SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2001.06001 · 2020

Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning

arXiv · PDF · Open in the Atlas

Code that ran

17 of 20 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, 0 violated it and 7 have no contract verdict; 8 failures of our instrument; 3 no recorded run), measured 2026-11-21; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2001.06001.json · badge: /api/ran/2001.06001.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
uvavision/Curriculum-Labeling canonical (classifier label)
classifier basis: census
17 ran · 3 no recorded run
FunctionStatusWhere it lives
ShearX Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
uvavision/Curriculum-Labeling/utils/augmentations.py
code served (permissive licence) · get_code("b92936d1f2ac3e6c")
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 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 random
import PIL
import PIL.Image
import PIL.ImageOps
import PIL.ImageEnhance
import PIL.ImageDraw

# Create a simple PIL Image for testing
# Create a small 4x3 RGB image
img = PIL.Image.new('RGB', (4, 3), color=(255, 0, 0))

# Define ARGS with all parameters for ShearX
ARGS = {
    'img': img,
    'v': 0.15
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
ShearY Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
uvavision/Curriculum-Labeling/utils/augmentations.py
code served (permissive licence) · get_code("008c64b77c4ae4c9")
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 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 random
import PIL
import PIL.Image
import PIL.ImageOps
import PIL.ImageEnhance
import PIL.ImageDraw

# Create a simple PIL Image for testing
# Create a small RGB image (4x3 pixels)
img = PIL.Image.new('RGB', (4, 3), color='red')

# Define ARGS with all parameters for ShearY
ARGS = {
    'img': img,
    'v': 0.15
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
TranslateX Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
uvavision/Curriculum-Labeling/utils/augmentations.py
code served (permissive licence) · get_code("ab50d5bbcf589623")
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 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 random
import PIL
import PIL.Image
import PIL.ImageOps
import PIL.ImageEnhance
import PIL.ImageDraw

# Create a simple PIL Image for testing
# Create a small RGB image (100x80 pixels)
img = PIL.Image.new('RGB', (100, 80), color='red')

# Define ARGS dict with all parameters
ARGS = {
    'img': img,
    'v': 0.3
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
WRN28_10 Ran
ran on a synthesized input
uvavision/Curriculum-Labeling/models/wideresnet.py
code served (permissive licence) · get_code("6aab213500e32db8")
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 Wide_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)

# The function WRN28_10 takes num_classes and dropout as parameters
# num_classes: int specifying number of output classes
# dropout: float specifying dropout rate

ARGS = {
    "num_classes": 10,
    "dropout": 0.0,
}
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 Wide_ResNet — a Wide_ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Wide_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
WRN28_2 Ran
ran on a synthesized input
uvavision/Curriculum-Labeling/models/wideresnet.py
code served (permissive licence) · get_code("5d1b43bed0430f20")
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 Wide_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)

ARGS = {
    "num_classes": 10,
    "dropout": 0.0,
}
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 Wide_ResNet — a Wide_ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Wide_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
apply_zca Ran
ran on a synthesized input
uvavision/Curriculum-Labeling/utils/dataloaders.py
code served (permissive licence) · get_code("071a33a07294a3b4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (2, 4, 3, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Create small sample data
# Shape: (batch_size, channels, height, width) = (2, 4, 3, 5)
data = torch.randn(2, 4, 3, 5).float()

# Create ZCA mean - should match flattened feature dimension
# Flattened size: 4 * 3 * 5 = 60
zca_mean = np.random.randn(60)

# Create ZCA components - should be (feature_dim, feature_dim)
# Shape: (60, 60)
zca_components = np.random.randn(60, 60).astype(np.float32)

ARGS = {
    "data": data,
    "zca_mean": zca_mean,
    "zca_components": zca_components
}
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 Tensor, ndim 4, dtype family float, shape (2, 4, 3, 5) — shape (2, 4, 3, 5) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
autoaug2arsaug Ran
ran; our contract draft was wrong, not the code
uvavision/Curriculum-Labeling/utils/archive.py
code served (permissive licence) · get_code("da679b4529854997")
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 numpy as np
from collections import defaultdict

def get_augment(name):
    """Mock function that returns (augment_func, low, high) for each augmentation"""
    augment_ranges = {
        'ShearX': (None, 0.0, 0.3),
        'ShearY': (None, 0.0, 0.3),
        'TranslateX': (None, 0.0, 10),
        'TranslateY': (None, 0.0, 10),
        'Rotate': (None, 0.0, 30),
        'Solarize': (None, 0.0, 256),
        'Posterize2': (None, 0.0, 4),
        'Contrast': (None, 0.1, 1.9),
        'Color': (None, 0.1, 1.9),
        'Brightness': (None, 0.1, 1.9),
        'Sharpness': (None, 0.1, 1.9),
        'CutoutAbs': (None, 0.0, 20),
    }
    return augment_ranges.get(name, (None, 0.0, 1.0))

