SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.05265 · 2022

Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging

arXiv · PDF · Open in the Atlas

Code that ran

14 of 21 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, 1 violated it and 5 have no contract verdict; 7 failures of our instrument; 7 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/2202.05265.json · badge: /api/ran/2202.05265.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
aangelopoulos/im2im-uq canonical (classifier label)
classifier basis not recorded on the link
14 ran · 7 no recorded run
FunctionStatusWhere it lives
bentkus_plus Ran
ran, honoured the contract we drafted
aangelopoulos/im2im-uq/core/calibration/bounds.py
code served (permissive licence) · get_code("6164fcc501da6f66")
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 float64, 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 numpy as np
from scipy.stats import binom

# Analyze the function: bentkus_plus(mu, x, n)
# - mu: used in binom.cdf as probability parameter (expects float in [0,1])
# - x: used in np.floor(n * x), expects numeric scalar or array-like
# - n: used in np.floor(n * x) and binom.cdf as number of trials, expects positive int

# Set up small, valid arguments
mu = 0.5  # probability parameter for binomial distribution
x = 0.3   # fraction parameter
n = 20    # number of trials (positive integer)

ARGS = {
    "mu": mu,
    "x": x,
    "n": n,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, 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
cacheable Ran
ran on a synthesized input
aangelopoulos/im2im-uq/core/utils.py
code served (permissive licence) · get_code("00660111f7ab14b9")
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 os
import sys
import inspect
import pathlib
import pickle as pkl
import torch
import torch.nn as nn

torch.manual_seed(0)

# The cacheable function takes a single parameter: func
# func is expected to be a callable that will be wrapped

def dummy_function(x, y):
    """A simple function that cacheable will wrap"""
    return x + y

ARGS = {
    'func': dummy_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
complex_abs Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
aangelopoulos/im2im-uq/core/datasets/fastmri/math_util.py
pointer only (licence: MIT); the stored copy get_code serves, from matt-bendel/pcaGAN, is pointer only (licence: NONE) · get_code("385e0a4ae00863da")
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 matt-bendel/pcaGAN, 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.

complex_conj Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
aangelopoulos/im2im-uq/core/datasets/fastmri/math_util.py
pointer only (licence: MIT); the stored copy get_code serves, from matt-bendel/pcaGAN, is pointer only (licence: NONE) · get_code("e5788b10a7f0b402")
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 matt-bendel/pcaGAN, 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.

complex_mul Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
aangelopoulos/im2im-uq/core/datasets/fastmri/math_util.py
pointer only (licence: MIT); the stored copy get_code serves, from matt-bendel/pcaGAN, is pointer only (licence: NONE) · get_code("f760d2d48a634ebd")
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 matt-bendel/pcaGAN, 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.

et_query Ran
ran; our contract draft was wrong, not the code
aangelopoulos/im2im-uq/core/datasets/fastmri/FastMRIDataset.py
code served (permissive licence) · get_code("33282a1691459010")
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 str. 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 xml.etree.ElementTree as etree

# Create a simple XML structure with the ISMRMRD namespace
xml_string = """<?xml version="1.0" encoding="UTF-8"?>
<root xmlns:ismrmrd="http://www.ismrm.org/ISMRMRD">
    <ismrmrd:Encoding>
        <ismrmrd:matrixSize>
            <ismrmrd:x>256</ismrmrd:x>
        </ismrmrd:matrixSize>
    </ismrmrd:Encoding>
</root>
"""

root = etree.fromstring(xml_string)

qlist = ["Encoding", "matrixSize", "x"]

namespace = "http://www.ismrm.org/ISMRMRD"

ARGS = {
    "root": root,
    "qlist": qlist,
    "namespace": namespace,
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
et_query Ran
ran; our contract draft was wrong, not the code
aangelopoulos/im2im-uq/core/datasets/fastmri/mri_data.py
code served (permissive licence) · get_code("656ebf54ad47cd94")
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 str. 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 xml.etree.ElementTree as etree

# Create a simple XML document with ISMRMRD namespace
xml_string = '''<?xml version="1.0" encoding="UTF-8"?>
<ISMRMRD xmlns="http://www.ismrm.org/ISMRMRD">
    <Encoding>
        <matrixSize>256</matrixSize>
    </Encoding>
</ISMRMRD>'''

root = etree.fromstring(xml_string)

ARGS = {
    'root': root,
    'qlist': ['Encoding', 'matrixSize'],
    'namespace': 'http://www.ismrm.org/ISMRMRD'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
fetch_dir Ran
ran; our contract draft was wrong, not the code
aangelopoulos/im2im-uq/core/datasets/fastmri/mri_data.py
code served (permissive licence) · get_code("cd2c51b462e7b045")
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 PosixPath. 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 os
import tempfile
from pathlib import Path
import yaml

