SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.06815 · 2020

Class-Imbalanced Semi-Supervised Learning

arXiv · PDF · Open in the Atlas

Code that ran

15 of 18 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, 1 violated it and 9 have no contract verdict; 5 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/2002.06815.json · badge: /api/ran/2002.06815.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
MinsungHyun/Class-Imbalanced-Semi-Supervised-Learning canonical (classifier label)
classifier basis: census
15 ran · 3 no recorded run
FunctionStatusWhere it lives
cnn13 Ran
ran; our contract draft was wrong, not the code
MinsungHyun/Class-Imbalanced-Semi-Supervised-Learning/CISSL_cls/lib/lenet.py
code served (permissive licence) · get_code("a6af49de6105f2aa")
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 CNN13. 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 = {
    "num_classes": 10,
    "dropout": 0.5,
}
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 CNN13 — a CNN13 output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CNN13 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
MinsungHyun/Class-Imbalanced-Semi-Supervised-Learning/CISSL_cls/lib/wrn.py
code served (permissive licence) · get_code("a4917ae1314a3442")
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 = {
    "i_c": 3,
    "o_c": 16,
    "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
learn_mine Ran
ran on a synthesized input
MinsungHyun/Class-Imbalanced-Semi-Supervised-Learning/CISSL_cls/lib/mi.py
code served (permissive licence) · get_code("a1d8ac416c2d60b7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import torch.optim as optim

torch.manual_seed(0)

# Build a simple neural network for mine_net
class MineNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.net = nn.Sequential(
            nn.Linear(4, 8),
            nn.ReLU(),
            nn.Linear(8, 1)
        )
    
    def forward(self, x):
        return self.net(x)

# Create instances
mine_net = MineNet()
mine_net_optim = optim.Adam(mine_net.parameters(), lr=0.01)

# Create batch with joint and marginal tensors
# joint: samples from joint distribution
# marginal: samples from marginal distribution
joint = torch.randn(2, 4)
marginal = torch.randn(2, 4)
batch = (joint, marginal)

# Initialize ma_et (moving average of e^t)
ma_et = torch.tensor(1.0)

ARGS = {
    "batch": batch,
    "mine_net": mine_net,
    "mine_net_optim": mine_net_optim,
    "ma_et": ma_et,
    "ma_rate": 0.01
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
mixup_criterion Ran
ran on a synthesized input
MinsungHyun/Class-Imbalanced-Semi-Supervised-Learning/CISSL_cls/lib/utils.py
code served (permissive licence) · get_code("79edc1957c1e3747")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# y_a and y_b are target tensors for mixup
# They should be class indices for classification
y_a = torch.tensor([0, 1], dtype=torch.long)
y_b = torch.tensor([1, 0], dtype=torch.long)

# lam is the mixup coefficient (between 0 and 1)
lam = 0.7

ARGS = {
    "y_a": y_a,
    "y_b": y_b,
    "lam": lam,
}
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
mixup_data Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
MinsungHyun/Class-Imbalanced-Semi-Supervised-Learning/CISSL_cls/lib/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from Ryoo72/dimension-wise_mixup, is pointer only (licence: NOASSERTION) · get_code("b062bea460457feb")
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 Ryoo72/dimension-wise_mixup, 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.

mixup_data_sup Ran
ran on a synthesized input
MinsungHyun/Class-Imbalanced-Semi-Supervised-Learning/CISSL_cls/lib/utils.py
code served (permissive licence) · get_code("d106bc2c1e37b5d0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)
np.random.seed(0)

# Create small tensors for x and y
x = torch.randn(2, 4)  # batch_size=2, features=4
y = torch.tensor([0, 1])  # batch_size=2, class labels

