SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · aaai_29068 · AAAI · 2024

Roll with the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning

Luping Zhou, Lei Wang, Yinghuan Shi, Zhen Zhao, Lei Qi, Yue Duan

Open in the Atlas

Code that ran

16 of 17 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 8 failures of our instrument; 1 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/aaai_29068.json · badge: /api/ran/aaai_29068.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
NJUyued/SoC4SS-FGVC canonical (classifier label)
classifier basis: census
16 ran · 1 no recorded run
FunctionStatusWhere it lives
AutoContrast Ran
ran; our contract draft was wrong, not the code
NJUyued/SoC4SS-FGVC/lib/datasets/augmentation/randaugment.py
code served (permissive licence) · get_code("4a0ac9d611e018bc")
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 Image. 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 PIL
import PIL.ImageOps
import PIL.ImageEnhance
import PIL.ImageDraw

# Create a simple PIL Image for testing
# AutoContrast expects a PIL Image object as the first parameter
img = PIL.Image.new('RGB', (4, 3), color=(128, 100, 150))

# The second parameter is unused (indicated by _), so we can pass None or any value
second_param = None

ARGS = {
    'img': img,
    '_': second_param,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
Brightness Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
NJUyued/SoC4SS-FGVC/lib/datasets/augmentation/randaugment.py
pointer only (licence: MIT); the stored copy get_code serves, from zhengzhang37/lecodu, is pointer only (licence: NONE) · get_code("61ed09bbdb8adb72")
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 zhengzhang37/lecodu, 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.

Color Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
NJUyued/SoC4SS-FGVC/lib/datasets/augmentation/randaugment.py
pointer only (licence: MIT); the stored copy get_code serves, from zhengzhang37/lecodu, is pointer only (licence: NONE) · get_code("5e4ee5c45933ae09")
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 zhengzhang37/lecodu, 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.

calcDis Ran
ran on a synthesized input
NJUyued/SoC4SS-FGVC/models/soc/soc_utils.py
code served (permissive licence) · get_code("42a46a1324ea199e")
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 list, ndim 2, 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 numpy as np

# Analyze the function:
# - dataSet: indexed with [i][c] and [c][i], so it's a 2D array-like
# - centroids: iterated over with `for c in centroids`, so it's an iterable of indices
# - k: parameter accepted but not used in the function body
# - The function accesses dataSet[i][c] and dataSet[c][i], suggesting symmetric indexing
# - np.size(dataSet, 0) gets the number of rows

# Create a small 2D numpy array (4x4 to allow symmetric access)
dataSet = np.array([
    [1.0, 2.0, 3.0, 4.0],
    [2.0, 5.0, 6.0, 7.0],
    [3.0, 6.0, 9.0, 10.0],
    [4.0, 7.0, 10.0, 13.0]
], dtype=np.float64)

# Create a list of centroid indices to iterate over
centroids = [0, 1, 2]

# k parameter (used in function signature but not in body)
k = 3

ARGS = {
    "dataSet": dataSet,
    "centroids": centroids,
    "k": k
}
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 list, ndim 2, dtype family float — a list 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
classify Ran
ran on a synthesized input
NJUyued/SoC4SS-FGVC/models/soc/soc_utils.py
code served (permissive licence) · get_code("46c00ea45d5825c1")
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 numpy as np

# Create a small symmetric-like dataset (similarity/distance matrix)
# The function treats dataSet as a matrix where dataSet[i][c] is accessed
np.random.seed(0)
dataSet = np.array([
    [1.0, 0.5, 0.3, 0.2],
    [0.5, 1.0, 0.4, 0.1],
    [0.3, 0.4, 1.0, 0.6],
    [0.2, 0.1, 0.6, 1.0]
])

# Define centroids as indices into the dataSet
centroids = [0, 2]

# Number of clusters
k = 2

# Reverse flag for min/max selection
reverse = False

ARGS = {
    "dataSet": dataSet,
    "centroids": centroids,
    "k": k,
    "reverse": reverse
}
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 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
conv1x1 Ran
ran; our contract draft was wrong, not the code
NJUyued/SoC4SS-FGVC/models/nets/resnet.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
conv3x3 Ran
ran; our contract draft was wrong, not the code
NJUyued/SoC4SS-FGVC/models/nets/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
count_parameters Ran
ran, honoured the contract we drafted
NJUyued/SoC4SS-FGVC/utils.py
code served (permissive licence) · get_code("f6b944f50d3f15ae")
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 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)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

