SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.19638 · 2023

A Unified Framework for U-Net Design and Analysis

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 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; 0 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 5 failures of our instrument; 1 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/2305.19638.json · badge: /api/ran/2305.19638.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
fabianfalck/unet-design canonical (classifier label)
classifier basis: census
7 ran · 1 no recorded run
FunctionStatusWhere it lives
calculate_frechet_distance Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fabianfalck/unet-design/diff_cifar/score/fid.py
pointer only (licence: MIT); the stored copy get_code serves, from liuxiao-guan/iet_agc, is pointer only (licence: WTFPL) · get_code("cd3edab30cfead44")
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 liuxiao-guan/iet_agc, and WTFPL, as GitHub detects it on that repository, 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.

extract Ran
ran; our contract draft was wrong, not the code
fabianfalck/unet-design/diff_cifar/diffusion.py
code served (permissive licence) · get_code("6a78f18d5b2ce056")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (2, 1, 1, 1) 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)

# v: a 1D tensor of coefficients (e.g., timestep-indexed values)
# t: a 1D tensor of timestep indices (batch_size,)
# x_shape: shape of the data tensor (e.g., [batch_size, channels, height, width])

batch_size = 2
num_timesteps = 10
channels = 3
height = 4
width = 5

# v is a 1D tensor with coefficients for each timestep
v = torch.randn(num_timesteps)

# t is a 1D tensor of timestep indices, one per batch element
t = torch.randint(0, num_timesteps, (batch_size,))

# x_shape represents the shape of the data tensor
x_shape = torch.Size([batch_size, channels, height, width])

ARGS = {
    'v': v,
    't': t,
    'x_shape': x_shape
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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, 1, 1, 1) — shape (2, 1, 1, 1) 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
get_inception_score Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fabianfalck/unet-design/diff_cifar/score/inception_score.py
pointer only (licence: MIT); the stored copy get_code serves, from liuxiao-guan/iet_agc, is pointer only (licence: WTFPL) · get_code("9b81ae7906ed29eb")
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 liuxiao-guan/iet_agc, and WTFPL, as GitHub detects it on that repository, 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_dict_from_yaml Ran
ran on a synthesized input
fabianfalck/unet-design/diff_cifar/utils.py
code served (permissive licence) · get_code("155ba6c6fc02802c")
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 dict. 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 tempfile
import os
import yaml

# Create a temporary YAML file with test data
temp_dir = tempfile.mkdtemp()
yaml_file = os.path.join(temp_dir, "test_config.yml")

test_data = {
    "model": "resnet50",
    "batch_size": 32,
    "learning_rate": 0.001,
    "epochs": 100,
    "layers": [64, 128, 256],
    "nested": {
        "param1": "value1",
        "param2": 42
    }
}

with open(yaml_file, 'w') as f:
    yaml.dump(test_data, f)

ARGS = {
    "file_path": yaml_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
sqrt_newton_schulz Ran
ran; our contract draft was wrong, not the code
fabianfalck/unet-design/diff_cifar/score/fid.py
code served (permissive licence) · get_code("2dfa8886e774088c")
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, 4, 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)

# Create a small batch of symmetric positive definite matrices
# Shape: (batch_size, dim, dim)
batch_size = 2
dim = 4

# Create random matrices and make them symmetric positive definite
# by computing A = M^T @ M for random M
M = torch.randn(batch_size, dim, dim)
A = torch.bmm(M.transpose(1, 2), M)

numIters = 3
dtype = None

ARGS = {
    "A": A,
    "numIters": numIters,
    "dtype": dtype,
}
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, 4, 4) — shape (2, 4, 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
str2bool Ran
ran, violated the contract we drafted
fabianfalck/unet-design/diff_cifar/utils.py
code served (permissive licence) · get_code("bc4ded9a701b4d62")
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 bool, 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 argparse

def str2bool(v):
    """
    Source code copied from: https://stackoverflow.com/questions/15008758/parsing-boolean-values-with-argparse
    """
    if isinstance(v, bool):
        return v
    if v.lower() in ('yes', 'true', 't', 'y', '1'):
        return True
    elif v.lower() in ('no', 'false', 'f', 'n', '0'):
        return False
    else:
        raise argparse.ArgumentTypeError('Boolean value expected.')


