SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.04604 · NeurIPS · 2023

NeurIPS 2023 Workshop on Adaptive Experimental Design and Active Learning in the Real World Transferable Candidate Proposal with Bounded Uncertainty

Kyeongryeol Go

arXiv · PDF · Open in the Atlas

Code that ran

11 of 21 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 1 has no contract verdict; 9 failures of our instrument; 10 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2312.04604.json · badge: /api/ran/2312.04604.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
gokyeongryeol/TBU canonical (classifier label)
classifier basis: census
9 ran · 5 no recorded run
gokyeongryeol/tbu canonical (classifier label)
classifier basis: classifier_2025
2 ran · 5 no recorded run
FunctionStatusWhere it lives
AutoContrast Ran
ran; our contract draft was wrong, not the code
gokyeongryeol/TBU/active/dataset/augment.py
code served (permissive licence) · get_code("4d1221a0588c0703")
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 torch
import numpy as np
from PIL import Image

# Create a small PIL Image object
# AutoContrast expects a PIL Image and ignores the second parameter
img_array = np.random.randint(0, 256, (32, 32, 3), dtype=np.uint8)
pil_img = Image.fromarray(img_array, mode='RGB')

ARGS = {
    'img': pil_img,
    '_': None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch — 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)
gokyeongryeol/TBU/active/dataset/augment.py
code served (permissive licence) · get_code("c83f67dd85072e2d")
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.Image
import PIL.ImageEnhance
import numpy as np

# Create a small PIL Image object
img_array = np.random.randint(0, 256, (10, 10, 3), dtype=np.uint8)
img = PIL.Image.fromarray(img_array, mode='RGB')

# Define brightness enhancement factor (must be >= 0.0)
v = 1.5

ARGS = {
    'img': img,
    'v': v
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — 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
Color Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gokyeongryeol/TBU/active/dataset/augment.py
code served (permissive licence) · get_code("8fa703bbf4bd406f")
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.Image
import PIL.ImageEnhance
import numpy as np

# Create a small test image
img_array = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)
img = PIL.Image.fromarray(img_array)

# Define arguments
ARGS = {
    'img': img,
    'v': 1.5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — 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
compute_metric Ran
ran; our contract draft was wrong, not the code
gokyeongryeol/tbu/active/models/train_utils.py
code served (permissive licence) · get_code("92b61b67ddcc3a83")
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 tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Analyze the function:
# - nLab: appears to be unused in the function body
# - true: used as indices, should be a 1D tensor of class labels
# - prob: used with .max(dim=1)[1] to get predictions, and indexed as prob[range(len(prob)), true]
#         so it should be a 2D tensor of shape (batch_size, num_classes)

batch_size = 2
num_classes = 4

# Create valid arguments
nLab = num_classes  # number of labels/classes
true = torch.tensor([0, 2], dtype=torch.long)  # true labels for batch of 2
prob = torch.softmax(torch.randn(batch_size, num_classes), dim=1)  # probabilities (batch_size x num_classes)

ARGS = {
    "nLab": nLab,
    "true": true,
    "prob": prob,
}
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 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
ema_thres_update Ran
ran, violated the contract we drafted
gokyeongryeol/TBU/active/models/train_utils.py
code served (permissive licence) · get_code("0b9bab4e26b54ad4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 1, dtype family float, shape (4,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# The function performs exponential moving average (EMA) update on a threshold
# It takes three numeric parameters and performs element-wise operations
# thres and thres_ema should be tensors or arrays that support arithmetic operations
# ema_m should be a scalar (momentum/decay parameter)

thres = torch.tensor([0.1, 0.2, 0.3, 0.4], dtype=torch.float32)
thres_ema = torch.tensor([0.15, 0.25, 0.35, 0.45], dtype=torch.float32)
ema_m = 0.9

ARGS = {
    "thres": thres,
    "thres_ema": thres_ema,
    "ema_m": ema_m,
}
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 1, dtype family float, shape (4,) — shape (4,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_dataset_train Ran
ran; our contract draft was wrong, not the code
gokyeongryeol/TBU/active/dataset/data.py
code served (permissive licence) · get_code("62292de77b72d38e")
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)

class MockData:
    def get_labeled_data(self):
        # Return a simple dataset (list of tuples)
        return [
            (torch.randn(4), torch.tensor(0)),
            (torch.randn(4), torch.tensor(1))
        ]
    
    def get_unlabeled_data(self, use_ws=False):
        # Return a tuple where index [1] is the unlabeled dataset
        unlabeled = [
            (torch.randn(4), torch.tensor(-1)),
            (torch.randn(4), torch.tensor(-1))
        ]
        return (None, unlabeled)

