SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.04285 · 2022

A Unification Framework for Euclidean and Hyperbolic Graph Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

10 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; 2 honoured the contract we drafted, 1 violated it and 6 have no contract verdict; 1 failure of our instrument; 2 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/2206.04285.json · badge: /api/ran/2206.04285.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
oom-debugger/ijcai23 canonical (classifier label)
classifier basis not recorded on the link
10 ran · 2 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran, honoured the contract we drafted
oom-debugger/ijcai23/GCNII-master/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from TianxiangZhao/GraphSmote, is pointer only (licence: NONE) · get_code("18557871f0c93b3f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from TianxiangZhao/GraphSmote, and GitHub detected no licence in that repository 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.

artanh Ran
ran on a synthesized input
oom-debugger/ijcai23/multirelational-normalized/utils.py
code served (permissive licence) · get_code("bbf43036d0d1be94")
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 Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was 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

torch.manual_seed(0)

# artanh takes a single argument x, which should be a tensor
# The function computes 0.5 * log((1 + x) / (1 - x))
# This requires x to be in the range (-1, 1) to avoid division by zero and log of negative/zero

# Create a small tensor with values strictly between -1 and 1
x = torch.tensor([
    [0.1, 0.2, 0.3, 0.4],
    [0.5, 0.6, -0.2, -0.3]
], dtype=torch.float32)

ARGS = {
    "x": x
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
euclidean_update Ran
ran on a synthesized input
oom-debugger/ijcai23/multirelational-normalized/rsgd.py
code served (permissive licence) · get_code("887d1966dc7d5944")
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 Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was 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

torch.manual_seed(0)

# Create a parameter tensor (p) - needs .data attribute
p = torch.nn.Parameter(torch.randn(2, 4))

# Create a gradient tensor (d_p)
d_p = torch.randn(2, 4)

# Create a learning rate (lr)
lr = 0.01

ARGS = {
    "p": p,
    "d_p": d_p,
    "lr": lr
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
normalize Ran
ran on a synthesized input
oom-debugger/ijcai23/GCNII-master/utils.py
code served (permissive licence) · get_code("ed47211c38204dd5")
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 csr_matrix. 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 numpy as np
import scipy.sparse as sp

# Create a small sparse matrix for testing
# Create a 4x3 sparse matrix with some non-zero values
row = np.array([0, 1, 2, 3, 0, 2])
col = np.array([0, 1, 2, 0, 2, 1])
data = np.array([1.0, 2.0, 3.0, 4.0, 5.0, 6.0])
mx = sp.csr_matrix((data, (row, col)), shape=(4, 3))

ARGS = {
    "mx": mx
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type csr_matrix — a csr_matrix output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a csr_matrix 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
p_exp_map Ran
ran on a synthesized input
oom-debugger/ijcai23/multirelational-normalized/utils.py
code served (permissive licence) · get_code("ef981fc4bad4a22b")
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 Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was 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

torch.manual_seed(0)

# The function p_exp_map takes a tensor v and applies an exponential map operation.
# It computes the norm along the last dimension, clamps it, and scales the input.
# The input v should be a tensor with batch dimensions.

v = torch.randn(2, 4)

ARGS = {
    "v": v
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
p_log_map Ran
ran on a synthesized input
oom-debugger/ijcai23/multirelational-normalized/utils.py
code served (permissive licence) · get_code("3d6121c6b6728621")
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 Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was 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

torch.manual_seed(0)

# Create a small tensor for v
# The function expects v to have a norm computed along dim=-1
# Shape: (batch_size, feature_dim)
v = torch.randn(2, 4)

ARGS = {
    'v': v
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
parse_index_file Ran
ran, honoured the contract we drafted
oom-debugger/ijcai23/GCNII-master/process.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from DSL-Lab/Specformer, is pointer only (licence: GPL-3.0) · get_code("c1d6392f89c5e495")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from DSL-Lab/Specformer, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

poincare_grad Ran
ran on a synthesized input
oom-debugger/ijcai23/multirelational-normalized/rsgd.py
code served (permissive licence) · get_code("9e8a3bc865c35646")
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 Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was 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

torch.manual_seed(0)

# Construct tensors for poincare_grad
# p: parameter tensor - needs to support .data, sum along dim=-1
# d_p: gradient tensor - needs to support element-wise operations and expand_as

p = torch.randn(2, 4, requires_grad=True)
d_p = torch.randn(2, 4)

ARGS = {
    "p": p,
    "d_p": d_p,
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
sample_mask Ran
ran, violated the contract we drafted
oom-debugger/ijcai23/GCNII-master/process.py
code served (permissive licence) · get_code("b32fd748b4bbe3bf")
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 ndarray, ndim 1, dtype family float, shape (5,) as a later run recorded it. The image it ran in was 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 numpy as np

# Analyze the function:
# - idx: used as an index into mask array, should be an integer or array of integers
# - l: used as the length parameter for np.zeros, should be an integer