# Create a temporary directory for the config file
temp_dir = tempfile.mkdtemp()
config_file_path = Path(temp_dir) / 'fastmri_dirs.yaml'

# Create a valid config file with required keys
config_data = {
    'knee_path': '/path/to/knee/data',
    'brain_path': '/path/to/brain/data',
    'log_path': '/path/to/logs'
}

with open(config_file_path, 'w') as f:
    yaml.dump(config_data, f)

ARGS = {
    'key': 'knee_path',
    'data_config_file': config_file_path
}
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 PosixPath — a PosixPath output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PosixPath 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
fft2c_new Ran
ran on a synthesized input
aangelopoulos/im2im-uq/core/datasets/fastmri/fftc.py
code served (permissive licence) · get_code("ef5182a3c1f446c4")
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, 3, 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

torch.manual_seed(0)

# The function fft2c_new expects:
# - data: A complex-valued tensor with at least 3 dimensions
#   - Last dimension (-1) must have size 2 (real/imaginary components)
#   - Dimensions -3 and -2 are spatial dimensions
#   - All other dimensions are batch dimensions

# Create a small tensor: batch=2, spatial dims 4x3, complex dim 2
data = torch.randn(2, 4, 3, 2)

ARGS = {
    "data": data,
}
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, 3, 2) — shape (2, 4, 3, 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
h1 Ran
ran, violated the contract we drafted
aangelopoulos/im2im-uq/core/calibration/bounds.py
code served (permissive licence) · get_code("86294eacaecc7ea5")
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 ndarray, 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 numpy as np
import torch

torch.manual_seed(0)

# h1 computes a KL divergence-like metric between y and mu
# Both y and mu should be probability values (between 0 and 1)
# They can be scalars, arrays, or have the same shape

# Create small numpy arrays with probability values
y = np.array([[0.1, 0.9, 0.3, 0.7],
              [0.2, 0.8, 0.4, 0.6]])

mu = np.array([[0.15, 0.85, 0.35, 0.65],
               [0.25, 0.75, 0.45, 0.55]])

ARGS = {
    "y": y,
    "mu": mu
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, 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
hoeffding_plus Ran
ran on a synthesized input
aangelopoulos/im2im-uq/core/calibration/bounds.py
code served (permissive licence) · get_code("91e18dc97f950939")
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 ndarray, ndim 1, dtype family float, shape (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 numpy as np

# The function hoeffding_plus takes three parameters:
# - mu: appears to be a scalar or array used in h1 function
# - x: appears to be a scalar or array used in h1 function  
# - n: appears to be a scalar (sample size)
#
# Looking at the function body:
# - hoeffding_plus calls h1(np.minimum(mu, x), mu)
# - h1 performs element-wise operations: y * np.log(y / mu) + (1 - y) * np.log((1 - y) / (1 - mu))
# - This requires y and mu to be compatible for broadcasting
# - np.minimum(mu, x) produces y, which should be in (0, 1) for the log to be valid
# - mu should also be in (0, 1)
# - n is used as a scalar multiplier

# Create valid arguments
mu = np.array([0.3, 0.5, 0.7, 0.6])  # Probabilities in (0, 1)
x = np.array([0.4, 0.6, 0.5, 0.8])   # Values in (0, 1)
n = 100  # Sample size (scalar)

ARGS = {
    "mu": mu,
    "x": x,
    "n": n
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (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
normalize Ran
ran on a synthesized input
aangelopoulos/im2im-uq/core/utils.py
code served (permissive licence) · get_code("9ae0c74fc30f64e6")
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 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

torch.manual_seed(0)

# Create a small tensor with shape (batch=2, channels=4, height=3, width=5)
x = torch.randn(2, 4, 3, 5)

# Test with 'standard' type and per_pixel=False
type_val = 'standard'
per_pixel_val = False
input_output_val = 'input'

ARGS = {
    'x': x,
    'type': type_val,
    'per_pixel': per_pixel_val,
    'input_output': input_output_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 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: none by the harness; any seed is in the setup block
normalize_dataset Ran
ran on a synthesized input
aangelopoulos/im2im-uq/core/utils.py
code served (permissive licence) · get_code("c1607cdb46c79988")
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 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.utils.data

torch.manual_seed(0)

# Create small sample tensors
# Input: (batch=2, channels=3, height=4, width=5)
# Output: (batch=2, channels=2, height=4, width=5)
input_data = torch.randn(2, 3, 4, 5)
output_data = torch.randn(2, 2, 4, 5)

# Create a dataset that supports indexing with [:] to get all data
dataset = torch.utils.data.TensorDataset(input_data, output_data)

ARGS = {
    'dataset': dataset,
    'type': ['standard', 'min-max'],
    'per_pixel': [False, True]
}
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 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: none by the harness; any seed is in the setup block
rss Ran
ran; our contract draft was wrong, not the code
aangelopoulos/im2im-uq/core/datasets/fastmri/coil_combine.py
pointer only (licence: MIT); the stored copy get_code serves, from matt-bendel/pcaGAN, is pointer only (licence: NONE) · get_code("a6fd5ed2509fce4e")
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 matt-bendel/pcaGAN, 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.

