SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.10102 · NeurIPS · 2022

Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging

Luc Van Gool, Radu Timofte, Xin Yuan, Yulun Zhang, Jing Lin, Yuanhao Cai, Haoqian Wang, Henghui Ding

arXiv · PDF · Open in the Atlas

Code that ran

4 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, 0 violated it and 1 has no contract verdict; 3 failures of our instrument; 4 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/2205.10102.json · badge: /api/ran/2205.10102.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
caiyuanhao1998/mst canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
caiyuanhao1998/MST marked official in Papers with Code
Papers with Code archive
1 ran · 4 no recorded run
FunctionStatusWhere it lives
A Ran
ran; our contract draft was wrong, not the code
caiyuanhao1998/mst/real/test_code/architecture/DAUHST.py
code served (permissive licence) · get_code("8cfbf95f63beb478")
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) and returned Tensor, ndim 1, dtype family float, shape (2,) 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

torch.manual_seed(0)

# Analyze the function:
# def A(x, Phi):
#     temp = x * Phi
#     y = torch.sum(temp, 1)
#     return y
#
# The function:
# - Takes x and Phi
# - Multiplies them element-wise: temp = x * Phi
# - Sums along dimension 1: y = torch.sum(temp, 1)
#
# For this to work, x and Phi must be broadcastable.
# The sum along dimension 1 suggests both should have at least 2 dimensions.
# Let's make x shape (batch=2, features=4) and Phi shape (batch=2, features=4)
# so they can be multiplied element-wise and summed along dim 1.

x = torch.randn(2, 4)  # batch_size=2, features=4
Phi = torch.randn(2, 4)  # batch_size=2, features=4

ARGS = {
    "x": x,
    "Phi": Phi,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
einops, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (2,) — shape (2,) 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
At Ran
ran; our contract draft was wrong, not the code
caiyuanhao1998/mst/real/test_code/architecture/DAUHST.py
code served (permissive licence) · get_code("5ea05f5d04570581")
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) and returned Tensor, ndim 4, dtype family float, shape (2, 5, 4, 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
import torch.nn as nn

torch.manual_seed(0)

# Analyze the function:
# At(y, Phi) takes:
# - y: tensor that gets unsqueezed at dim 1, so shape (batch, ...) -> (batch, 1, ...)
# - Phi: tensor with shape[1] accessed, used in repeat and element-wise multiply
# The function does:
# 1. unsqueeze(y, 1) -> adds dimension at position 1
# 2. repeat(1, Phi.shape[1], 1, 1) -> repeats along dimension 1
# 3. element-wise multiply with Phi

# y should be 3D or 4D to make sense with the repeat pattern (1, Phi.shape[1], 1, 1)
# After unsqueeze at dim 1, y becomes 4D: (batch, 1, dim1, dim2)
# repeat(1, Phi.shape[1], 1, 1) makes it: (batch, Phi.shape[1], dim1, dim2)
# Phi should be broadcastable to this shape

# Let's use:
# y: shape (2, 4, 3) - batch=2, spatial dims 4x3
# After unsqueeze(y, 1): (2, 1, 4, 3)
# After repeat(1, Phi.shape[1], 1, 1): (2, Phi.shape[1], 4, 3)
# Phi: shape (2, 5, 4, 3) - batch=2, channels=5, spatial 4x3

y = torch.randn(2, 4, 3)
Phi = torch.randn(2, 5, 4, 3)

ARGS = {
    "y": y,
    "Phi": Phi,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
einops, 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, 5, 4, 3) — shape (2, 5, 4, 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
HyPaNet Ran
ran on a synthesized input
caiyuanhao1998/MST/real/test_code/architecture/DAUHST.py
code served (permissive licence) · get_code("7fa2a6ddba8a14ca")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned tuple. 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

# INIT_ARGS for HyPaNet.__init__
INIT_ARGS = {
    'in_nc': 29,
    'out_nc': 8,
    'channel': 64
}

# ARGS for HyPaNet.forward
# Input tensor shape: (batch_size, in_nc, height, width)
# The network downsamples by 2x, so we need height and width >= 2
ARGS = {
    'x': torch.randn(2, 29, 8, 8)
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
trunc_normal_ Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
caiyuanhao1998/mst/real/test_code/architecture/DAUHST.py
code served (permissive licence) · get_code("505222cf2cc4240f")
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) 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
import math

torch.manual_seed(0)

# Create a small tensor to initialize
tensor = torch.empty(2, 4)

# Define arguments for trunc_normal_
ARGS = {
    'tensor': tensor,
    'mean': 0.0,
    'std': 1.0,
    'a': -2.0,
    'b': 2.0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
einops, 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
DAUHST Not yet run
unverified (harvested, no recorded run)
caiyuanhao1998/MST/real/test_code/architecture/DAUHST.py
code served (permissive licence) · get_code("274c97d4f930b2a5")
How it ran

no invocation recorded.

HSAB Not yet run
unverified (harvested, no recorded run)
caiyuanhao1998/MST/real/test_code/architecture/DAUHST.py
code served (permissive licence) · get_code("ef9d8563a512cf58")
How it ran

no invocation recorded.

HST Not yet run
unverified (harvested, no recorded run)
caiyuanhao1998/MST/real/test_code/architecture/DAUHST.py
code served (permissive licence) · get_code("0f98e488a725ce23")
How it ran

no invocation recorded.

HS_MSA Not yet run
unverified (harvested, no recorded run)
caiyuanhao1998/MST/real/test_code/architecture/DAUHST.py
code served (permissive licence) · get_code("8828cb70d2f4874d")
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, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 2 later) and 6 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
trunc_normal_
brick of this paper's assembly: helper
160 other papers
34 dated earlier, 4 the same month, 121 later, 1 same year, order not determinable · 36 only as an assembly brick
1911.10194 (2019-11)
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
2005.10242 (2020-05)
Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
2007.12911 (2020-07)
Tighter risk certificates for neural networks
and 157 more not named here
At 1 other paper
1 later
04825 (2024 (year only))
Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive Imaging

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

In coded aperture snapshot spectral compressive imaging (CASSI) systems, hyperspectral image (HSI) reconstruction methods are employed to recover the spatialspectral signal from a compressed measurement. Among these algorithms, deep unfolding methods demonstrate promising performance but suffer from two issues. Firstly, they do not estimate the degradation patterns and ill-posedness degree from CASSI to guide the iterative learning. Secondly, they are mainly CNN-based, showing limitations in capturing long-range dependencies. In this paper, we propose a principled Degradation-Aware Unfolding Framework (DAUF) that estimates parameters from the compressed image and physical mask, and then uses these parameters to control each iteration. Moreover, we customize a novel Half-Shuffle Transformer (HST) that simultaneously captures local contents and non-local dependencies. By plugging HST into DAUF, we establish the first Transformer-based deep unfolding method, Degradation-Aware Unfolding Half-Shuffle Transformer (DAUHST), for HSI reconstruction. Experiments show that DAUHST surpasses state-of-the-art methods while requiring cheaper computational and memory costs. Code and models are publicly available at https://github.com/caiyuanhao1998/MST

For agents

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

get_harvested_code_for_paper("2205.10102")
get_code_for_paper("2205.10102")
have("2205.10102")

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

curl https://syntology.ai/api/ran/2205.10102.json

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

[![Syntology run record](https://syntology.ai/api/ran/2205.10102.svg)](https://syntology.ai/paper/2205.10102)

Connect an agent — have() is free.