ARGS = {
    "model": model
}
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 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
get_SGD Ran
ran; our contract draft was wrong, not the code
NJUyued/SoC4SS-FGVC/train_utils.py
code served (permissive licence) · get_code("55edaf2e12bfbe17")
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

torch.manual_seed(0)

# Create a simple neural network with batch normalization layers
class SimpleNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(4, 8)
        self.bn1 = nn.BatchNorm1d(8)
        self.fc2 = nn.Linear(8, 3)
        self.bn2 = nn.BatchNorm1d(3)
    
    def forward(self, x):
        x = self.fc1(x)
        x = self.bn1(x)
        x = self.fc2(x)
        x = self.bn2(x)
        return x

net = SimpleNet()

ARGS = {
    'net': net,
    'name': 'SGD',
    'lr': 0.1,
    'momentum': 0.9,
    'weight_decay': 0.0005,
    'nesterov': True,
    'bn_wd_skip': 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 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
get_cosine_schedule_with_warmup Ran
ran; our contract draft was wrong, not the code
NJUyued/SoC4SS-FGVC/train_utils.py
code served (permissive licence) · get_code("26ea400f0a8a65f4")
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 LambdaLR. 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 torch.optim import SGD

torch.manual_seed(0)

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

model = SimpleModel()

# Create an optimizer
optimizer = SGD(model.parameters(), lr=0.1)

# Define the arguments for get_cosine_schedule_with_warmup
ARGS = {
    'optimizer': optimizer,
    'num_training_steps': 100,
    'num_cycles': 7.0 / 16.0,
    'num_warmup_steps': 10,
    'last_epoch': -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 LambdaLR — a LambdaLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LambdaLR 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
get_logger Ran
ran on a synthesized input
NJUyued/SoC4SS-FGVC/utils.py
code served (permissive licence) · get_code("f134f238fbf660cc")
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 Logger. 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 logging
import tempfile

# Create a temporary directory for potential log file output
temp_dir = tempfile.mkdtemp()

ARGS = {
    'name': 'test_logger',
    'save_path': temp_dir,
    'level': 'INFO'
}
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
get_nodecay_schedule Ran
ran on a synthesized input
NJUyued/SoC4SS-FGVC/train_utils.py
code served (permissive licence) · get_code("6f608df48c9995b9")
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 LambdaLR. 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 torch.optim import SGD

torch.manual_seed(0)

# Create a small model
model = nn.Linear(4, 3)

# Create an optimizer
optimizer = SGD(model.parameters(), lr=0.1)

# Define ARGS dictionary with all parameters for get_nodecay_schedule
ARGS = {
    "optimizer": optimizer,
    "last_epoch": -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 LambdaLR — a LambdaLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LambdaLR 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
make_dataset Ran
ran on a synthesized input
NJUyued/SoC4SS-FGVC/lib/datasets/iNatDataset.py
code served (permissive licence) · get_code("9161f54c1bae8cd7")
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 os
import tempfile

# Create a temporary directory structure with the necessary files
temp_dir = tempfile.mkdtemp()
dataset_root = temp_dir

# Create directory structure
task = 'All'
task_dir = os.path.join(dataset_root, task)
os.makedirs(task_dir, exist_ok=True)

# Create a split file (train.txt)
split_file = os.path.join(task_dir, 'train.txt')
with open(split_file, 'w') as f:
    f.write('image1 0\n')
    f.write('image2 1\n')
    f.write('image3 0\n')

# Create an unsupervised split file (val_oracle.txt)
unsup_split_file = os.path.join(task_dir, 'val_oracle.txt')
with open(unsup_split_file, 'w') as f:
    f.write('image4 1\n')
    f.write('image5 0\n')

