SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.08463 · ICCV · 2023

Learning to Distill Global Representation for Sparse-View CT

Jie Chen, Zilong Li, Junping Zhang, Hongming Shan, Chenglong Ma

arXiv · PDF · Open in the Atlas

Code that ran

5 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 3 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/2308.08463.json · badge: /api/ran/2308.08463.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
longzilicart/GloReDi canonical (classifier label)
classifier basis: census
5 ran · 3 no recorded run
FunctionStatusWhere it lives
dct_normalize_torch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
longzilicart/GloReDi/src/Basic_Freq_Module/Freq_norm.py
code served (permissive licence) · get_code("b653e84143fd1281")
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)

# Create a small tensor with real values for DCT results
# Using shape (2, 4) as a small example
dct_results = torch.randn(2, 4, dtype=torch.float32)

# Test with different methods
ARGS = {
    'dct_results': dct_results,
    'method': 'min-max'
}
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
fft_normalize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
longzilicart/GloReDi/src/Basic_Freq_Module/Freq_norm.py
code served (permissive licence) · get_code("bd08491eac4cee3e")
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)

# Create a small complex tensor to represent FFT results
# Shape: (2, 4) - batch size 2, 4 frequency components
fft_results = torch.randn(2, 4, dtype=torch.complex64)

ARGS = {
    'fft_results': fft_results,
    'method': 'magnitude'
}
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
get_grid_from_dict Ran
ran, honoured the contract we drafted
longzilicart/GloReDi/src/Logger/longzili_logger.py
code served (permissive licence) · get_code("d9dbdebef9623138")
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, 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 torch

torch.manual_seed(0)

# Create a dictionary of tensors with shape (N, C, H, W)
# N=2 (batch), C=4 (channels), H=3 (height), W=5 (width)
plot_dict = {
    "tensor_1": torch.randn(2, 4, 3, 5),
    "tensor_2": torch.randn(2, 4, 3, 5),
    "tensor_3": torch.randn(2, 4, 3, 5),
    "tensor_4": torch.randn(2, 4, 3, 5),
}

ARGS = {
    "plot_dict": plot_dict,
    "n_rows": 2,
    "n_cols": 0,
}
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, 10) — shape (2, 4, 6, 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
get_grid_from_list Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
longzilicart/GloReDi/src/Logger/longzili_logger.py
code served (permissive licence) · get_code("6063d14af4cc1cd2")
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, 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 torch

torch.manual_seed(0)

# Create a list of tensors with shape (N, C, H, W)
# N=2 (batch), C=4 (channels), H=3 (height), W=5 (width)
tensor1 = torch.randn(2, 4, 3, 5)
tensor2 = torch.randn(2, 4, 3, 5)
tensor3 = torch.randn(2, 4, 3, 5)
tensor4 = torch.randn(2, 4, 3, 5)

plot_list = [tensor1, tensor2, tensor3, tensor4]

ARGS = {
    "plot_list": plot_list,
    "n_rows": 2,
    "n_cols": 0
}
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, 10) — shape (2, 4, 6, 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
only_on_rank0 Ran
ran; our contract draft was wrong, not the code
longzilicart/GloReDi/src/Logger/longzili_logger.py
code served (permissive licence) · get_code("e53b1fbdf8c4bfd2")
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 function. 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

# Define a minimal class that has a rank attribute
class MockLogger:
    def __init__(self, rank):
        self.rank = rank
    
    def log_message(self, msg):
        return f"Logged: {msg}"

# Define the decorator
def only_on_rank0(func):
    """wrapper for only log on the first rank"""
    def wrapper(self, *args, **kwargs):
        if self.rank != 0:
            return
        return func(self, *args, **kwargs)
    return wrapper

# Create an instance with rank 0
mock_logger_rank0 = MockLogger(rank=0)

# Create a test function that uses the decorator
@only_on_rank0
def test_function(self, message):
    return self.log_message(message)

# Bind the decorated function to the mock logger instance
decorated_method = test_function.__get__(mock_logger_rank0, MockLogger)