def sample_policies():
    """Mock function that returns policies in the format expected by autoaug2arsaug"""
    # Each policy is a list of (name, probability, level) tuples
    policies = [
        [
            ('ShearX', 0.5, 3),
            ('Rotate', 0.8, 5),
        ],
        [
            ('Color', 0.6, 7),
            ('Brightness', 0.4, 2),
        ],
    ]
    return policies

def f():
    """Function that returns policies"""
    return sample_policies()

ARGS = {
    'f': f,
}
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 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
castClasses Ran
ran on a synthesized input
uvavision/Curriculum-Labeling/methods/entropy/curriculum_labeling_eval.py
code served (permissive licence) · get_code("edac169ce303f83f")
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 int, 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)

# The function expects 'targets' which is iterable and contains numeric values
# It iterates through targets, subtracts 2 from each element, and stores in a tensor
# targets should be a list or tensor-like of numeric values

targets = [5, 7, 3, 9]

ARGS = {
    "targets": targets
}
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 int, 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
cnn13 Ran
ran; our contract draft was wrong, not the code
uvavision/Curriculum-Labeling/models/lenet.py
code served (permissive licence) · get_code("17edc50738edda68")
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
uvavision/Curriculum-Labeling/models/wideresnet.py
pointer only (licence: MIT); the stored copy get_code serves, from DaikiTanak/manifold_mixup, is pointer only (licence: NONE) · get_code("00e569acd6b45ef0")
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 DaikiTanak/manifold_mixup, 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
uvavision/Curriculum-Labeling/models/resnet.py
code served (permissive licence) · get_code("dd1114865f06f0fd")
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
from torch import nn

torch.manual_seed(0)

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
denorm Ran
ran; our contract draft was wrong, not the code
uvavision/Curriculum-Labeling/utils/dataloaders.py
pointer only (licence: MIT); the stored copy get_code serves, from ilyak93/SinGan, is pointer only (licence: NOASSERTION) · get_code("289ace78904e68a8")
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 ilyak93/SinGan, 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.

float_parameter Ran
ran, honoured the contract we drafted
uvavision/Curriculum-Labeling/utils/archive.py
pointer only (licence: MIT); the stored copy get_code serves, from chenchenzong/dpc, is pointer only (licence: NONE) · get_code("40d3c39a403ae1f7")
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 chenchenzong/dpc, 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.

int_parameter Ran
ran, honoured the contract we drafted
uvavision/Curriculum-Labeling/utils/archive.py
pointer only (licence: MIT); the stored copy get_code serves, from chenchenzong/dpc, is pointer only (licence: NONE) · get_code("7900a3a6deef908b")
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 chenchenzong/dpc, 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.

softmax_kl_loss Ran
ran on a synthesized input
uvavision/Curriculum-Labeling/utils/losses.py
code served (permissive licence) · get_code("1702794d89949977")
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 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.functional as F

torch.manual_seed(0)

# Create two small logit tensors with batch size 2 and 4 classes
batch_size = 2
num_classes = 4

input_logits = torch.randn(batch_size, num_classes)
target_logits = torch.randn(batch_size, num_classes)

ARGS = {
    "input_logits": input_logits,
    "target_logits": target_logits,
}
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 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
softmax_mse_loss Ran
ran on a synthesized input
uvavision/Curriculum-Labeling/utils/losses.py
code served (permissive licence) · get_code("8b19d99a6e799176")
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 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
from torch.nn import functional as F

torch.manual_seed(0)

# Create small logit tensors
# batch_size=2, num_classes=4
input_logits = torch.randn(2, 4)
target_logits = torch.randn(2, 4)

ARGS = {
    'input_logits': input_logits,
    'target_logits': target_logits,
}
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 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
symmetric_mse_loss Ran
ran on a synthesized input
uvavision/Curriculum-Labeling/utils/losses.py
code served (permissive licence) · get_code("d75345cece6fcc81")
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 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

torch.manual_seed(0)

# Create two small tensors with the same shape
# batch_size=2, num_classes=4
input1 = torch.randn(2, 4, requires_grad=True)
input2 = torch.randn(2, 4, requires_grad=True)

ARGS = {
    "input1": input1,
    "input2": input2,
}
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 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
getNetwork Not yet run
unverified (harvested, no recorded run)
uvavision/Curriculum-Labeling/methods/entropy/curriculum_labeling_eval.py
code served (permissive licence) · get_code("a7892ed042f9619a")
How it ran

no invocation recorded.

load_data_subsets Not yet run
unverified (harvested, no recorded run)
uvavision/Curriculum-Labeling/utils/dataloaders.py
code served (permissive licence) · get_code("7977f67858e013e2")
How it ran

no invocation recorded.

validate Not yet run
unverified (harvested, no recorded run)
uvavision/Curriculum-Labeling/methods/entropy/curriculum_labeling_eval.py
code served (permissive licence) · get_code("7b176dbcc79454ff")
How it ran

no invocation recorded.