# Create dummy image directories
for img_prefix in ['image1', 'image2', 'image3', 'image4', 'image5']:
    img_dir = os.path.join(dataset_root, img_prefix)
    os.makedirs(img_dir, exist_ok=True)
    img_file = os.path.join(img_dir, img_prefix)
    with open(img_file, 'w') as f:
        f.write('dummy')

# Create a pseudo-label list (optional)
pl_list = [
    'image6 1\n',
    'image7 0\n'
]

# Create image directories for pseudo-labeled images
for img_prefix in ['image6', 'image7']:
    img_dir = os.path.join(dataset_root, img_prefix)
    os.makedirs(img_dir, exist_ok=True)
    img_file = os.path.join(img_dir, img_prefix)
    with open(img_file, 'w') as f:
        f.write('dummy')

ARGS = {
    'dataset_root': dataset_root,
    'split': 'train',
    'task': 'All',
    'pl_list': None
}
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 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
mish Ran
ran; our contract draft was wrong, not the code
NJUyued/SoC4SS-FGVC/models/nets/wrn_var.py
pointer only (licence: MIT); the stored copy get_code serves, from zhouzihao11/CCL, is pointer only (licence: NONE) · get_code("0a7c46eb67c0c21b")
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 zhouzihao11/CCL, 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.

net_builder Ran
ran on a synthesized input
NJUyued/SoC4SS-FGVC/utils.py
code served (permissive licence) · get_code("2a6800e66b850dd7")
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 method. 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)

# Create minimal builder classes that the function expects
class MockWideResNetBuilder:
    def __init__(self):
        self.depth = 28
        self.width = 2
        self.dropout = 0.0
    
    def build(self, num_classes=10):
        return nn.Linear(10, num_classes)

class MockWideResNetVarBuilder:
    def __init__(self):
        self.depth = 28
        self.width = 2
        self.dropout = 0.0
    
    def build(self, num_classes=10):
        return nn.Linear(10, num_classes)

class MockCNN13Builder:
    def __init__(self):
        pass
    
    def build(self, num_classes=10):
        return nn.Linear(10, num_classes)

class MockResNet50Builder:
    def __init__(self):
        self.net_name = 'resnet50'
    
    def build(self, num_classes=10):
        return nn.Linear(10, num_classes)

# Create minimal mock modules for the imports
import sys
from types import ModuleType

wrn_module = ModuleType('models.nets.wrn')
def build_WideResNet():
    return MockWideResNetBuilder()
wrn_module.build_WideResNet = build_WideResNet
sys.modules['models.nets.wrn'] = wrn_module
sys.modules['models'] = ModuleType('models')
sys.modules['models.nets'] = ModuleType('models.nets')

wrn_var_module = ModuleType('models.nets.wrn_var')
def build_WideResNetVar():
    return MockWideResNetVarBuilder()
wrn_var_module.build_WideResNetVar = build_WideResNetVar
sys.modules['models.nets.wrn_var'] = wrn_var_module

cnn13_module = ModuleType('models.nets.cnn13')
def build_CNN13():
    return MockCNN13Builder()
cnn13_module.build_CNN13 = build_CNN13
sys.modules['models.nets.cnn13'] = cnn13_module

resnet_module = ModuleType('models.nets.resnet')
def build_ResNet50():
    return MockResNet50Builder()
resnet_module.build_ResNet50 = build_ResNet50
sys.modules['models.nets.resnet'] = resnet_module

ARGS = {
    'net_name': 'wrn',
    'net_conf': {
        'depth': 16,
        'width': 4,
        'dropout': 0.3
    },
    'num_classes': 10
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
models, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type method — a method output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a method 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
normalize Ran
ran on a synthesized input
NJUyued/SoC4SS-FGVC/models/soc/soc_utils.py
code served (permissive licence) · get_code("e0a36b148e1eb152")
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)