ARGS = {
    "func": test_function,
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
dct Not yet run
unverified (harvested, no recorded run)
longzilicart/GloReDi/src/Basic_Freq_Module/torch_dct.py
code served (permissive licence) · get_code("2722de6c59374643")
How it ran

no invocation recorded.

dct1 Not yet run
unverified (harvested, no recorded run)
longzilicart/GloReDi/src/Basic_Freq_Module/torch_dct.py
pointer only (licence: MIT); the stored copy get_code serves, from yuyi-sd/baiqa, is pointer only (licence: NONE) · get_code("c3f2ecb9e39faba4")
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 yuyi-sd/baiqa, 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. No invocation recorded.

idct1 Not yet run
unverified (harvested, no recorded run)
longzilicart/GloReDi/src/Basic_Freq_Module/torch_dct.py
pointer only (licence: MIT); the stored copy get_code serves, from yuyi-sd/baiqa, is pointer only (licence: NONE) · get_code("e2f1e6b54f8342d0")
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 yuyi-sd/baiqa, 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. 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, 6 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 5 later) and 2 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
idct1 10 other papers
4 dated earlier, 6 later
2011.04823 (2020-11)
Language Through a Prism: A Spectral Approach for Multiscale Language Representations
2105.08997 (2021-05)
When Deep Classifiers Agree: Analyzing Correlations between Learning Order and Image Statistics
2209.11888 (2022-09)
JPEG Artifact Correction using Denoising Diffusion Restoration Models
and 7 more not named here
dct1 2 other papers
1 dated earlier, 1 later
2105.08997 (2021-05)
When Deep Classifiers Agree: Analyzing Correlations between Learning Order and Image Statistics
2412.07277 (2024-12)
Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable Trigger
dct 1 other paper
1 dated earlier
2105.08997 (2021-05)
When Deep Classifiers Agree: Analyzing Correlations between Learning Order and Image Statistics
get_grid_from_dict 1 other paper
1 later
2312.05038 (2023-12)
Prompt-In-Prompt Learning for Universal Image Restoration
get_grid_from_list 1 other paper
1 later
2312.05038 (2023-12)
Prompt-In-Prompt Learning for Universal Image Restoration
only_on_rank0 1 other paper
1 later
2312.05038 (2023-12)
Prompt-In-Prompt Learning for Universal Image Restoration

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

Sparse-view computed tomography (CT)-using a small number of projections for tomographic reconstructionenables much lower radiation dose to patients and accelerated data acquisition. The reconstructed images, however, suffer from strong artifacts, greatly limiting their diagnostic value. Current trends for sparse-view CT turn to the raw data for better information recovery. The resultant dual-domain methods, nonetheless, suffer from secondary artifacts, especially in ultra-sparse view scenarios, and their generalization to other scanners/protocols is greatly limited. A crucial question arises: have the image post-processing methods reached the limit? Our answer is not yet. In this paper, we stick to image post-processing methods due to great flexibility and propose global representation(GloRe) distillation framework for sparse-view CT, termed GloReDi. First, we propose to learn GloRe with Fourier convolution, so each element in GloRe has an image-wide receptive field. Second, unlike methods that only use the full-view images for supervision, we propose to distill GloRe from intermediate-view reconstructed images that are readily available but not explored in previous literature. The success of GloRe distillation is attributed to two key components: representation directional distillation to align the GloRe directions, and band-pass-specific contrastive distillation to gain clinically important details. Extensive experiments demonstrate the superiority of the proposed GloReDi over the state-of-the-art methods, including dual-domain ones. The source code is available at https: //github.com/longzilicart/GloReDi.

For agents

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

get_harvested_code_for_paper("2308.08463")
get_code_for_paper("2308.08463")
have("2308.08463")

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

curl https://syntology.ai/api/ran/2308.08463.json

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

[![Syntology run record](https://syntology.ai/api/ran/2308.08463.svg)](https://syntology.ai/paper/2308.08463)

Connect an agent — have() is free.