create_mask_for_mask_type Not yet run
unverified (harvested, no recorded run)
aangelopoulos/im2im-uq/core/datasets/fastmri/subsample.py
code served (permissive licence) · get_code("84e1a77035c301fe")
How it ran

no invocation recorded.

fft2c_old Not yet run
unverified (harvested, no recorded run)
aangelopoulos/im2im-uq/core/datasets/fastmri/fftc.py
code served (permissive licence) · get_code("1e9da50866e41bae")
How it ran

no invocation recorded.

get_rcps_losses Not yet run
unverified (harvested, no recorded run)
aangelopoulos/im2im-uq/core/calibration/calibrate_model.py
code served (permissive licence) · get_code("4df39bd3bce9fa0d")
How it ran

no invocation recorded.

get_rcps_losses_from_outputs Not yet run
unverified (harvested, no recorded run)
aangelopoulos/im2im-uq/core/calibration/calibrate_model.py
code served (permissive licence) · get_code("409578d8bfb9c122")
How it ran

no invocation recorded.

get_rcps_metrics_from_outputs Not yet run
unverified (harvested, no recorded run)
aangelopoulos/im2im-uq/core/calibration/calibrate_model.py
code served (permissive licence) · get_code("a3f8321918f99c0d")
How it ran

no invocation recorded.

ifft2c_old Not yet run
unverified (harvested, no recorded run)
aangelopoulos/im2im-uq/core/datasets/fastmri/fftc.py
code served (permissive licence) · get_code("67883fe2b6265694")
How it ran

no invocation recorded.

normalize_dataset Not yet run
unverified (harvested, no recorded run)
aangelopoulos/im2im-uq/core/datasets/utils.py
code served (permissive licence) · get_code("6c13382d785eb557")
How it ran

no invocation recorded.

Also present in other papers' code

Of 21 samples lifted from this paper's linked repositories, 21 carry a function identity and 0 do not. Of the 20 distinct functions with an identity, 8 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 8 later) and 12 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
et_query 4 other papers
2 dated earlier, 2 later
1811.08839 (2018-11)
fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
2012.06318 (2020-12)
Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction
2304.09254 (2023-04)
FastMRI Prostate: A Publicly Available, Biparametric MRI Dataset to Advance Machine Learning for Prostate Cancer Imaging
and 1 more not named here
fetch_dir 3 other papers
2 dated earlier, 1 later
1811.08839 (2018-11)
fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
2012.06318 (2020-12)
Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction
2304.09254 (2023-04)
FastMRI Prostate: A Publicly Available, Biparametric MRI Dataset to Advance Machine Learning for Prostate Cancer Imaging
h1 3 other papers
2 dated earlier, 1 later
2101.02703 (2021-01)
Distribution-Free, Risk-Controlling Prediction Sets
2110.01052 (2021-10)
Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control
2207.10074 (2022-07)
Semantic uncertainty intervals for disentangled latent spaces
rss 2 other papers
2 later
2411.00605 (2024-11)
pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization
2607.03299 (2026-07)
Piecewise Dynamic Diffusion Regularization for Reconstruction of Cardiac Cine MRI
bentkus_plus 1 other paper
1 later
2207.10074 (2022-07)
Semantic uncertainty intervals for disentangled latent spaces
complex_abs 1 other paper
1 later
2411.00605 (2024-11)
pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization
complex_conj 1 other paper
1 later
2411.00605 (2024-11)
pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization
complex_mul 1 other paper
1 later
2411.00605 (2024-11)
pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization

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

Image-to-image regression is an important learning task, used frequently in biological imaging. Current algorithms, however, do not generally offer statistical guarantees that protect against a model's mistakes and hallucinations. To address this, we develop uncertainty quantification techniques with rigorous statistical guarantees for image-to-image regression problems. In particular, we show how to derive uncertainty intervals around each pixel that are guaranteed to contain the true value with a user-specified confidence probability. Our methods work in conjunction with any base machine learning model, such as a neural network, and endow it with formal mathematical guarantees -- regardless of the true unknown data distribution or choice of model. Furthermore, they are simple to implement and computationally inexpensive. We evaluate our procedure on three image-to-image regression tasks: quantitative phase microscopy, accelerated magnetic resonance imaging, and super-resolution transmission electron microscopy of a Drosophila melanogaster brain.

For agents

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

get_harvested_code_for_paper("2202.05265")
get_code_for_paper("2202.05265")
have("2202.05265")

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

curl https://syntology.ai/api/ran/2202.05265.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.05265.svg)](https://syntology.ai/paper/2202.05265)

Connect an agent — have() is free.