# The function normalize takes a tensor x, sums it, divides by the sum,
# and returns the detached result. It only uses torch.sum() and .detach()
x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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
resnet18 Not yet run
unverified (harvested, no recorded run)
NJUyued/SoC4SS-FGVC/models/nets/resnet.py
code served (permissive licence) · get_code("18d774a570c3febb")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 11 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 0 the same month, 4 later) and 6 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
conv1x1 431 other papers
313 dated earlier, 30 later, 87 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
214 dated earlier, 22 later, 75 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
count_parameters 180 other papers
114 dated earlier, 24 later, 42 same year, order not determinable · 8 only as an assembly brick
1705.08415 (2017-05)
Supervised Community Detection with Line Graph Neural Networks
1707.01926 (2017-07)
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
1808.09367 (2018-08)
Deriving Machine Attention from Human Rationales
and 177 more not named here
resnet18 95 other papers
59 dated earlier, 10 later, 25 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
mish 15 other papers
10 dated earlier, 5 same year, order not determinable
1908.00821 (2019-08)
Learning Lightweight Lane Detection CNNs by Self Attention Distillation
2001.07685 (2020-01)
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
2105.14148 (2021-05)
OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers
and 12 more not named here
AutoContrast 14 other papers
9 dated earlier, 5 same year, order not determinable · 4 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
1909.13719 (2019-09)
RandAugment: Practical automated data augmentation with a reduced search space
and 11 more not named here
Brightness 7 other papers
2 dated earlier, 5 same year, order not determinable
136970483 (2022 (year only))
S 2 -VER: Semi-Supervised Visual Emotion Recognition
2312.04604 (2023-12)
NeurIPS 2023 Workshop on Adaptive Experimental Design and Active Learning in the Real World Transferable Candidate Proposal with Bounded Uncertainty
aaai_28150 (2024 (year only))
DiDA: Disambiguated Domain Alignment for Cross-Domain Retrieval with Partial Labels
and 4 more not named here
Color 7 other papers
2 dated earlier, 5 same year, order not determinable
136970483 (2022 (year only))
S 2 -VER: Semi-Supervised Visual Emotion Recognition
2312.04604 (2023-12)
NeurIPS 2023 Workshop on Adaptive Experimental Design and Active Learning in the Real World Transferable Candidate Proposal with Bounded Uncertainty
aaai_28150 (2024 (year only))
DiDA: Disambiguated Domain Alignment for Cross-Domain Retrieval with Partial Labels
and 4 more not named here
get_cosine_schedule_with_warmup 2 other papers
1 dated earlier, 1 same year, order not determinable
136970483 (2022 (year only))
S 2 -VER: Semi-Supervised Visual Emotion Recognition
2404.08951 (2024-04)
Constructing and Exploring Intermediate Domains in Mixed Domain Semi-supervised Medical Image Segmentation
get_logger 2 other papers
2 dated earlier
136970483 (2022 (year only))
S 2 -VER: Semi-Supervised Visual Emotion Recognition
2303.11066 (2023-03)
Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data
get_SGD 1 other paper
1 same year, order not determinable
2404.08951 (2024-04)
Constructing and Exploring Intermediate Domains in Mixed Domain Semi-supervised Medical Image 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

While semi-supervised learning (SSL) has yielded promising results, the more realistic SSL scenario remains to be explored, in which the unlabeled data exhibits extremely high recognition difficulty, e.g., fine-grained visual classification in the context of SSL (SS-FGVC). The increased recognition difficulty on fine-grained unlabeled data spells disaster for pseudo-labeling accuracy, resulting in poor performance of the SSL model. To tackle this challenge, we propose Soft Label Selection with Confidence-Aware Clustering based on Class Transition Tracking (SoC) by reconstructing the pseudo-label selection process by jointly optimizing Expansion Objective and Shrinkage Objective, which is based on a soft label manner. Respectively, the former objective encourages soft labels to absorb more candidate classes to ensure the attendance of ground-truth class, while the latter encourages soft labels to reject more noisy classes, which is theoretically proved to be equivalent to entropy minimization. In comparisons with various state-of-the-art methods, our approach demonstrates its superior performance in SS-FGVC. Checkpoints and source code are available at https: //github.com/NJUyued/SoC4SS-FGVC.

For agents

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

get_harvested_code_for_paper("aaai_29068")
get_code_for_paper("aaai_29068")
have("aaai_29068")

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

curl https://syntology.ai/api/ran/aaai_29068.json

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

[![Syntology run record](https://syntology.ai/api/ran/aaai_29068.svg)](https://syntology.ai/paper/aaai_29068)

Connect an agent — have() is free.