SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.03689 · 2022

WaveMix: Resource-efficient Token Mixing for Images

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 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; 1 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 0 failures 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/2203.03689.json · badge: /api/ran/2203.03689.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
pranavphoenix/WaveMix canonical (classifier label)
classifier basis not recorded on the link
3 ran · 2 no recorded run
FunctionStatusWhere it lives
mode_to_int Ran
ran, honoured the contract we drafted
pranavphoenix/WaveMix/Image_Classification/WaveMix_Version2.py
pointer only (licence: MIT); the stored copy get_code serves, from fbcotter/pytorch_wavelets, is pointer only (licence: NOASSERTION) · get_code("8ed51e89287a2345")
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 fbcotter/pytorch_wavelets, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

reflect Ran
ran, violated the contract we drafted
pranavphoenix/WaveMix/Image_Classification/WaveMix_Version2.py
code served (permissive licence) · get_code("c18931526ac3006c")
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 ndarray, ndim 1, dtype family float, shape (10,) 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

ARGS = {
    "x": np.array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9], dtype=np.float32),
    "minx": 0.5,
    "maxx": 5.5,
}
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 ndarray, ndim 1, dtype family float, shape (10,) — shape (10,) 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
sfb1d Ran
ran on a synthesized input
pranavphoenix/WaveMix/Image_Classification/WaveMix_Version2.py
code served (permissive licence) · get_code("cbba9f74dd6f7cce")
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 4, dtype family float, shape (2, 3, 4, 8) 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
import torch.nn.functional as F
import numpy as np

torch.manual_seed(0)

# Create small filter kernels for g0 and g1
g0_array = np.array([0.5, 0.5])
g1_array = np.array([0.5, -0.5])

# Create lo and hi tensors
# Shape: (batch=2, channels=3, height=4, width=4) for dim=-1 (width)
# Shape: (batch=2, channels=3, height=8, width=2) for dim=-2 (height)
lo = torch.randn(2, 3, 4, 4)
hi = torch.randn(2, 3, 4, 4)

ARGS = {
    'lo': lo,
    'hi': hi,
    'g0': g0_array,
    'g1': g1_array,
    'mode': 'zero',
    'dim': -1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 3, 4, 8) — shape (2, 3, 4, 8) 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
reflect Not yet run
unverified (harvested, no recorded run)
pranavphoenix/WaveMix/Semantic_Segmentation/WaveMix.py
code served (permissive licence) · get_code("61229493ece46198")
How it ran

no invocation recorded.

sfb1d Not yet run
unverified (harvested, no recorded run)
pranavphoenix/WaveMix/Semantic_Segmentation/WaveMix.py
code served (permissive licence) · get_code("63548ddcf2956599")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 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
reflect 4 other papers
4 later
2311.08819 (2023-11)
Frequency Domain-based Dataset Distillation
2402.19215 (2024-02)
Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts *
2404.11273 (2024-04)
Training Transformer Models by Wavelet Losses Improves Quantitative and Visual Performance in Single Image Super-Resolution
and 1 more not named here
mode_to_int 2 other papers
2 later
2311.08819 (2023-11)
Frequency Domain-based Dataset Distillation
2412.17176 (2024-12)
WPMixer: Efficient Multi-Resolution Mixing for Long-Term Time Series Forecasting

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

Although certain vision transformer (ViT) and CNN architectures generalize well on vision tasks, it is often impractical to use them on green, edge, or desktop computing due to their computational requirements for training and even testing. We present WaveMix as an alternative neural architecture that uses a multi-scale 2D discrete wavelet transform (DWT) for spatial token mixing. Unlike ViTs, WaveMix neither unrolls the image nor requires self-attention of quadratic complexity. Additionally, DWT introduces another inductive bias -- besides convolutional filtering -- to utilize the 2D structure of an image to improve generalization. The multi-scale nature of the DWT also reduces the requirement for a deeper architecture compared to the CNNs, as the latter relies on pooling for partial spatial mixing. WaveMix models show generalization that is competitive with ViTs, CNNs, and token mixers on several datasets while requiring lower GPU RAM (training and testing), number of computations, and storage. WaveMix have achieved State-of-the-art (SOTA) results in EMNIST Byclass and EMNIST Balanced datasets.

For agents

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

get_harvested_code_for_paper("2203.03689")
get_code_for_paper("2203.03689")
have("2203.03689")

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

curl https://syntology.ai/api/ran/2203.03689.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.03689.svg)](https://syntology.ai/paper/2203.03689)

Connect an agent — have() is free.