SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.04967 · 2022

UNeXt: MLP-based Rapid Medical Image Segmentation Network

arXiv · PDF · Open in the Atlas

Code that ran

20 of 26 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; 2 honoured the contract we drafted, 1 violated it and 11 have no contract verdict; 6 failures of our instrument; 6 no recorded run); 2 of them were also run on the host, not in the jail, by the peer-agreement lane that set their level, 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/2203.04967.json · badge: /api/ran/2203.04967.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
jeya-maria-jose/Medical-Transformer canonical (classifier label)
classifier basis not recorded on the link
14 ran · 5 no recorded run
jeya-maria-jose/unext-pytorch canonical (classifier label)
classifier basis not recorded on the link
6 ran · 1 no recorded run
FunctionStatusWhere it lives
count_params Ran
ran, honoured the contract we drafted
jeya-maria-jose/unext-pytorch/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from gdisag/gradient_disaggregation, is pointer only (licence: NONE) · get_code("616b5e82dd2a38f9")
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 gdisag/gradient_disaggregation, 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.

cross_entropy_for_onehot Ran
ran; our contract draft was wrong, not the code
jeya-maria-jose/Medical-Transformer/lib/utils.py
code served (permissive licence) · get_code("e4df01238c9e5ba5")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T03:10:52Z). 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 small tensors for the function
# pred: logits tensor, shape (batch_size, num_classes)
# target: one-hot encoded targets, shape (batch_size, num_classes)

batch_size = 2
num_classes = 4

pred = torch.randn(batch_size, num_classes)
target = torch.zeros(batch_size, num_classes)
# Create one-hot encoded targets
target[0, 0] = 1.0
target[1, 2] = 1.0

ARGS = {
    "pred": pred,
    "target": target,
}
Setup block drafted by
a language model, Claude Haiku 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 Tensor, 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
adjust_learning_rate Ran
ran on a synthesized input
jeya-maria-jose/Medical-Transformer/lib/utils.py
code served (permissive licence) · get_code("9d1a2a8f3cd2f263")
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 float, 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 torch
import torch.nn as nn
import torch.optim as optim
import math

torch.manual_seed(0)

# Create a minimal args object
class Args:
    def __init__(self):
        self.warmup_epochs = 5
        self.epochs = 100
        self.lr = 0.1

args = Args()

# Create a minimal model and optimizer
model = nn.Linear(4, 3)
optimizer = optim.SGD(model.parameters(), lr=args.lr)

# Set up parameters for the function
epoch = 10
batch_idx = 5
data_nums = 128
type_schedule = 'cosine'

ARGS = {
    'args': args,
    'optimizer': optimizer,
    'epoch': epoch,
    'batch_idx': batch_idx,
    'data_nums': data_nums,
    'type': type_schedule
}
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 float, 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
build_optimizer Ran
ran on a synthesized input
jeya-maria-jose/Medical-Transformer/lib/build_optimizer.py
code served (permissive licence) · get_code("57c57f81551ed227")
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 SGD. 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
import torch.optim as optim

torch.manual_seed(0)

# Build a minimal model with parameters
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

model = MinimalModel()

# Build args object with all required attributes
class Args:
    def __init__(self):
        self.optim = 'sgd'
        self.lr = 0.01
        self.momentum = 0.9
        self.weight_decay = 1e-4
        self.nesterov = True

args = Args()

ARGS = {
    'args': args,
    'model': model
}
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 SGD — a SGD output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SGD 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
classwise_f1 Ran
ran on a synthesized input
jeya-maria-jose/Medical-Transformer/metrics.py
code served (permissive licence) · get_code("23e3645b57111011")
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 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 torch

torch.manual_seed(0)

# Create small tensors for the function
# output: (n_batch, n_classes, image.shape) - let's use (2, 4, 3, 3) for batch_size=2, n_classes=4, image=3x3
# gt: (n_batch, image.shape) - let's use (2, 3, 3) with class indices
n_batch = 2
n_classes = 4
image_h = 3
image_w = 3

# output logits - shape (n_batch, n_classes, image_h, image_w)
output = torch.randn(n_batch, n_classes, image_h, image_w)

