SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.06558 · NeurIPS · 2023

Convolve and Conquer: Data Comparison with Wiener Filters

Deborah Cruz, George Strong, Oscar Bates, Carlos Cueto, Jiashun Yao, Lluis Guasch

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 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; 2 failures 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/2311.06558.json · badge: /api/ran/2311.06558.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
dpelacani/AWLoss marked official in Papers with Code
Papers with Code archive
5 ran · 0 no recorded run
FunctionStatusWhere it lives
WienerLoss Ran
ran on a synthesized input · constructed an object; no result was computed
dpelacani/AWLoss/wiener_loss/wiener_loss.py
code served (permissive licence) · get_code("670b44a225967864")
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 an instance of its own class, WienerLoss: the run constructed the object and did not call it, so no result was computed. 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

torch.manual_seed(0)

# Define a simple penalty function callable
def simple_penalty_fn(mesh):
    return torch.ones(mesh.shape[:-1])

# Define ARGS dict with all parameters for WienerLoss.__init__
ARGS = {
    'method': 'fft',
    'filter_scale': 2,
    'reduction': 'mean',
    'mode': 'reverse',
    'penalty_function': None,
    'store_filters': False,
    'lmbda': 0.0001,
    'std': 0.0001,
    'clamp_min': None,
    'corr_norm': True,
    'input_shape': (3, 4, 4),
}
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 WienerLoss — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a WienerLoss output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
identity Ran
ran, violated the contract we drafted
dpelacani/AWLoss/wiener_loss/wiener_loss.py
code served (permissive licence) · get_code("0e4da82afd23903a")
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 2, dtype family float, shape (2, 4) 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

torch.manual_seed(0)

# The function accesses mesh[..., -1], so mesh must be a tensor with at least 1 dimension
# It uses torch.zeros_like on that slice, so mesh should be a numeric tensor
# The function returns a tensor of the same shape as mesh[..., -1]

# Create a small mesh tensor with shape (2, 4, 3) so mesh[..., -1] has shape (2, 4)
mesh = torch.randn(2, 4, 3)

# val is a scalar parameter, defaulting to 1
val = 1

ARGS = {
    "mesh": mesh,
    "val": val,
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
multigauss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
dpelacani/AWLoss/wiener_loss/wiener_loss.py
code served (permissive licence) · get_code("6b2e08b05ba8e05a")
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 3, dtype family float, shape (2, 3, 3) 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
from torch.distributions.multivariate_normal import MultivariateNormal

torch.manual_seed(0)

# Parameters for multigauss function
# - mesh: shape (batch, dim, dim, ..., dim) where dim is the dimensionality
# - mean: shape (dim,) - mean vector
# - covmatrix: shape (dim, dim) - covariance matrix

dim = 3
batch_size = 2

# Create mean vector of shape (3,)
mean = torch.randn(dim)

# Create positive definite covariance matrix of shape (3, 3)
# Using A @ A.T ensures positive definiteness
A = torch.randn(dim, dim)
covmatrix = A @ A.T

# Create mesh tensor of shape (batch_size, dim, dim, dim)
# This represents a batch of 2 samples in 3D space
mesh = torch.randn(batch_size, dim, dim, dim)

ARGS = {
    "mesh": mesh,
    "mean": mean,
    "covmatrix": covmatrix,
}
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 Tensor, ndim 3, dtype family float, shape (2, 3, 3) — shape (2, 3, 3) 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
pad_signal Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
dpelacani/AWLoss/wiener_loss/wiener_loss.py
code served (permissive licence) · get_code("893b53a6bfcefdde")
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, 6, 7) 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 as nn
from math import floor

torch.manual_seed(0)

# Create a small 4D tensor: [B=2, C=3, D1=4, D2=5]
x = torch.randn(2, 3, 4, 5)

# Define target shape [B, C, D1, D2] where spatial dims are larger
# This will require padding
shape = [2, 3, 6, 7]

# Padding value
val = 0

ARGS = {
    'x': x,
    'shape': shape,
    'val': val
}
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 Tensor, ndim 4, dtype family float, shape (2, 3, 6, 7) — shape (2, 3, 6, 7) 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
rms Ran
ran, honoured the contract we drafted
dpelacani/AWLoss/wiener_loss/wiener_loss.py
code served (permissive licence) · get_code("563dcaf0ca0ac558")
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 float, ndim 0, dtype family float, shape () 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

torch.manual_seed(0)

# Create a small tensor
x = torch.randn(2, 4)

ARGS = {
    'x': x
}
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 float, ndim 0, dtype family float, shape () — shape () 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

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 5 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 5 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

Quantitative evaluations of differences and/or similarities between data samples define and shape optimisation problems associated with learning data distributions. Current methods to compare data often suffer from limitations in capturing such distributions or lack desirable mathematical properties for optimisation (e.g. smoothness, differentiability, or convexity). In this paper, we introduce a new method to measure (dis)similarities between paired samples inspired by Wiener-filter theory. The convolutional nature of Wiener filters allows us to comprehensively compare data samples in a globally correlated way. We validate our approach in four machine learning applications: data compression, medical imaging imputation, translated classification, and non-parametric generative modelling. Our results demonstrate increased resolution in reconstructed images with better perceptual quality and higher data fidelity, as well as robustness against translations, compared to conventional meansquared-error analogue implementations.

For agents

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

get_harvested_code_for_paper("2311.06558")
get_code_for_paper("2311.06558")
have("2311.06558")

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

curl https://syntology.ai/api/ran/2311.06558.json

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

[![Syntology run record](https://syntology.ai/api/ran/2311.06558.svg)](https://syntology.ai/paper/2311.06558)

Connect an agent — have() is free.