SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.03134 · 2021

Pseudo-Riemannian Graph Convolutional Networks

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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 3 have no contract verdict; 1 failure of our instrument; 0 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/2106.03134.json · badge: /api/ran/2106.03134.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
xiongbo010/qgcn canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
average_distortion Ran
ran on a synthesized input
xiongbo010/qgcn/models/base_models.py
code served (permissive licence) · get_code("0c9e95d7a496772c")
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 float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

# Create small pairwise distance arrays
# For n=4 points, we have n*(n-1)//2 = 6 pairwise distances
n_pairs = 6

# Graph pairwise distances (e.g., shortest paths on a graph)
g_pdists = np.array([1.0, 2.0, 1.5, 3.0, 2.5, 4.0])

# Manifold pairwise distances (e.g., Euclidean distances in embedding space)
m_pdists = np.array([1.1, 2.1, 1.4, 3.2, 2.6, 3.9])

ARGS = {
    "g_pdists": g_pdists,
    "m_pdists": m_pdists,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
get_dim_act Ran
ran; our contract draft was wrong, not the code
xiongbo010/qgcn/layers/layers.py
pointer only (licence: MIT); the stored copy get_code serves, from ringbdstack/hypdiff, is pointer only (licence: NONE) · get_code("d527d436e4c4c8b0")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ringbdstack/hypdiff, 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.

get_dim_act_curv Ran
ran on a synthesized input
xiongbo010/qgcn/layers/hyp_layers.py
code served (permissive licence) · get_code("93fff6b57b2f74cb")
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 tuple. 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
import torch.nn.functional as F

torch.manual_seed(0)

class Args:
    def __init__(self):
        self.act = 'relu'
        self.num_layers = 3
        self.feat_dim = 16
        self.dim = 32
        self.task = 'nc'
        self.manifold = 'Hyperboloid'
        self.c = None
        self.cuda = -1
        self.device = 'cpu'

ARGS = {'args': Args()}
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 tuple — a tuple output has no array shape of its own; none is 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
mean_average_precision Ran
ran on a synthesized input
xiongbo010/qgcn/models/base_models.py
code served (permissive licence) · get_code("44f4208d3cb09de0")
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 float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 networkx as nx

# Create a small graph with known structure
g = nx.Graph()
g.add_nodes_from([0, 1, 2, 3])
g.add_edges_from([(0, 1), (0, 2), (1, 2), (2, 3)])

# Create a pairwise distance matrix (4x4 for 4 nodes)
# The distances should reflect some ordering where neighbors are closer
m_pdists = np.array([
    [0.0, 0.1, 0.2, 0.9],  # node 0: closest to 1, then 2, then 3
    [0.1, 0.0, 0.15, 0.8], # node 1: closest to 0, then 2, then 3
    [0.2, 0.15, 0.0, 0.3], # node 2: closest to 1, then 0, then 3
    [0.9, 0.8, 0.3, 0.0],  # node 3: closest to 2, then 1, then 0
])

ARGS = {
    "g": g,
    "m_pdists": m_pdists,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
networkx, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 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.

FunctionAlso present inEarliest-datedOthers named
get_dim_act 3 other papers
3 later
2401.15478 (2024-01)
Product Manifold Representations for Learning on Biological Pathways
2405.03188 (2024-05)
Hyperbolic Geometric Latent Diffusion Model for Graph Generation
2505.08157 (2025-05)
Hyperbolic Contrastive Learning with Model-augmentation for Knowledge-aware Recommendation

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

Graph convolutional networks (GCNs) are powerful frameworks for learning embeddings of graph-structured data. GCNs are traditionally studied through the lens of Euclidean geometry. Recent works find that non-Euclidean Riemannian manifolds provide specific inductive biases for embedding hierarchical or spherical data. However, they cannot align well with data of mixed graph topologies. We consider a larger class of pseudo-Riemannian manifolds that generalize hyperboloid and sphere. We develop new geodesic tools that allow for extending neural network operations into geodesically disconnected pseudo-Riemannian manifolds. As a consequence, we derive a pseudo-Riemannian GCN that models data in pseudo-Riemannian manifolds of constant nonzero curvature in the context of graph neural networks. Our method provides a geometric inductive bias that is sufficiently flexible to model mixed heterogeneous topologies like hierarchical graphs with cycles. We demonstrate the representational capabilities of this method by applying it to the tasks of graph reconstruction, node classification and link prediction on a series of standard graphs with mixed topologies. Empirical results demonstrate that our method outperforms Riemannian counterparts when embedding graphs of complex topologies.

For agents

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

get_harvested_code_for_paper("2106.03134")
get_code_for_paper("2106.03134")
have("2106.03134")

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

curl https://syntology.ai/api/ran/2106.03134.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.03134.svg)](https://syntology.ai/paper/2106.03134)

Connect an agent — have() is free.