ARGS = {
    'v': 'true'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, 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
torch_cov Ran
ran; our contract draft was wrong, not the code
fabianfalck/unet-design/diff_cifar/score/fid.py
pointer only (licence: MIT); the stored copy get_code serves, from liuxiao-guan/iet_agc, is pointer only (licence: WTFPL) · get_code("b304af5c4fc5341a")
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 liuxiao-guan/iet_agc, and WTFPL, as GitHub detects it on that repository, 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_inception_and_fid_score Not yet run
unverified (harvested, no recorded run)
fabianfalck/unet-design/diff_cifar/score/both.py
code served (permissive licence) · get_code("ca4fdffd71aabc48")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 7 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 2 the same month, 7 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
str2bool 175 other papers
68 dated earlier, 7 the same month, 97 later, 3 same year, order not determinable · 2 only as an assembly brick
1406.6247 (2014-06)
Recurrent Models of Visual Attention
1603.09382 (2016-03)
Deep Networks with Stochastic Depth
1710.10196 (2017-10)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
and 172 more not named here
extract 12 other papers
2 dated earlier, 1 the same month, 9 later · 3 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2302.01316 (2023-02)
Are Diffusion Models Vulnerable to Membership Inference Attacks?
2305.00562 (2023-05)
Class-Balancing Diffusion Models
and 9 more not named here
torch_cov 12 other papers
7 dated earlier, 5 later
1406.2661 (2014-06)
Generative Adversarial Networks
1811.10597 (2018-11)
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
1912.05270 (2019-12)
MineGAN: effective knowledge transfer from GANs to target domains with few images
and 9 more not named here
sqrt_newton_schulz 5 other papers
5 later
2310.03337 (2023-10)
Denoising Diffusion Step-aware Models
2310.11440 (2023-10)
EvalCrafter: Benchmarking and Evaluating Large Video Generation Models
2405.05846 (2024-05)
An Inversion-based Measure of Memorization for Diffusion Models
and 2 more not named here
calculate_frechet_distance 3 other papers
3 later
2310.03337 (2023-10)
Denoising Diffusion Step-aware Models
2405.05846 (2024-05)
An Inversion-based Measure of Memorization for Diffusion Models
2407.15328 (2024-07)
Iterative Ensemble Training with Anti-Gradient Control for Mitigating Memorization in Diffusion Models
get_inception_and_fid_score 3 other papers
3 later
2310.03337 (2023-10)
Denoising Diffusion Step-aware Models
2405.05846 (2024-05)
An Inversion-based Measure of Memorization for Diffusion Models
2407.15328 (2024-07)
Iterative Ensemble Training with Anti-Gradient Control for Mitigating Memorization in Diffusion Models
get_inception_score 3 other papers
3 later
2310.03337 (2023-10)
Denoising Diffusion Step-aware Models
2405.05846 (2024-05)
An Inversion-based Measure of Memorization for Diffusion Models
2407.15328 (2024-07)
Iterative Ensemble Training with Anti-Gradient Control for Mitigating Memorization in Diffusion Models

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

U-Nets are a go-to, state-of-the-art neural architecture across numerous tasks for continuous signals on a square such as images and Partial Differential Equations (PDE), however their design and architecture is understudied. In this paper, we provide a framework for designing and analysing general U-Net architectures. We present theoretical results which characterise the role of the encoder and decoder in a U-Net, their high-resolution scaling limits and their conjugacy to ResNets via preconditioning. We propose Multi-ResNets, U-Nets with a simplified, wavelet-based encoder without learnable parameters. Further, we show how to design novel U-Net architectures which encode function constraints, natural bases, or the geometry of the data. In diffusion models, our framework enables us to identify that high-frequency information is dominated by noise exponentially faster, and show how U-Nets with average pooling exploit this. In our experiments, we demonstrate how Multi-ResNets achieve competitive and often superior performance compared to classical U-Nets in image segmentation, PDE surrogate modelling, and generative modelling with diffusion models. Our U-Net framework paves the way to study the theoretical properties of U-Nets and design natural, scalable neural architectures for a multitude of problems beyond the square.

For agents

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

get_harvested_code_for_paper("2305.19638")
get_code_for_paper("2305.19638")
have("2305.19638")

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

curl https://syntology.ai/api/ran/2305.19638.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.19638.svg)](https://syntology.ai/paper/2305.19638)

Connect an agent — have() is free.