SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.18858 · 2026

Hyperbolic Busemann Neural Networks

Bernhard Schölkopf, Nicu Sebe, Ziheng Chen

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 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 0 have no contract verdict; 2 failures of our instrument; 2 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/2602.18858.json · badge: /api/ran/2602.18858.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
GitZH-Chen/HBNN canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
GitZH-Chen/HBNN/lib/utils/utils.py
pointer only (licence: NONE) · get_code("c78dcb0bdf203602")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GitZH-Chen/HBNN 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.

insert_docs Ran
ran; our contract draft was wrong, not the code
GitZH-Chen/HBNN/lib/geoopt/docutils.py
pointer only (licence: NONE) · get_code("98350b92a936748b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GitZH-Chen/HBNN 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.

make_tuple Ran
ran, honoured the contract we drafted
GitZH-Chen/HBNN/lib/geoopt/utils.py
pointer only (licence: NONE) · get_code("19896c4283eab1ec")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GitZH-Chen/HBNN 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.

prod Ran
ran, violated the contract we drafted
GitZH-Chen/HBNN/lib/geoopt/utils.py
pointer only (licence: NONE) · get_code("d4e7ce8697742d11")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GitZH-Chen/HBNN 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.

strip_tuple Ran
ran, honoured the contract we drafted
GitZH-Chen/HBNN/lib/geoopt/utils.py
pointer only (licence: NONE) · get_code("47af2deb6b9eac9c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GitZH-Chen/HBNN 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.

visualize_generations Not yet run
unverified (harvested, no recorded run)
GitZH-Chen/HBNN/lib/utils/visualize.py
pointer only (licence: NONE) · get_code("ac52379c03709d45")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GitZH-Chen/HBNN 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.

visualize_reconstructions Not yet run
unverified (harvested, no recorded run)
GitZH-Chen/HBNN/lib/utils/visualize.py
pointer only (licence: NONE) · get_code("f80c9a17cdd21c1a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GitZH-Chen/HBNN 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 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 0 later) and 0 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
make_tuple 4 other papers
4 dated earlier
2106.04941 (2021-06)
Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approach
2303.15919 (2023-03)
Fully Hyperbolic Convolutional Neural Networks for Computer Vision
2507.21648 (2025-07)
Hyperbolic Genome Embeddings
and 1 more not named here
strip_tuple 4 other papers
4 dated earlier
2106.04941 (2021-06)
Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approach
2303.15919 (2023-03)
Fully Hyperbolic Convolutional Neural Networks for Computer Vision
2507.21648 (2025-07)
Hyperbolic Genome Embeddings
and 1 more not named here
accuracy 3 other papers
3 dated earlier
2303.15919 (2023-03)
Fully Hyperbolic Convolutional Neural Networks for Computer Vision
2504.08912 (2025-04)
HyperCore: The Core Framework for Building Hyperbolic Foundation Models with Comprehensive Modules
2507.21648 (2025-07)
Hyperbolic Genome Embeddings
insert_docs 3 other papers
3 dated earlier
2303.15919 (2023-03)
Fully Hyperbolic Convolutional Neural Networks for Computer Vision
2507.21648 (2025-07)
Hyperbolic Genome Embeddings
2601.19849 (2026-01)
HexFormer: Hyperbolic Vision Transformer with Exponential Map Aggregation
prod 3 other papers
3 dated earlier
2303.15919 (2023-03)
Fully Hyperbolic Convolutional Neural Networks for Computer Vision
2507.21648 (2025-07)
Hyperbolic Genome Embeddings
2601.19849 (2026-01)
HexFormer: Hyperbolic Vision Transformer with Exponential Map Aggregation
visualize_generations 2 other papers
2 dated earlier
2303.15919 (2023-03)
Fully Hyperbolic Convolutional Neural Networks for Computer Vision
2507.21648 (2025-07)
Hyperbolic Genome Embeddings
visualize_reconstructions 2 other papers
2 dated earlier
2303.15919 (2023-03)
Fully Hyperbolic Convolutional Neural Networks for Computer Vision
2507.21648 (2025-07)
Hyperbolic Genome Embeddings

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 spaces provide a natural geometry for representing hierarchical and tree-structured data due to their exponential volume growth. To leverage these benefits, neural networks require intrinsic and efficient components that operate directly in hyperbolic space. In this work, we lift two core components of neural networks, Multinomial Logistic Regression (MLR) and Fully Connected (FC) layers, into hyperbolic space via Busemann functions, resulting in Busemann MLR (BMLR) and Busemann FC (BFC) layers with a unified mathematical interpretation. BMLR provides compact parameters, a point-to-horosphere distance interpretation, batch-efficient computation, and a Euclidean limit, while BFC generalizes FC and activation layers with comparable complexity. Experiments on image classification, genome sequence learning, node classification, and link prediction demonstrate improvements in effectiveness and efficiency over prior hyperbolic layers. The code is available at https://github.com/GitZH-Chen/HBNN .

For agents

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

get_harvested_code_for_paper("2602.18858")
get_code_for_paper("2602.18858")
have("2602.18858")

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

curl https://syntology.ai/api/ran/2602.18858.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.18858.svg)](https://syntology.ai/paper/2602.18858)

Connect an agent — have() is free.