# ground truth labels - shape (n_batch, image_h, image_w) with class indices 0-3
gt = torch.randint(0, n_classes, (n_batch, image_h, image_w))

ARGS = {
    "output": output,
    "gt": gt,
}
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 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
classwise_iou Ran
ran on a synthesized input
jeya-maria-jose/Medical-Transformer/metrics.py
code served (permissive licence) · get_code("0000f4908d2309ef")
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 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 torch

torch.manual_seed(0)

# Construct minimal valid arguments for classwise_iou
# output: torch.Tensor of shape (n_batch, n_classes, image.shape)
# gt: torch.LongTensor of shape (n_batch, image.shape)

n_batch = 2
n_classes = 4
height = 3
width = 5

# Create output tensor: (batch_size=2, n_classes=4, height=3, width=5)
# Values should be between 0 and 1 (logits/probabilities)
output = torch.rand(n_batch, n_classes, height, width)

# Create ground truth tensor: (batch_size=2, height=3, width=5)
# Values should be class indices in range [0, n_classes)
gt = torch.randint(0, n_classes, (n_batch, height, width))

ARGS = {
    "output": output,
    "gt": gt,
}
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 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
conv1x1 Ran
ran; our contract draft was wrong, not the code
jeya-maria-jose/Medical-Transformer/lib/models/axialnet.py
code served (permissive licence) · get_code("d9def42110729a85")
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 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 conv1x1 takes in_planes, out_planes, and stride as parameters
# It returns an nn.Conv2d layer configured for 1x1 convolution
# We need to provide valid integer arguments for these parameters

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1
}
Setup block drafted by
a language model, Claude Haiku 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
conv1x1 Ran
ran; our contract draft was wrong, not the code
jeya-maria-jose/unext-pytorch/archs.py
code served (permissive licence) · get_code("88d8920bc9d995f6")
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": 64,
    "out_planes": 128,
    "stride": 1,
}
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 Ran
ran; our contract draft was wrong, not the code
jeya-maria-jose/Medical-Transformer/lib/models/resnet.py
code served (permissive licence) · get_code("160bb14bd76201b4")
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 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,
    "groups": 1,
    "dilation": 1,
}
Setup block drafted by
a language model, Claude Haiku 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
jeya-maria-jose/Medical-Transformer/extractors.py
pointer only (licence: MIT); the stored copy get_code serves, from hkchengrex/Tracking-Anything-with-DEVA, is pointer only (licence: NOASSERTION) · get_code("48f5a5ec1d5dd2ef")
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 hkchengrex/Tracking-Anything-with-DEVA, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

dice_coef Ran
ran on a synthesized input
jeya-maria-jose/unext-pytorch/metrics.py
code served (permissive licence) · get_code("fc0365a30b108850")
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 float32, 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 torch
import numpy as np

torch.manual_seed(0)

# Create small tensors for output and target
# output: raw logits that will be passed through sigmoid
# target: binary labels
output = torch.randn(2, 4)  # batch_size=2, features=4
target = torch.randint(0, 2, (2, 4), dtype=torch.float32)  # binary targets

ARGS = {
    "output": output,
    "target": target
}
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 float32, 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
get_config Ran
ran on a synthesized input
jeya-maria-jose/unext-pytorch/config.py
code served (permissive licence) · get_code("5b11c8193755906a")
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 CfgNode. 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
from yacs.config import CfgNode as CN

torch.manual_seed(0)

# The function takes a single parameter 'args'
# Looking at the function body, it only clones _C and returns it
# So args is not actually used in the function body
# But we need to provide a valid argument for it

# Create a simple stand-in args object
class Args:
    def __init__(self):
        self.config_file = None
        self.opts = []

args = Args()

ARGS = {
    "args": args
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, yacs — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CfgNode — a CfgNode output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CfgNode 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
imagenet1k Ran
ran on a synthesized input
jeya-maria-jose/Medical-Transformer/lib/datasets/imagenet1k.py
code served (permissive licence) · get_code("d951f27a92264740")
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 1, dtype family float; 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 tempfile
import os
from pathlib import Path
from PIL import Image
import numpy as np

torch.manual_seed(0)