# Create valid arguments
idx = 2  # Single index into the mask array
l = 5    # Length of the mask array

ARGS = {
    "idx": idx,
    "l": l
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (5,) — shape (5,) 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
sys_normalized_adjacency Ran
ran; our contract draft was wrong, not the code
oom-debugger/ijcai23/GCNII-master/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from tengxiao1/l2p, is pointer only (licence: NONE) · get_code("55d314d6731edc0a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from tengxiao1/l2p, and GitHub detected no licence in that repository 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.

full_load_citation Not yet run
unverified (harvested, no recorded run)
oom-debugger/ijcai23/GCNII-master/process.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from wendongbi/MMGNN, is pointer only (licence: MIT) · get_code("08311aa668365d42")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from wendongbi/MMGNN, and MIT, as GitHub detects it on that repository, is in the permissive set, but a licence decision keeps the body a pointer: its licence file names an outside party, so it may cover vendored code rather than the repository owner's files (recorded as pointer:licence_names_third_party_corporation). 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.

poincare_update Not yet run
unverified (harvested, no recorded run)
oom-debugger/ijcai23/multirelational-normalized/rsgd.py
code served (permissive licence) · get_code("97c4be1bf3b277b5")
How it ran

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 (9 with at least one paper dated earlier, 2 the same month, 5 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
parse_index_file 53 other papers
34 dated earlier, 1 the same month, 15 later, 3 same year, order not determinable · 1 only as an assembly brick
1603.08861 (2016-03)
Revisiting Semi-Supervised Learning with Graph Embeddings
1611.07308 (2016-11)
Variational Graph Auto-Encoders
1710.10568 (2017-10)
Stochastic Training of Graph Convolutional Networks with Variance Reduction
and 50 more not named here
sample_mask 28 other papers
22 dated earlier, 5 later, 1 same year, order not determinable
1603.08861 (2016-03)
Revisiting Semi-Supervised Learning with Graph Embeddings
1710.10568 (2017-10)
Stochastic Training of Graph Convolutional Networks with Variance Reduction
1710.10903 (2017-10)
Graph Attention Networks
and 25 more not named here
accuracy 14 other papers
5 dated earlier, 1 the same month, 8 later
1902.07153 (2019-02)
Simplifying Graph Convolutional Networks
1905.09550 (2019-05)
Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
2002.07128 (2020-02)
Disease State Prediction From Single-Cell Data Using Graph Attention Networks
and 11 more not named here
artanh 1 other paper
1 dated earlier
1905.09791 (2019-05)
Multi-relational Poincaré Graph Embeddings
euclidean_update 1 other paper
1 dated earlier
1905.09791 (2019-05)
Multi-relational Poincaré Graph Embeddings
full_load_citation 1 other paper
1 later
2208.07012 (2022-08)
MM-GNN: Mix-Moment Graph Neural Network towards Modeling Neighborhood Feature Distribution
p_exp_map 1 other paper
1 dated earlier
1905.09791 (2019-05)
Multi-relational Poincaré Graph Embeddings
p_log_map 1 other paper
1 dated earlier
1905.09791 (2019-05)
Multi-relational Poincaré Graph Embeddings
poincare_grad 1 other paper
1 dated earlier
1905.09791 (2019-05)
Multi-relational Poincaré Graph Embeddings
poincare_update 1 other paper
1 dated earlier
1905.09791 (2019-05)
Multi-relational Poincaré Graph Embeddings
sys_normalized_adjacency 1 other paper
1 later
2310.00697 (2023-10)
Learning How to Propagate Messages in Graph Neural Networks

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

Hyperbolic neural networks can effectively capture the inherent hierarchy of graph datasets, and consequently a powerful choice of GNNs. However, they entangle multiple incongruent (gyro-)vector spaces within a layer, which makes them limited in terms of generalization and scalability. In this work, we propose the Poincare disk model as our search space, and apply all approximations on the disk (as if the disk is a tangent space derived from the origin), thus getting rid of all inter-space transformations. Such an approach enables us to propose a hyperbolic normalization layer and to further simplify the entire hyperbolic model to a Euclidean model cascaded with our hyperbolic normalization layer. We applied our proposed nonlinear hyperbolic normalization to the current state-of-the-art homogeneous and multi-relational graph networks. We demonstrate that our model not only leverages the power of Euclidean networks such as interpretability and efficient execution of various model components, but also outperforms both Euclidean and hyperbolic counterparts on various benchmarks. Our code is made publicly available at https://github.com/oom-debugger/ijcai23.

For agents

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

get_harvested_code_for_paper("2206.04285")
get_code_for_paper("2206.04285")
have("2206.04285")

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

curl https://syntology.ai/api/ran/2206.04285.json

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

[![Syntology run record](https://syntology.ai/api/ran/2206.04285.svg)](https://syntology.ai/paper/2206.04285)

Connect an agent — have() is free.