class MockArgs:
    def __init__(self, semi=False):
        self.semi = semi

# Test with semi=True to exercise the conditional
data = MockData()
args = MockArgs(semi=True)

ARGS = {
    "data": data,
    "args": args
}
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
get_dataset_valid Ran
ran; our contract draft was wrong, not the code
gokyeongryeol/TBU/active/dataset/data.py
code served (permissive licence) · get_code("51d821f3a4dce07f")
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. 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)

class MockData:
    def __init__(self):
        self.valid_data = [
            (torch.randn(2, 4), torch.randint(0, 2, (2,))),
            (torch.randn(2, 4), torch.randint(0, 2, (2,)))
        ]
    
    def get_valid_data(self):
        return self.valid_data

data = MockData()

ARGS = {
    "data": data
}
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 list — a list 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
hard_masking Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gokyeongryeol/tbu/active/models/train_utils.py
code served (permissive licence) · get_code("0a3b40f70517db28")
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 Tensor, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Build a minimal model that satisfies the function's usage
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.ema_g = torch.tensor([0.8, 0.7, 0.9, 0.6])
        self.ema_l = torch.tensor([0.5, 0.4, 0.6, 0.3])
    
    def eval(self):
        return self

class MinimalEMAModel(nn.Module):
    def __init__(self):
        super().__init__()
    
    def predict(self, x, n_MCdrop=None, pool=False):
        # Return probabilities for each sample in batch
        # x shape: (batch_size, features)
        batch_size = x.shape[0]
        num_classes = 4
        return torch.rand(batch_size, num_classes)

# Build a minimal data loader
# Each batch should be (u_x, _, _, idxs)
class MinimalDataset:
    def __init__(self):
        self.data = [
            (torch.randn(2, 4), None, None, torch.tensor([0, 1])),
            (torch.randn(2, 4), None, None, torch.tensor([2, 3])),
        ]
    
    def __iter__(self):
        return iter(self.data)
    
    def __len__(self):
        return 4

class MinimalLoader:
    def __init__(self):
        self.dataset = MinimalDataset()
    
    def __iter__(self):
        return iter(self.dataset)

# Construct arguments
model = MinimalModel()
ema_model = MinimalEMAModel()
loader_sub = MinimalLoader()
n_MCdrop = 5

ARGS = {
    "loader_sub": loader_sub,
    "model": model,
    "ema_model": ema_model,
    "n_MCdrop": n_MCdrop,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float — no output shape is stated: observe_signature.py could not observe it (call:AssertionError)
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
init_centers Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gokyeongryeol/TBU/active/selection/badge.py
code served (permissive licence) · get_code("75953c142ae4e662")
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 1, dtype family int; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
from scipy import stats

torch.manual_seed(0)

# Create a small numpy array as input X
# The function expects X to be convertible to a torch.Tensor
# Shape: (5, 3) - 5 samples, 3 dimensions
X = np.random.randn(5, 3).astype(np.float32)

# K is the number of centers to initialize
K = 3

ARGS = {
    "X": X,
    "K": K
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, 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 int — 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
make_loader Ran
ran on a synthesized input
gokyeongryeol/TBU/active/models/trainer.py
code served (permissive licence) · get_code("279d8d05cf132b12")
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 random
import numpy as np
import torch
from torch.utils.data import DataLoader

torch.manual_seed(0)

# Create minimal stand-in datasets
class MinimalDataset:
    def __init__(self, size=10):
        self.size = size
    
    def __len__(self):
        return self.size
    
    def __getitem__(self, idx):
        # Return (x, y) tuple
        return (torch.randn(4), torch.tensor(idx % 2))

# Create minimal args object
class Args:
    def __init__(self):
        self.n_tr_batch = 2
        self.semi = True
        self.mu = 2
        self.n_worker = 0
        self.n_ev_batch = 4

# Instantiate datasets
dataset_lab = MinimalDataset(size=10)
dataset_unlab = MinimalDataset(size=20)
dataset_valid = MinimalDataset(size=8)

# Instantiate args
args = Args()

# Build ARGS dict
ARGS = {
    "dataset_lab": dataset_lab,
    "dataset_unlab": dataset_unlab,
    "dataset_valid": dataset_valid,
    "args": args
}
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, 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
make_scheduler Ran
ran; our contract draft was wrong, not the code
gokyeongryeol/TBU/active/models/trainer.py
code served (permissive licence) · get_code("28c0113be1ca01e1")
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
model = nn.Linear(4, 3)

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

# Create args object with all required attributes
class Args:
    def __init__(self, semi=True):
        self.semi = semi
        self.w_epoch = 100
        self.w_lr = 0.05
        self.lr = 0.1
        self.n_batch = 1000
        self.cycle = 1.0
        self.milestone = [30, 60, 90]
        self.gamma = 0.1

ARGS = {
    "optimizer": optimizer,
    "args": Args(semi=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 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
Architecture Not yet run
unverified (harvested, no recorded run)
gokyeongryeol/tbu/active/selection/strategy.py
code served (permissive licence) · get_code("9ee7db2b8fa19d16")
How it ran

no invocation recorded.