# Create temporary directories with fake ImageFolder structure
temp_dir = tempfile.mkdtemp()
train_dir = os.path.join(temp_dir, 'train')
val_dir = os.path.join(temp_dir, 'val')

# Create class directories and dummy images
for split_dir in [train_dir, val_dir]:
    for class_idx in range(2):
        class_dir = os.path.join(split_dir, f'class_{class_idx}')
        os.makedirs(class_dir, exist_ok=True)
        # Create 2 dummy images per class
        for img_idx in range(2):
            img_array = np.random.randint(0, 256, (224, 224, 3), dtype=np.uint8)
            img = Image.fromarray(img_array)
            img_path = os.path.join(class_dir, f'image_{img_idx}.jpg')
            img.save(img_path)

# Create args object
class Args:
    def __init__(self):
        self.train_dirs = train_dir
        self.val_dirs = val_dir
        self.batch_size = 2
        self.val_batch_size = 2
        self.num_workers = 0
        self.color_jitter = True

ARGS = {
    'args': Args(),
    'distributed': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, 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
iou_score Ran
ran on a synthesized input
jeya-maria-jose/unext-pytorch/metrics.py
code served (permissive licence) · get_code("14b6fae92a98329f")
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 1, dtype family float; 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

torch.manual_seed(0)

# Create small tensor outputs (batch_size=2, spatial_dims=4)
output = torch.randn(2, 4, requires_grad=True)

# Create small tensor targets (same shape as output)
target = torch.randint(0, 2, (2, 4)).float()

ARGS = {
    "output": output,
    "target": target,
}
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 1, 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
label_smoothing Ran
ran on a synthesized input
jeya-maria-jose/Medical-Transformer/lib/utils.py
code served (permissive licence) · get_code("5c9e8b037a72dcd8")
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 prediction tensor: batch_size=2, n_classes=4
pred = torch.randn(2, 4)

# Create target tensor: batch_size=2 with class indices in range [0, 3]
target = torch.tensor([1, 3])

# eta parameter for label smoothing
eta = 0.1

ARGS = {
    "pred": pred,
    "target": target,
    "eta": eta,
}
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
make_weighted_metric Ran
ran on a synthesized input
jeya-maria-jose/Medical-Transformer/metrics.py
code served (permissive licence) · get_code("a0dd9f41120c5917")
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

torch.manual_seed(0)

# Create a mock classwise_metric function that takes output and gt tensors
# and returns classwise scores
def mock_classwise_metric(output, gt):
    """
    Mock classwise metric that returns per-class scores.
    output shape: (batch, classes, ...)
    Returns: tensor of shape (classes,)
    """
    batch_size = output.shape[0]
    num_classes = output.shape[1]
    # Return a simple classwise score for each class
    return torch.rand(num_classes)

# Create sample tensors
batch_size = 2
num_classes = 4
height = 3
width = 5

output = torch.randn(batch_size, num_classes, height, width)
gt = torch.randint(0, num_classes, (batch_size, height, width))

ARGS = {
    "classwise_metric": mock_classwise_metric,
}
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
resnet18 Ran
ran; our contract draft was wrong, not the code
jeya-maria-jose/Medical-Transformer/lib/models/resnet.py
code served (permissive licence) · get_code("72e76034eb3a8502")
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 ResNet. 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)

# Define the ResNet function signature based on the incomplete code
def resnet18(pretrained=False, progress=True, **kwargs):
    """Constructs a ResNet-18 model."""
    return ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)

# Build ARGS dictionary with all parameters for resnet18
ARGS = {
    'pretrained': False,
    'progress': 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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
squeezenet Ran
ran on a synthesized input
jeya-maria-jose/Medical-Transformer/extractors.py
code served (permissive licence) · get_code("2522f45181a337ce")
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 SqueezeNet. 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
from collections import OrderedDict

torch.manual_seed(0)

ARGS = {
    'pretrained': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SqueezeNet — a SqueezeNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SqueezeNet 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
str2bool Ran
ran, violated the contract we drafted
jeya-maria-jose/unext-pytorch/utils.py
code served (permissive licence) · get_code("8b9a62f72ecd14a7")
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 bool, 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 argparse

def str2bool(v):
    if v.lower() in ['true', 1]:
        return True
    elif v.lower() in ['false', 0]:
        return False
    else:
        raise argparse.ArgumentTypeError('Boolean value expected.')

