SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2001.07645 · 2020

SAUNet: Shape Attentive U-Net for Interpretable Medical Image Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

12 of 15 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 5 have no contract verdict; 7 failures of our instrument; 3 no recorded run), measured 2026-11-21; 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/2001.07645.json · badge: /api/ran/2001.07645.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
sunjesse/shape-attentive-unet canonical (classifier label)
classifier basis: census
9 ran · 3 no recorded run
bowang-lab/shape-attentive-unet canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
adaptive_avgmax_pool2d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sunjesse/shape-attentive-unet/models/adaptive_avgmax_pool.py
code served (permissive licence) · get_code("24ba52fa75e98634")
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, 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
import torch.nn.functional as F

torch.manual_seed(0)

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

ARGS = {
    'x': x,
    'pool_type': 'avg',
    'padding': 0,
    'count_include_pad': False,
}
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, 1, 1) — shape (2, 4, 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
batchnorm Ran
ran; our contract draft was wrong, not the code
sunjesse/shape-attentive-unet/models/attention_blocks.py
code served (permissive licence) · get_code("5fd9109962bb3e30")
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 BatchNorm2d. 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

torch.manual_seed(0)

ARGS = {
    "in_planes": 64
}
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 BatchNorm2d — a BatchNorm2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a BatchNorm2d 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
calc_pad_same Ran
ran on a synthesized input
sunjesse/shape-attentive-unet/models/custom_functions.py
code served (permissive licence) · get_code("264280edf128c77a")
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 int, ndim 0, dtype family int, 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 torch
import numpy as np

torch.manual_seed(0)

# calc_pad_same takes 4 integer parameters for computing padding
# in_siz: input size
# out_siz: output size
# stride: stride value
# ksize: kernel size

ARGS = {
    "in_siz": 28,
    "out_siz": 28,
    "stride": 1,
    "ksize": 3
}
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 int, ndim 0, dtype family int, 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
conv1x1 Ran
ran; our contract draft was wrong, not the code
sunjesse/shape-attentive-unet/models/attention_blocks.py
code served (permissive licence) · get_code("d5715d28a2cf2e5f")
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 Conv2d. 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

torch.manual_seed(0)

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
    "bias": False,
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
conv1x1_bn_relu Ran
ran; our contract draft was wrong, not the code
bowang-lab/shape-attentive-unet/models/models.py
code served (permissive licence) · get_code("1f54b5b7c5eed259")
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 Sequential. 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

torch.manual_seed(0)

# The function conv1x1_bn_relu takes three parameters:
# - in_planes: number of input channels
# - out_planes: number of output channels  
# - stride: stride for the convolution (default=1)

# We need to provide distinct values for in_planes and out_planes
in_planes = 3
out_planes = 5
stride = 2

ARGS = {
    'in_planes': in_planes,
    'out_planes': out_planes,
    'stride': stride
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
bowang-lab/shape-attentive-unet/models/models.py
code served (permissive licence) · get_code("dbcb53696bc43ef9")
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 Conv2d. 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

torch.manual_seed(0)

# The function conv3x3 creates a Conv2d layer
# Parameters:
# - in_planes: number of input channels (int)
# - out_planes: number of output channels (int)
# - stride: stride for convolution (int, default=1)
# - has_bias: whether to use bias (bool, default=False)

ARGS = {
    'in_planes': 3,
    'out_planes': 8,
    'stride': 2,
    'has_bias': True
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
sunjesse/shape-attentive-unet/models/attention_blocks.py
code served (permissive licence) · get_code("ca893f9498143980")
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 Conv2d. 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

torch.manual_seed(0)

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
    "bias": False,
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
conv3x3_bn_relu Ran
ran; our contract draft was wrong, not the code
bowang-lab/shape-attentive-unet/models/models.py
code served (permissive licence) · get_code("bf378f5e74f9c237")
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 Sequential. 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

torch.manual_seed(0)

# The function conv3x3_bn_relu takes in_planes, out_planes, and stride
# in_planes: number of input channels
# out_planes: number of output channels
# stride: stride for the convolution

in_planes = 3
out_planes = 16
stride = 2

ARGS = {
    'in_planes': in_planes,
    'out_planes': out_planes,
    'stride': stride
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
convert_to_grayscale Ran
ran on a synthesized input
sunjesse/shape-attentive-unet/misc_functions.py
code served (permissive licence) · get_code("1205772b3f3f23ae")
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 3, dtype family float, shape (1, 4, 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 numpy as np

# Create a small RGB image with shape (D, W, H)
# Using distinct dimensions: 3 channels, 4 width, 5 height
im_as_arr = np.random.rand(3, 4, 5)

ARGS = {
    "im_as_arr": im_as_arr
}
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 3, dtype family float, shape (1, 4, 5) — shape (1, 4, 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
format_np_output Ran
ran on a synthesized input
sunjesse/shape-attentive-unet/misc_functions.py
code served (permissive licence) · get_code("3033223e4e93074d")
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 3, dtype family int, shape (4, 5, 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 numpy as np