BaseModel Not yet run
unverified (harvested, no recorded run)
gokyeongryeol/tbu/active/selection/strategy.py
code served (permissive licence) · get_code("d6be60152ea57197")
How it ran

no invocation recorded.

Laplace Not yet run
unverified (harvested, no recorded run)
gokyeongryeol/tbu/active/selection/strategy.py
code served (permissive licence) · get_code("bf32d8572c0843cb")
How it ran

no invocation recorded.

Strategy Not yet run
unverified (harvested, no recorded run)
gokyeongryeol/tbu/active/selection/strategy.py
code served (permissive licence) · get_code("f71b931ef7fcb1e3")
How it ran

no invocation recorded.

ema_thres_update Not yet run
unverified (harvested, no recorded run)
gokyeongryeol/tbu/active/models/train_utils.py
code served (permissive licence) · get_code("7441d4dcb7a2f492")
How it ran

no invocation recorded. this sample carries JSON test cases instead of a setup block; get_reference_implementation serves them with the level they back.

get_transform Not yet run
unverified (harvested, no recorded run)
gokyeongryeol/TBU/active/dataset/data_utils.py
code served (permissive licence) · get_code("50d9500f54e43bd3")
How it ran

no invocation recorded.

make_ema_model Not yet run
unverified (harvested, no recorded run)
gokyeongryeol/TBU/active/models/model_factory.py
code served (permissive licence) · get_code("f3b4f1ca365fd45e")
How it ran

no invocation recorded.

make_model Not yet run
unverified (harvested, no recorded run)
gokyeongryeol/TBU/active/models/model_factory.py
code served (permissive licence) · get_code("181e3925fb15dca8")
How it ran

no invocation recorded.

prepare_data Not yet run
unverified (harvested, no recorded run)
gokyeongryeol/TBU/active/dataset/data.py
code served (permissive licence) · get_code("d4ab69f9179216c0")
How it ran

no invocation recorded.

train_model Not yet run
unverified (harvested, no recorded run)
gokyeongryeol/TBU/active/models/trainer.py
code served (permissive licence) · get_code("10e0b8b620b79988")
How it ran

no invocation recorded.

Also present in other papers' code

Of 21 samples lifted from this paper's linked repositories, 21 carry a function identity and 0 do not. Of the 20 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 17 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
AutoContrast 14 other papers
8 dated earlier, 6 later · 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
1 dated earlier, 6 later
136970483 (2022 (year only))
S 2 -VER: Semi-Supervised Visual Emotion Recognition
aaai_28150 (2024 (year only))
DiDA: Disambiguated Domain Alignment for Cross-Domain Retrieval with Partial Labels
aaai_29068 (2024 (year only))
Roll with the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning
and 4 more not named here
Color 7 other papers
1 dated earlier, 6 later
136970483 (2022 (year only))
S 2 -VER: Semi-Supervised Visual Emotion Recognition
aaai_28150 (2024 (year only))
DiDA: Disambiguated Domain Alignment for Cross-Domain Retrieval with Partial Labels
aaai_29068 (2024 (year only))
Roll with the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning
and 4 more not named here

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

From an empirical perspective, the subset chosen through active learning cannot guarantee an advantage over random sampling when transferred to another model. While it underscores the significance of verifying transferability, experimental design from previous works often neglected that the informativeness of a data subset can change over model configurations. To tackle this issue, we introduce a new experimental design, coined as Candidate Proposal, to find transferable data candidates from which active learning algorithms choose the informative subset. Correspondingly, a data selection algorithm is proposed, namely Transferable candidate proposal with Bounded Uncertainty (TBU), which constrains the pool of transferable data candidates by filtering out the presumably redundant data points based on uncertainty estimation. We verified the validity of TBU in image classification benchmarks, including CIFAR-10/100 and SVHN. When transferred to different model configurations, TBU consistency improves performance in existing active learning algorithms. Our code is available at https://github.com/gokyeongryeol/TBU.

For agents

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

get_harvested_code_for_paper("2312.04604")
get_code_for_paper("2312.04604")
have("2312.04604")

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

curl https://syntology.ai/api/ran/2312.04604.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.04604.svg)](https://syntology.ai/paper/2312.04604)

Connect an agent — have() is free.