# Define ARGS dict with all parameters
ARGS = {
    "x": x,
    "y": y,
    "alpha": 1.0
}
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 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
multibox Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
MinsungHyun/Class-Imbalanced-Semi-Supervised-Learning/CISSL_det/csd.py
code served (permissive licence) · get_code("b490ac8699f5a7ad")
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 tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# First, we need to create a VGG configuration and build the vgg layers
vgg_cfg = [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'C', 512, 512, 512, 'M', 512, 512, 512]

def vgg(cfg, i, batch_norm=False):
    layers = []
    in_channels = i
    for v in cfg:
        if v == 'M':
            layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
        elif v == 'C':
            layers += [nn.MaxPool2d(kernel_size=2, stride=2, ceil_mode=True)]
        else:
            conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
            if batch_norm:
                layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
            else:
                layers += [conv2d, nn.ReLU(inplace=True)]
            in_channels = v
    pool5 = nn.MaxPool2d(kernel_size=3, stride=1, padding=1)
    conv6 = nn.Conv2d(512, 1024, kernel_size=3, padding=6, dilation=6)
    conv7 = nn.Conv2d(1024, 1024, kernel_size=1)
    layers += [pool5, conv6, nn.ReLU(inplace=True), conv7, nn.ReLU(inplace=True)]
    return layers

# Build vgg layers
vgg_layers = vgg(vgg_cfg, 3, batch_norm=False)

# Create extra_layers - these should be conv layers with out_channels attribute
# The function accesses extra_layers[1::2] (every other element starting from index 1)
# and expects them to have .out_channels
extra_layers = [
    nn.Conv2d(1024, 256, kernel_size=1),
    nn.Conv2d(256, 512, kernel_size=3, stride=2, padding=1),
    nn.Conv2d(512, 128, kernel_size=1),
    nn.Conv2d(128, 256, kernel_size=3, stride=2, padding=1),
]

# cfg is a list of numbers representing the number of boxes per feature map
# The function expects len(cfg) >= 2 + len(extra_layers[1::2])
# extra_layers[1::2] has length 2, so cfg needs at least 4 elements
cfg = [4, 6, 6, 4]

# num_classes
num_classes = 21

ARGS = {
    'vgg': vgg_layers,
    'extra_layers': extra_layers,
    'cfg': cfg,
    'num_classes': num_classes
}
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 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
mutual_information Ran
ran on a synthesized input
MinsungHyun/Class-Imbalanced-Semi-Supervised-Learning/CISSL_cls/lib/mi.py
code served (permissive licence) · get_code("6d5a151acd8314fc")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a simple neural network that takes a tensor and outputs a scalar
class MineNet(nn.Module):
    def __init__(self, input_dim):
        super().__init__()
        self.net = nn.Sequential(
            nn.Linear(input_dim, 8),
            nn.ReLU(),
            nn.Linear(8, 1)
        )
    
    def forward(self, x):
        return self.net(x)

# Create small tensors with distinct dimensions
# joint: batch_size=2, feature_dim=4
joint = torch.randn(2, 4)

# marginal: batch_size=2, feature_dim=4
marginal = torch.randn(2, 4)

# Create the neural network
mine_net = MineNet(input_dim=4)

ARGS = {
    'joint': joint,
    'marginal': marginal,
    'mine_net': mine_net
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
rampweight Ran
ran on a synthesized input
MinsungHyun/Class-Imbalanced-Semi-Supervised-Learning/CISSL_det/ext/semi_train_mt.py
code served (permissive licence) · get_code("89565071aa64ab3d")
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 math

def rampweight(iteration):
    ramp_up_end = 32000
    ramp_down_start = 100000
    if iteration < ramp_up_end:
        ramp_weight = math.exp(-5 * math.pow(1 - iteration / ramp_up_end, 2))
    elif iteration > ramp_down_start:
        ramp_weight = math.exp(-12.5 * math.pow(1 - (120000 - iteration) / 20000, 2))
    else:
        ramp_weight = 1
    if iteration == 0:
        ramp_weight = 0
    return ramp_weight


ARGS = {
    "iteration": 50000
}
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 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
sample_batch Ran
ran on a synthesized input
MinsungHyun/Class-Imbalanced-Semi-Supervised-Learning/CISSL_cls/lib/mi.py
code served (permissive licence) · get_code("c57d6ed45a1f7842")
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, 60) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small tensor with shape (batch_size, channels, height, width)
# The function expects data.size(0) to work and indexing with [index]
# It also expects data to be indexable and reshapeable
data = torch.randn(2, 3, 4, 5)