# Test case 1: 2D array (grayscale image)
np_arr_2d = np.random.rand(4, 5)

# Test case 2: 1xWxH array (single channel)
np_arr_1xwxh = np.random.rand(1, 4, 5)

# Test case 3: 3xWxH array (already correct format, normalized)
np_arr_3xwxh = np.random.rand(3, 4, 5)

# Test case 4: 3xWxH array with values > 1 (already in 0-255 range)
np_arr_3xwxh_255 = np.random.randint(0, 256, size=(3, 4, 5), dtype=np.uint8)

# Use the first test case for ARGS
ARGS = {
    "np_arr": np_arr_2d
}
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 3, dtype family int, shape (4, 5, 3) — shape (4, 5, 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
gradient_central_diff Ran
ran on a synthesized input
sunjesse/shape-attentive-unet/models/custom_functions.py
code served (permissive licence) · get_code("a0843c57fbf62259")
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, ndim 5, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch.nn.functional as F

torch.manual_seed(0)

# Create a small input tensor: batch_size=2, channels=3, height=4, width=4
input_tensor = torch.randn(2, 3, 4, 4)

# cuda parameter can be int, bool, or False
cuda_param = False

ARGS = {
    "input": input_tensor,
    "cuda": cuda_param
}
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, ndim 5, dtype family float — a tuple 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
pooling_factor Ran
ran on a synthesized input
sunjesse/shape-attentive-unet/models/adaptive_avgmax_pool.py
code served (permissive licence) · get_code("3a8857dbf960f1e4")
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 int, ndim 0, dtype family int, 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 torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'pool_type': 'avgmaxc'
}
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 int, ndim 0, dtype family int, 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
apply_colormap_on_image Not yet run
unverified (harvested, no recorded run)
sunjesse/shape-attentive-unet/misc_functions.py
code served (permissive licence) · get_code("b27e3b79ace9291a")
How it ran

no invocation recorded.

conv2d_same Not yet run
unverified (harvested, no recorded run)
sunjesse/shape-attentive-unet/models/custom_functions.py
code served (permissive licence) · get_code("c7421ba4abae271c")
How it ran

no invocation recorded.

dice_loss Not yet run
unverified (harvested, no recorded run)
sunjesse/shape-attentive-unet/loss.py
code served (permissive licence) · get_code("249ebf36856edf1d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 7 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 5 later) and 8 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
conv3x3 8 other papers
2 dated earlier, 6 later
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1805.11046 (2018-05)
Scalable Methods for 8-bit Training of Neural Networks
2003.07069 (2020-03)
Self-Supervised Discovering of Interpretable Features for Reinforcement Learning
and 5 more not named here
conv3x3 7 other papers
4 dated earlier, 3 later
1804.08864 (2018-04)
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
1807.11590 (2018-07)
Acquisition of Localization Confidence for Accurate Object Detection
and 4 more not named here
batchnorm 2 other papers
1 dated earlier, 1 later
1809.04766 (2018-09)
Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations
2003.07069 (2020-03)
Self-Supervised Discovering of Interpretable Features for Reinforcement Learning
conv1x1 2 other papers
1 dated earlier, 1 later
1906.04423 (2019-06)
NAS-FCOS: Fast Neural Architecture Search for Object Detection
2003.07069 (2020-03)
Self-Supervised Discovering of Interpretable Features for Reinforcement Learning
adaptive_avgmax_pool2d 1 other paper
1 dated earlier
1808.08127 (2018-08)
Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks
conv3x3_bn_relu 1 other paper
1 later
2010.16417 (2020-10)
MichiGAN: Multi-Input-Conditioned Hair Image Generation for Portrait Editing
pooling_factor 1 other paper
1 dated earlier
1808.08127 (2018-08)
Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Medical image segmentation is a difficult but important task for many clinical operations such as cardiac bi-ventricular volume estimation. More recently, there has been a shift to utilizing deep learning and fully convolutional neural networks (CNNs) to perform image segmentation that has yielded state-of-the-art results in many public benchmark datasets. Despite the progress of deep learning in medical image segmentation, standard CNNs are still not fully adopted in clinical settings as they lack robustness and interpretability. Shapes are generally more meaningful features than solely textures of images, which are features regular CNNs learn, causing a lack of robustness. Likewise, previous works surrounding model interpretability have been focused on post hoc gradient-based saliency methods. However, gradient-based saliency methods typically require additional computations post hoc and have been shown to be unreliable for interpretability. Thus, we present a new architecture called Shape Attentive U-Net (SAUNet) which focuses on model interpretability and robustness. The proposed architecture attempts to address these limitations by the use of a secondary shape stream that captures rich shape-dependent information in parallel with the regular texture stream. Furthermore, we suggest multi-resolution saliency maps can be learned using our dual-attention decoder module which allows for multi-level interpretability and mitigates the need for additional computations post hoc. Our method also achieves state-of-the-art results on the two large public cardiac MRI image segmentation datasets of SUN09 and AC17.

For agents

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

get_harvested_code_for_paper("2001.07645")
get_code_for_paper("2001.07645")
have("2001.07645")

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

curl https://syntology.ai/api/ran/2001.07645.json

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

[![Syntology run record](https://syntology.ai/api/ran/2001.07645.svg)](https://syntology.ai/paper/2001.07645)

Connect an agent — have() is free.