SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.15634 · ICML · 2026

Beyond ReLU: Bifurcation, Oversmoothing, and Topological Priors

Maks Ovsjanikov, Erkan Turan, Gaspard Abel, Maysam Behmanesh, Emery Pierson

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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 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/2602.15634.json · badge: /api/ran/2602.15634.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
maysambehmanesh/relu-bifurcation canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
build_A_norm_sparse Ran
ran; our contract draft was wrong, not the code
maysambehmanesh/relu-bifurcation/utils.py
pointer only (licence: NONE) · get_code("dc6972cd5c2f3d88")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, maysambehmanesh/relu-bifurcation 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.

create_split Ran
ran; our contract draft was wrong, not the code
maysambehmanesh/relu-bifurcation/load_data.py
pointer only (licence: NONE) · get_code("5dd887660420e715")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, maysambehmanesh/relu-bifurcation 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.

top_eigvec_power Ran
ran, honoured the contract we drafted
maysambehmanesh/relu-bifurcation/utils.py
pointer only (licence: NONE) · get_code("e4e406cd130b6f09")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, maysambehmanesh/relu-bifurcation 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.

train_epoch Ran
ran, honoured the contract we drafted
maysambehmanesh/relu-bifurcation/utils.py
pointer only (licence: NONE) · get_code("94c92414bc4e8e5f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, maysambehmanesh/relu-bifurcation 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.

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, 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 4 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

Graph Neural Networks (GNNs) learn node representations through iterative network-based message-passing. While powerful, deep GNNs suffer from oversmoothing, where node features converge to a homogeneous, non-informative state. We re-frame this problem of representational collapse from a bifurcation theory perspective, characterizing oversmoothing as convergence to a stable "homogeneous fixed point." Our central contribution is the theoretical discovery that this undesired stability can be broken by replacing standard monotone activations (e.g., ReLU) with a class of functions. Using Lyapunov-Schmidt reduction, we analytically prove that this substitution induces a bifurcation that destabilizes the homogeneous state and creates a new pair of stable, non-homogeneous patterns that provably resist oversmoothing. Our theory predicts a precise, nontrivial scaling law for the amplitude of these emergent patterns, which we quantitatively validate in experiments. Finally, we demonstrate the practical utility of our theory by deriving a closed-form, bifurcation-aware initialization and showing its utility in real benchmark experiments.

For agents

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

get_harvested_code_for_paper("2602.15634")
get_code_for_paper("2602.15634")
have("2602.15634")

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

curl https://syntology.ai/api/ran/2602.15634.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.15634.svg)](https://syntology.ai/paper/2602.15634)

Connect an agent — have() is free.