Also present in other papers' code

Of 20 samples lifted from this paper's linked repositories, 20 carry a function identity and 0 do not. Of the 20 distinct functions with an identity, 11 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 1 the same month, 11 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
conv3x3 686 other papers
182 dated earlier, 4 the same month, 499 later, 1 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
conv3x3 74 other papers
13 dated earlier, 61 later · 5 only as an assembly brick
1605.07146 (2016-05)
Wide Residual Networks
1707.01629 (2017-07)
Dual Path Networks
1802.05668 (2018-02)
Model compression via distillation and quantization
and 71 more not named here
float_parameter 15 other papers
6 dated earlier, 9 later
1409.4842 (2014-09)
Going deeper with convolutions
1512.00567 (2015-12)
Rethinking the Inception Architecture for Computer Vision
1608.06993 (2016-08)
Densely Connected Convolutional Networks
and 12 more not named here
ShearX 8 other papers
2 dated earlier, 6 later · 1 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
2005.04373 (2020-05)
AutoCLINT: The Winning Method in AutoCV Challenge 2019
and 5 more not named here
ShearY 8 other papers
2 dated earlier, 6 later · 1 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
2005.04373 (2020-05)
AutoCLINT: The Winning Method in AutoCV Challenge 2019
and 5 more not named here
TranslateX 8 other papers
2 dated earlier, 6 later · 1 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
2005.04373 (2020-05)
AutoCLINT: The Winning Method in AutoCV Challenge 2019
and 5 more not named here
int_parameter 6 other papers
2 dated earlier, 4 later
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
2003.03780 (2020-03)
DADA: Differentiable Automatic Data Augmentation
and 3 more not named here
denorm 5 other papers
1 dated earlier, 4 later
1905.01164 (2019-05)
SinGAN: Learning a Generative Model from a Single Natural Image
2003.11512 (2020-03)
Improved Techniques for Training Single-Image GANs
2110.02900 (2021-10)
Meta Internal Learning
and 2 more not named here
symmetric_mse_loss 2 other papers
1 dated earlier, 1 later
1904.04717 (2019-04)
Label Propagation for Deep Semi-supervised Learning
2006.11280 (2020-06)
Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training
autoaug2arsaug 1 other paper
1 later
2311.01002 (2023-11)
Robust Data Pruning under Label Noise via Maximizing Re-labeling Accuracy
cnn13 1 other paper
1 later
2002.06815 (2020-02)
Class-Imbalanced Semi-Supervised Learning

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

In this paper we revisit the idea of pseudo-labeling in the context of semi-supervised learning where a learning algorithm has access to a small set of labeled samples and a large set of unlabeled samples. Pseudo-labeling works by applying pseudo-labels to samples in the unlabeled set by using a model trained on the combination of the labeled samples and any previously pseudo-labeled samples, and iteratively repeating this process in a self-training cycle. Current methods seem to have abandoned this approach in favor of consistency regularization methods that train models under a combination of different styles of self-supervised losses on the unlabeled samples and standard supervised losses on the labeled samples. We empirically demonstrate that pseudo-labeling can in fact be competitive with the state-of-the-art, while being more resilient to out-of-distribution samples in the unlabeled set. We identify two key factors that allow pseudo-labeling to achieve such remarkable results (1) applying curriculum learning principles and (2) avoiding concept drift by restarting model parameters before each self-training cycle. We obtain 94.91% accuracy on CIFAR-10 using only 4,000 labeled samples, and 68.87% top-1 accuracy on Imagenet-ILSVRC using only 10% of the labeled samples. The code is available at https://github.com/uvavision/Curriculum-Labeling

For agents

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

get_harvested_code_for_paper("2001.06001")
get_code_for_paper("2001.06001")
have("2001.06001")

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

curl https://syntology.ai/api/ran/2001.06001.json

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

[![Syntology run record](https://syntology.ai/api/ran/2001.06001.svg)](https://syntology.ai/paper/2001.06001)

Connect an agent — have() is free.