SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2608.14636 · 2026

Fractional Optimizers Meet Fractal Activation Functions: An Empirical Study of Multi-Scale Optimization in Neural Networks

Sebastian Raubitzek, Georg Goldenits, Sebastian Schrittwieser, Philip König, Kevin Mallinger

arXiv · PDF

Code that ran

20 of 27 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; 3 honoured the contract we drafted, 5 violated it and 0 have no contract verdict; 12 failures of our instrument; 7 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/2608.14636.json · badge: /api/ran/2608.14636.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
Raubkatz/FractalAndFractional2026 canonical (classifier label)
classifier basis: census
20 ran · 7 no recorded run
FunctionStatusWhere it lives
ackley Ran
ran, violated the contract we drafted
Raubkatz/FractalAndFractional2026/A_05_plot_loss_surfaces.py
pointer only (licence: CC-BY-4.0) · get_code("62a8d70090b66885")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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.

derive_optimizer_seed Ran
ran, honoured the contract we drafted
Raubkatz/FractalAndFractional2026/A_01_himmelblau_loss_surface_optimization.py
pointer only (licence: CC-BY-4.0) · get_code("b3b0467ad01ca309")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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.

eval_fn Ran
ran, honoured the contract we drafted
Raubkatz/FractalAndFractional2026/C_04_plot_fractal_activations.py
pointer only (licence: CC-BY-4.0) · get_code("7e658d9354cd9e4a")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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.

himmelblau Ran
ran, honoured the contract we drafted
Raubkatz/FractalAndFractional2026/A_05_plot_loss_surfaces.py
pointer only (licence: CC-BY-4.0) · get_code("7e37b835a3db06ec")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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.

interpolate Ran
ran, violated the contract we drafted
Raubkatz/FractalAndFractional2026/C_01_plot_koch_curve_depths.py
pointer only (licence: CC-BY-4.0) · get_code("6959a2b4d00bb0b9")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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.

koch_subdivide Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Raubkatz/FractalAndFractional2026/C_01_plot_koch_curve_depths.py
pointer only (licence: CC-BY-4.0) · get_code("0d261f0d3227e28a")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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.

load_json Ran
ran; our contract draft was wrong, not the code
Raubkatz/FractalAndFractional2026/A_03_analyze_himmelblau.py
pointer only (licence: CC-BY-4.0) · get_code("4d82a982fa751f10")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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.

midpoint Ran
ran, violated the contract we drafted
Raubkatz/FractalAndFractional2026/C_02_plot_sierpinski_trianlge_depths.py
pointer only (licence: CC-BY-4.0) · get_code("41448593ed7beb5f")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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.

pointwise_numerical_derivative Ran
ran; our contract draft was wrong, not the code
Raubkatz/FractalAndFractional2026/C_05_plot_fractional_fractal_derivatives.py
pointer only (licence: CC-BY-4.0) · get_code("c47afb8fc536f97f")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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.

rastrigin Ran
ran, violated the contract we drafted
Raubkatz/FractalAndFractional2026/A_05_plot_loss_surfaces.py
pointer only (licence: CC-BY-4.0) · get_code("3885de8f53be5712")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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.

refine_polyline Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Raubkatz/FractalAndFractional2026/C_01_plot_koch_curve_depths.py
pointer only (licence: CC-BY-4.0) · get_code("e2f5f6f0a197db9b")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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.

refine_triangles Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Raubkatz/FractalAndFractional2026/C_02_plot_sierpinski_trianlge_depths.py
pointer only (licence: CC-BY-4.0) · get_code("26f2c6a1cc0658ed")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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.

select_reference_minimum Ran
ran; our contract draft was wrong, not the code
Raubkatz/FractalAndFractional2026/A_01_himmelblau_loss_surface_optimization.py
pointer only (licence: CC-BY-4.0) · get_code("6d1c52fc2c9cbde4")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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.

select_reference_minimum Ran
ran; our contract draft was wrong, not the code
Raubkatz/FractalAndFractional2026/A_02_ackley_loss_surface_optimization.py
pointer only (licence: CC-BY-4.0) · get_code("462d177aabf623d6")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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.

sierpinski_subdivide Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Raubkatz/FractalAndFractional2026/C_02_plot_sierpinski_trianlge_depths.py
pointer only (licence: CC-BY-4.0) · get_code("d11bb702b5fbe28b")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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.

symmetric_ylim Ran
ran, violated the contract we drafted
Raubkatz/FractalAndFractional2026/C_03_plot_fractal_function_depths.py
pointer only (licence: CC-BY-4.0) · get_code("6d930537fa500eb5")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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.