ARGS = {
    'data': data,
    'batch_size': 100,
    'sample_mode': 'joint'
}
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, 60) — shape (2, 60) 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
split_imbalance_l_u Ran
ran on a synthesized input
MinsungHyun/Class-Imbalanced-Semi-Supervised-Learning/CISSL_cls/build_dataset.py
code served (permissive licence) · get_code("342ed21ca299d761")
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
import random

# Create a simple training set with images and labels
np.random.seed(0)
random.seed(0)

# Create synthetic data: 12 images, 3 classes (4 images per class)
n_images = 12
n_classes = 3
image_size = 4

images = np.random.randn(n_images, image_size).astype(np.float32)
labels = np.array([0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2])

train_set = {
    'images': images,
    'labels': labels
}

ARGS = {
    'train_set': train_set,
    'n_labels': 6,
    'imb_factor': 1.5,
    'seed': 0,
    'n_unlabels': 6,
    'imb_unlabel': None
}
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
split_imbalance_toy_ul Ran
ran on a synthesized input
MinsungHyun/Class-Imbalanced-Semi-Supervised-Learning/CISSL_cls/build_dataset.py
code served (permissive licence) · get_code("1eea364c84764f2c")
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
import random

# Create a small toy dataset
np.random.seed(0)
random.seed(0)

# Create images: shape (20, 4) - 20 images, 4 features each
images = np.random.randn(20, 4).astype(np.float32)

# Create labels: 4 classes, imbalanced
labels = np.array([0, 0, 0, 0, 0,
                   1, 1, 1, 1,
                   2, 2, 2,
                   3, 3, 3, 3, 3, 3, 3, 3], dtype=np.int64)

# Create train_set dict
train_set = {
    'images': images,
    'labels': labels
}

ARGS = {
    'train_set': train_set,
    'n_labels': 10,
    'imb_factor': 2.0,
    'seed': 0,
    'n_unlabels': 10
}
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
split_trainval Ran
ran on a synthesized input
MinsungHyun/Class-Imbalanced-Semi-Supervised-Learning/CISSL_cls/build_dataset.py
code served (permissive licence) · get_code("32f8691dfa2fc262")
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 numpy as np

# Create a small training set with images and labels
# 2 classes (0 and 1), with 6 samples total (3 per class)
images = np.array([
    [[1, 2, 3, 4], [5, 6, 7, 8]],      # class 0, sample 1
    [[9, 10, 11, 12], [13, 14, 15, 16]],  # class 0, sample 2
    [[17, 18, 19, 20], [21, 22, 23, 24]], # class 0, sample 3
    [[25, 26, 27, 28], [29, 30, 31, 32]], # class 1, sample 1
    [[33, 34, 35, 36], [37, 38, 39, 40]], # class 1, sample 2
    [[41, 42, 43, 44], [45, 46, 47, 48]], # class 1, sample 3
])

labels = np.array([0, 0, 0, 1, 1, 1])

train_set = {
    'images': images,
    'labels': labels
}

num_val = 2  # Request 2 validation samples total (1 per class)

ARGS = {
    'train_set': train_set,
    'num_val': num_val,
}
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, 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
str2bool Ran
ran, violated the contract we drafted
MinsungHyun/Class-Imbalanced-Semi-Supervised-Learning/CISSL_det/ext/semi_train_mt.py
code served (permissive licence) · get_code("25c7475539e39da4")
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 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 torch

def str2bool(v):
    return v.lower() in ('yes', 'true', 't', '1')

ARGS = {
    'v': 'true'
}
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 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
vgg Ran
ran; our contract draft was wrong, not the code
MinsungHyun/Class-Imbalanced-Semi-Supervised-Learning/CISSL_det/csd.py
code served (permissive licence) · get_code("6921f7ed00595a4f")
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 list, 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 torch.nn as nn

torch.manual_seed(0)

# The function expects:
# - cfg: a list/tuple containing integers (number of channels) and strings 'M' or 'C' for pooling
# - i: integer representing input channels
# - batch_norm: boolean flag

# Looking at the function body, cfg is iterated over and can contain:
# - 'M' or 'C' for MaxPool2d layers
# - integers for Conv2d output channels
# The function builds a VGG-style network

# Create a simple configuration
cfg = [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'C', 512, 512, 512, 'M', 512, 512, 512]