# The function takes a single parameter 'v' which should be a string
# It calls .lower() on v, so v must be a string
# It checks if v.lower() is in a list containing 'true' or 1
# Valid inputs are strings like 'true', 'True', 'TRUE', 'false', 'False', 'FALSE'

ARGS = {
    'v': 'true'
}
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 bool, 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
to_long_tensor Ran
ran, honoured the contract we drafted
jeya-maria-jose/Medical-Transformer/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from shashankhuang/reclmis, is pointer only (licence: NOASSERTION) · get_code("1f565d043b253a06")
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 shashankhuang/reclmis, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

axial26s Not yet run
unverified (harvested, no recorded run)
jeya-maria-jose/Medical-Transformer/lib/models/model_codes.py
code served (permissive licence) · get_code("946f264b8237be73")
How it ran

no invocation recorded.

axial50s Not yet run
unverified (harvested, no recorded run)
jeya-maria-jose/Medical-Transformer/lib/models/model_codes.py
code served (permissive licence) · get_code("c5c8c16bf6032b72")
How it ran

no invocation recorded.

axialunet Not yet run
unverified (harvested, no recorded run)
jeya-maria-jose/Medical-Transformer/lib/models/axialnet.py
pointer only (licence: MIT); the stored copy get_code serves, from jayparanjape/biastuning, is pointer only (licence: NONE) · get_code("b44a1d3a0190256d")
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 jayparanjape/biastuning, 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.

densenet Not yet run
unverified (harvested, no recorded run)
jeya-maria-jose/Medical-Transformer/extractors.py
code served (permissive licence) · get_code("d424c563d915d012")
How it ran

no invocation recorded.

gated Not yet run
unverified (harvested, no recorded run)
jeya-maria-jose/Medical-Transformer/lib/models/axialnet.py
pointer only (licence: MIT); the stored copy get_code serves, from jayparanjape/biastuning, is pointer only (licence: NONE) · get_code("e90a4014d74c1fa1")
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 jayparanjape/biastuning, 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.

