threshold": 0.5
}

with open(config_filepath, 'w', encoding='utf-8') as f:
    yaml.dump(config_data, f)

ARGS = {
    "filepath": config_filepath
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 5 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

Multi-domain graph pre-training integrates knowledge from diverse domains to enhance performance in the target domains, which is crucial for building graph foundation models. Despite initial success, existing solutions often fall short of answering a fundamental question: how is knowledge integrated or transferred across domains? This theoretical limitation motivates us to rethink the consistency and transferability between model pre-training and domain adaptation. In this paper, we propose a fresh Riemannian geometry perspective, whose core idea is to merge any graph dataset into a unified, smooth Riemannian manifold, enabling a systematic understanding of knowledge integration and transfer. To achieve this, our key contribution is the theoretical establishment of neural manifold gluing, which first characterizes local geometry using an adaptive orthogonal frame and then "glues" the local pieces together into a coherent whole. Building on this theory, we present the GRAPHGLUE framework, which supports batched pre-training with EMA prototyping and provides a transferability measure based on geometric consistence. Extensive experiments demonstrate its superior performance across diverse graph domains. Moreover, we empirically validated GRAPHGLUE's geometric scaling law, showing that larger quantities of datasets improve model transferability by producing a smoother manifold. Codes are available at https://github.com/RiemannGraph/GraphGlue.

For agents

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

get_harvested_code_for_paper("2603.00618")
get_code_for_paper("2603.00618")
have("2603.00618")

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

curl https://syntology.ai/api/ran/2603.00618.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.00618.svg)](https://syntology.ai/paper/2603.00618)

Connect an agent — have() is free.