weierstrass_derivative_exact Ran
ran; our contract draft was wrong, not the code
Raubkatz/FractalAndFractional2026/C_05_plot_fractional_fractal_derivatives.py
pointer only (licence: CC-BY-4.0) · get_code("1bef0e8cb892ca9a")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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.

weierstrass_partial_sum Ran
ran; our contract draft was wrong, not the code
Raubkatz/FractalAndFractional2026/C_03_plot_fractal_function_depths.py
pointer only (licence: CC-BY-4.0) · get_code("5c898c742a825109")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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.

weierstrass_partial_sum Ran
ran; our contract draft was wrong, not the code
Raubkatz/FractalAndFractional2026/C_05_plot_fractional_fractal_derivatives.py
pointer only (licence: CC-BY-4.0) · get_code("4cb6dd7c4d29e2bb")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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.

weierstrass_tanh_activation_depth Ran
ran; our contract draft was wrong, not the code
Raubkatz/FractalAndFractional2026/C_03_plot_fractal_function_depths.py
pointer only (licence: CC-BY-4.0) · get_code("5333943926f0b98f")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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.

get_dataset_batch_size Not yet run
unverified (harvested, no recorded run)
Raubkatz/FractalAndFractional2026/B_01_run_nn_classification.py
pointer only (licence: CC-BY-4.0) · get_code("8f40700a592d355a")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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. No invocation recorded.

get_dataset_epochs Not yet run
unverified (harvested, no recorded run)
Raubkatz/FractalAndFractional2026/B_01_run_nn_classification.py
pointer only (licence: CC-BY-4.0) · get_code("e118ab122dcba9cb")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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. No invocation recorded.

get_dataset_hidden_units Not yet run
unverified (harvested, no recorded run)
Raubkatz/FractalAndFractional2026/B_01_run_nn_classification.py
pointer only (licence: CC-BY-4.0) · get_code("48574923a1f978f3")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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. No invocation recorded.

plot_activation_label Not yet run
unverified (harvested, no recorded run)
Raubkatz/FractalAndFractional2026/B_02_analyze_neural_network_experiments.py
pointer only (licence: CC-BY-4.0) · get_code("00ded4eb82606e13")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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. No invocation recorded.

plot_optimizer_label Not yet run
unverified (harvested, no recorded run)
Raubkatz/FractalAndFractional2026/B_02_analyze_neural_network_experiments.py
pointer only (licence: CC-BY-4.0) · get_code("107c8ced23fd328d")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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. No invocation recorded.

plot_optimizer_labels Not yet run
unverified (harvested, no recorded run)
Raubkatz/FractalAndFractional2026/B_02_analyze_neural_network_experiments.py
pointer only (licence: CC-BY-4.0) · get_code("e55a20151612283e")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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. No invocation recorded.

point_inside_domain Not yet run
unverified (harvested, no recorded run)
Raubkatz/FractalAndFractional2026/A_01_himmelblau_loss_surface_optimization.py
pointer only (licence: CC-BY-4.0) · get_code("7b302d8193c60f4c")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, Raubkatz/FractalAndFractional2026, 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. No invocation recorded.

Also present in other papers' code

Of 27 samples lifted from this paper's linked repositories, 27 carry a function identity and 0 do not. Of the 27 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 27 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

Fractional optimization methods and fractal activation functions are two independent directions for improving neural network training. Fractional optimizers extend first-order optimization through fractional derivatives and memory effects, whereas fractal activations introduce multi-scale nonlinear representations based on self-similar Weierstrass-and Blancmange-type functions. Here, we investigate their interaction within a unified experimental framework. We evaluate fractional optimizer families on Ackley and Himmelblau benchmark surfaces, in standard form and with additive Weierstrass-type perturbations, and then in feed-forward neural networks with conventional and fractal activations on ten classification datasets. The comparison includes standard methods, regularization-style optimizers, explicit and adaptive memory-based fractional optimizers, and other representative literature methods. Overall, fractional optimization and fractal activations show useful but selective pairings. Regularization-style fractional scaling performs well with selected fractal activations in network training, while Grünwald-Letnikov memory is most relevant on perturbed surfaces. Adaptive memory improves plain memory substitution in several cases, supporting controlled fractional memory as a promising direction rather than a universal replacement.

For agents

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

get_harvested_code_for_paper("2608.14636")
get_code_for_paper("2608.14636")
have("2608.14636")

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

curl https://syntology.ai/api/ran/2608.14636.json

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

[![Syntology run record](https://syntology.ai/api/ran/2608.14636.svg)](https://syntology.ai/paper/2608.14636)

Connect an agent — have() is free.