SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.06688 · 2020

End-to-End Variational Networks for Accelerated MRI Reconstruction

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; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 1 failure 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/2004.06688.json · badge: /api/ran/2004.06688.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
facebookresearch/fastMRI canonical (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
MathFLDS/MRAugment community (classifier label)
classifier basis not recorded on the link
3 ran · 1 no recorded run
FunctionStatusWhere it lives
crop_if_needed Ran
ran on a synthesized input
MathFLDS/MRAugment/mraugment/helpers.py
code served (permissive licence) · get_code("8ed423f79785e1fb")
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, 4, 6, 5) 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 takes an image tensor and crops it to a maximum shape
# im: a tensor with shape [..., height, width]
# max_shape: a tuple/list of length 2 specifying (max_height, max_width)

# Create a sample image tensor with shape (batch=2, channels=4, height=10, width=8)
im = torch.randn(2, 4, 10, 8)

# Create max_shape as a tuple of length 2
max_shape = (6, 5)

ARGS = {
    "im": im,
    "max_shape": max_shape,
}
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, 4, 6, 5) — shape (2, 4, 6, 5) 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
load_args_from_config Ran
ran; our contract draft was wrong, not the code
MathFLDS/MRAugment/mraugment_examples/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from ChongWang1024/PDAC, is pointer only (licence: NONE) · get_code("1b315f2b67a89eab")
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 ChongWang1024/PDAC, and GitHub detected no licence in that repository 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.

to_repeated_list Ran
ran on a synthesized input
MathFLDS/MRAugment/mraugment/helpers.py
code served (permissive licence) · get_code("9442ed4fdccf362f")
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 list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 numpy as np

torch.manual_seed(0)

# Test case 1: list input
list_input = [1, 2, 3]

# Test case 2: tuple input
tuple_input = (4, 5, 6)

# Test case 3: scalar input that will be repeated
scalar_input = 42

# The function takes two parameters: 'a' and 'length'
# 'a' can be a list, tuple, or scalar
# 'length' is used to repeat 'a' if it's not a list or tuple

ARGS = {
    "a": scalar_input,
    "length": 5
}
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 list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
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
create_mask_for_mask_type Not yet run
unverified (harvested, no recorded run)
facebookresearch/fastMRI/fastmri/data/subsample.py
code served (permissive licence) · get_code("5ebb28570c9d2d27")
How it ran

no invocation recorded.

pad_if_needed Not yet run
unverified (harvested, no recorded run)
MathFLDS/MRAugment/mraugment/helpers.py
code served (permissive licence) · get_code("4ffc7705d7166286")
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 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 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.

FunctionAlso present inEarliest-datedOthers named
load_args_from_config 2 other papers
2 later
2203.08213 (2022-03)
HUMUS-Net: Hybrid unrolled multi-scale network architecture for accelerated MRI reconstruction
2403.10064 (2024-03)
Progressive Divide-and-Conquer via Subsampling Decomposition for Accelerated MRI

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

The slow acquisition speed of magnetic resonance imaging (MRI) has led to the development of two complementary methods: acquiring multiple views of the anatomy simultaneously (parallel imaging) and acquiring fewer samples than necessary for traditional signal processing methods (compressed sensing). While the combination of these methods has the potential to allow much faster scan times, reconstruction from such undersampled multi-coil data has remained an open problem. In this paper, we present a new approach to this problem that extends previously proposed variational methods by learning fully end-to-end. Our method obtains new state-of-the-art results on the fastMRI dataset for both brain and knee MRIs.

For agents

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

get_harvested_code_for_paper("2004.06688")
get_code_for_paper("2004.06688")
have("2004.06688")

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

curl https://syntology.ai/api/ran/2004.06688.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.06688.svg)](https://syntology.ai/paper/2004.06688)

Connect an agent — have() is free.