# Input channels (typically 3 for RGB images)
i = 3

# Batch normalization flag
batch_norm = False

ARGS = {
    'cfg': cfg,
    'i': i,
    'batch_norm': batch_norm
}
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 list, ndim 1, 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
add_extras Not yet run
unverified (harvested, no recorded run)
MinsungHyun/Class-Imbalanced-Semi-Supervised-Learning/CISSL_det/csd.py
code served (permissive licence) · get_code("a73c255a822431a2")
How it ran

no invocation recorded.

create_vis_plot Not yet run
unverified (harvested, no recorded run)
MinsungHyun/Class-Imbalanced-Semi-Supervised-Learning/CISSL_det/ext/semi_train_mt.py
code served (permissive licence) · get_code("567ece0b1b81daa6")
How it ran

no invocation recorded.

mlp Not yet run
unverified (harvested, no recorded run)
MinsungHyun/Class-Imbalanced-Semi-Supervised-Learning/CISSL_cls/lib/mlp.py
code served (permissive licence) · get_code("2a826909e901934c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 9 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 7 later) and 9 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
str2bool 23 other papers
10 dated earlier, 13 later
1410.5401 (2014-10)
Neural Turing Machines
1502.04623 (2015-02)
DRAW: A Recurrent Neural Network For Image Generation
1504.06852 (2015-04)
FlowNet: Learning Optical Flow with Convolutional Networks
and 20 more not named here
vgg 11 other papers
9 dated earlier, 2 later
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1512.02325 (2015-12)
SSD: Single Shot MultiBox Detector
1611.08563 (2016-11)
Online Real-time Multiple Spatiotemporal Action Localisation and Prediction
and 8 more not named here
multibox 6 other papers
4 dated earlier, 2 later
1512.02325 (2015-12)
SSD: Single Shot MultiBox Detector
1908.07129 (2019-08)
Zero-Shot Grounding of Objects from Natural Language Queries
1911.10033 (2019-11)
Domain Adaptation for Object Detection via Style Consistency
and 3 more not named here
conv3x3 3 other papers
3 later
2106.00209 (2021-06)
Rethinking Re-Sampling in Imbalanced Semi-Supervised Learning
2112.04564 (2021-12)
CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learning
2403.10391 (2024-03)
CDMAD: Class-Distribution-Mismatch-Aware Debiasing for Class-Imbalanced Semi-Supervised Learning
add_extras 1 other paper
1 later
2006.02158 (2020-06)
Interpolation-based semi-supervised learning for object detection
cnn13 1 other paper
1 dated earlier
2001.06001 (2020-01)
Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning
create_vis_plot 1 other paper
1 later
2006.02158 (2020-06)
Interpolation-based semi-supervised learning for object detection
mixup_criterion 1 other paper
1 later
2207.13378 (2022-07)
Identifying Hard Noise in Long-Tailed Sample Distribution
mixup_data 1 other paper
1 dated earlier
1710.09412 (2017-10)
mixup: BEYOND EMPIRICAL RISK MINIMIZATION

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

Semi-Supervised Learning (SSL) has achieved great success in overcoming the difficulties of labeling and making full use of unlabeled data. However, SSL has a limited assumption that the numbers of samples in different classes are balanced, and many SSL algorithms show lower performance for the datasets with the imbalanced class distribution. In this paper, we introduce a task of class-imbalanced semi-supervised learning (CISSL), which refers to semi-supervised learning with class-imbalanced data. In doing so, we consider class imbalance in both labeled and unlabeled sets. First, we analyze existing SSL methods in imbalanced environments and examine how the class imbalance affects SSL methods. Then we propose Suppressed Consistency Loss (SCL), a regularization method robust to class imbalance. Our method shows better performance than the conventional methods in the CISSL environment. In particular, the more severe the class imbalance and the smaller the size of the labeled data, the better our method performs.

For agents

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

get_harvested_code_for_paper("2002.06815")
get_code_for_paper("2002.06815")
have("2002.06815")

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

curl https://syntology.ai/api/ran/2002.06815.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.06815.svg)](https://syntology.ai/paper/2002.06815)

Connect an agent — have() is free.