shift Not yet run
unverified (harvested, no recorded run)
jeya-maria-jose/unext-pytorch/archs.py
pointer only (licence: MIT); the stored copy get_code serves, from zhenqi-he/transnuseg, is pointer only (licence: NONE) · get_code("000b07edf24001b4")
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 zhenqi-he/transnuseg, 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 26 samples lifted from this paper's linked repositories, 26 carry a function identity and 0 do not. Of the 26 distinct functions with an identity, 19 are also present in other papers whose code we hold (14 with at least one paper dated earlier, 4 the same month, 11 later) and 7 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
conv1x1 431 other papers
174 dated earlier, 10 the same month, 235 later, 11 same year, order not determinable, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
conv3x3 312 other papers
106 dated earlier, 8 the same month, 188 later, 9 same year, order not determinable, 1 undated · 31 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 309 more not named here
resnet18 95 other papers
34 dated earlier, 1 the same month, 56 later, 3 same year, order not determinable, 1 undated
1805.00907 (2018-05)
Glow: Graph Lowering Compiler Techniques for Neural Networks
1902.08153 (2019-02)
Learned Step Size Quantization
1904.01355 (2019-04)
FCOS: Fully Convolutional One-Stage Object Detection
and 92 more not named here
conv3x3 18 other papers
10 dated earlier, 1 the same month, 6 later, 1 same year, order not determinable
1612.00593 (2016-12)
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
1901.04780 (2019-01)
DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion
1905.09646 (2019-05)
Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks
and 15 more not named here
count_params 13 other papers
5 dated earlier, 8 later
1807.10165 (2018-07)
UNet++: A Nested U-Net Architecture for Medical Image Segmentation
1811.11168 (2018-11)
Deformable ConvNets v2: More Deformable, Better Results
1907.03950 (2019-07)
Learning by Abstraction: The Neural State Machine
and 10 more not named here
str2bool 5 other papers
4 dated earlier, 1 later
1807.10165 (2018-07)
UNet++: A Nested U-Net Architecture for Medical Image Segmentation
1811.11168 (2018-11)
Deformable ConvNets v2: More Deformable, Better Results
2004.03657 (2020-04)
FedMAX: Mitigating Activation Divergence for Accurate and Communication-Efficient Federated Learning
and 2 more not named here
cross_entropy_for_onehot 4 other papers
4 dated earlier
1906.08935 (2019-06)
Deep Leakage from Gradients
2003.07853 (2020-03)
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation
2010.02772 (2020-10)
InstaHide: Instance-hiding Schemes for Private Distributed Learning *
and 1 more not named here
conv1x1 2 other papers
2 later
2307.08051 (2023-07)
TransNuSeg: A Lightweight Multi-Task Transformer for Nuclei Segmentation
2308.03726 (2023-08)
AdaptiveSAM: Towards Efficient Tuning of SAM for Surgical Scene Segmentation
to_long_tensor 2 other papers
2 later
aaai_28394 (2024 (year only))
DTMFormer: Dynamic Token Merging for Boosting Transformer-Based Medical Image Segmentation
2404.02845 (2024-04)
Cross-Modal Conditioned Reconstruction for Language-guided Medical Image Segmentation
adjust_learning_rate 1 other paper
1 dated earlier
2003.07853 (2020-03)
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation
axial26s 1 other paper
1 dated earlier
2003.07853 (2020-03)
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation
axial50s 1 other paper
1 dated earlier
2003.07853 (2020-03)
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation
axialunet 1 other paper
1 later
2308.03726 (2023-08)
AdaptiveSAM: Towards Efficient Tuning of SAM for Surgical Scene Segmentation
build_optimizer 1 other paper
1 dated earlier
2003.07853 (2020-03)
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation
dice_coef 1 other paper
1 dated earlier
1807.10165 (2018-07)
UNet++: A Nested U-Net Architecture for Medical Image Segmentation
gated 1 other paper
1 later
2308.03726 (2023-08)
AdaptiveSAM: Towards Efficient Tuning of SAM for Surgical Scene Segmentation
imagenet1k 1 other paper
1 dated earlier
2003.07853 (2020-03)
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation
label_smoothing 1 other paper
1 dated earlier
2003.07853 (2020-03)
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation
shift 1 other paper
1 later
2307.08051 (2023-07)
TransNuSeg: A Lightweight Multi-Task Transformer for Nuclei Segmentation

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

UNet and its latest extensions like TransUNet have been the leading medical image segmentation methods in recent years. However, these networks cannot be effectively adopted for rapid image segmentation in point-of-care applications as they are parameter-heavy, computationally complex and slow to use. To this end, we propose UNeXt which is a Convolutional multilayer perceptron (MLP) based network for image segmentation. We design UNeXt in an effective way with an early convolutional stage and a MLP stage in the latent stage. We propose a tokenized MLP block where we efficiently tokenize and project the convolutional features and use MLPs to model the representation. To further boost the performance, we propose shifting the channels of the inputs while feeding in to MLPs so as to focus on learning local dependencies. Using tokenized MLPs in latent space reduces the number of parameters and computational complexity while being able to result in a better representation to help segmentation. The network also consists of skip connections between various levels of encoder and decoder. We test UNeXt on multiple medical image segmentation datasets and show that we reduce the number of parameters by 72x, decrease the computational complexity by 68x, and improve the inference speed by 10x while also obtaining better segmentation performance over the state-of-the-art medical image segmentation architectures. Code is available at https://github.com/jeya-maria-jose/UNeXt-pytorch

For agents

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

get_harvested_code_for_paper("2203.04967")
get_code_for_paper("2203.04967")
have("2203.04967")

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

curl https://syntology.ai/api/ran/2203.04967.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.04967.svg)](https://syntology.ai/paper/2203.04967)

Connect an agent — have() is free.