SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.11066 · CVPR · 2023

Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data

Yuhao Chen, Xin Tan, Xuequan Lu, Jiajun Liang, Borui Zhao, Renjie Song, Zhaowei Chen

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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 5 have no contract verdict; 0 failures of our instrument; 0 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/2303.11066.json · badge: /api/ran/2303.11066.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
megvii-research/FullMatch canonical (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
FunctionStatusWhere it lives
adjust_learning_rate Ran
ran on a synthesized input
megvii-research/FullMatch/train_utils.py
code served (permissive licence) · get_code("9651662a8cedbe73")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from torch.optim import SGD
import math

torch.manual_seed(0)

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

# Create an optimizer
optimizer = SGD(model.parameters(), lr=0.03)

# Define arguments for adjust_learning_rate
ARGS = {
    'optimizer': optimizer,
    'current_step': 5,
    'num_training_steps': 100,
    'num_cycles': 7.0 / 16.0,
    'num_warmup_steps': 10,
    'base_lr': 0.03
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_logger Ran
ran on a synthesized input
megvii-research/FullMatch/utils.py
code served (permissive licence) · get_code("f134f238fbf660cc")
How it ran

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

import os
import logging
import tempfile

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

ARGS = {
    'name': 'test_logger',
    'save_path': temp_dir,
    'level': 'INFO'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
net_builder Ran
ran on a synthesized input
megvii-research/FullMatch/utils.py
code served (permissive licence) · get_code("2ed8b93c17cf7375")
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 Mock. 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 unittest.mock import Mock

torch.manual_seed(0)

# Create a minimal builder class that has the required interface
class MockBuilder:
    def __init__(self):
        self.some_attr = None
        self.another_attr = None
    
    def build(self):
        # Return a minimal nn.Module
        return nn.Linear(4, 3)

# Create a mock net module with build_WideResNet function
class MockNetModule:
    @staticmethod
    def build_WideResNet():
        return MockBuilder()

# Patch the import to avoid actual file imports
import sys
mock_net_module = MockNetModule()
sys.modules['models'] = Mock()
sys.modules['models.nets'] = Mock()
sys.modules['models.nets.wrn'] = mock_net_module

# Define the arguments
ARGS = {
    'net_name': 'WideResNet',
    'from_name': False,
    'net_conf': {
        'depth': 28,
        'widen_factor': 10,
        'dropout_rate': 0.3
    },
    'is_remix': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
models, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Mock — a Mock 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
sample_labeled_data Ran
ran on a synthesized input
megvii-research/FullMatch/datasets/data_utils.py
code served (permissive licence) · get_code("6347b368d978a7fd")
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 math

# Set random seed for reproducibility
np.random.seed(0)

# Create a small stand-in class for args
class Args:
    def __init__(self):
        self.batch_size = 2
        self.world_size = 2
        self.num_eval_iter = 3

args = Args()

# Create small numpy arrays for data and target
# data: shape (10, 4) - 10 samples, 4 features
data = np.random.randn(10, 4).astype(np.float32)

# target: shape (10,) - 10 labels, values in range [0, 1, 2] for 3 classes
target = np.array([0, 0, 0, 0, 1, 1, 1, 2, 2, 2], dtype=np.int32)

# Parameters
num_labels = 6  # 2 labels per class
num_classes = 3

# index parameter (None for the main case, but can be provided)
index = None

# name parameter
name = None

ARGS = {
    "args": args,
    "data": data,
    "target": target,
    "num_labels": num_labels,
    "num_classes": num_classes,
    "index": index,
    "name": name
}
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_ssl_data Ran
ran on a synthesized input
megvii-research/FullMatch/datasets/data_utils.py
code served (permissive licence) · get_code("5d7b58a4dd56f54f")
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 math

# Create small test data
np.random.seed(0)
num_samples = 10
num_classes = 2
num_features = 4

# Create synthetic data and targets
data = np.random.randn(num_samples, num_features).astype(np.float32)
target = np.array([0, 0, 0, 0, 0, 1, 1, 1, 1, 1], dtype=np.int32)

# Create args object with required attributes
class Args:
    def __init__(self):
        self.batch_size = 2
        self.world_size = 1
        self.num_eval_iter = 4
        self.uratio = 2

args = Args()

# Define the ARGS dictionary with all parameters for split_ssl_data
ARGS = {
    'args': args,
    'data': data,
    'target': target,
    'num_labels': 4,
    'num_classes': 2,
    'index': None,
    'include_lb_to_ulb': True
}
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
str2bool Ran
ran, violated the contract we drafted
megvii-research/FullMatch/utils.py
code served (permissive licence) · get_code("8605dc8a088f3db8")
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 argparse

def str2bool(v):
    if isinstance(v, bool):
        return v
    if v.lower() in ('yes', 'true', 't', 'y', '1'):
        return True
    elif v.lower() in ('no', 'false', 'f', 'n', '0'):
        return False
    else:
        raise argparse.ArgumentTypeError('Boolean value expected.')

# Test cases for the str2bool function
ARGS = {
    'v': 'true'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 2 later) and 4 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 175 other papers
64 dated earlier, 2 the same month, 106 later, 3 same year, order not determinable · 2 only as an assembly brick
1406.6247 (2014-06)
Recurrent Models of Visual Attention
1603.09382 (2016-03)
Deep Networks with Stochastic Depth
1710.10196 (2017-10)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
and 172 more not named here
get_logger 2 other papers
1 dated earlier, 1 later
136970483 (2022 (year only))
S 2 -VER: Semi-Supervised Visual Emotion Recognition
aaai_29068 (2024 (year only))
Roll with the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained 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 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Semi-supervised learning (SSL) has attracted enormous attention due to its vast potential of mitigating the dependence on large labeled datasets. The latest methods (e.g., FixMatch) use a combination of consistency regularization and pseudo-labeling to achieve remarkable successes. However, these methods all suffer from the waste of complicated examples since all pseudo-labels have to be selected by a high threshold to filter out noisy ones. Hence, the examples with ambiguous predictions will not contribute to the training phase. For better leveraging all unlabeled examples, we propose two novel techniques: Entropy Meaning Loss (EML) and Adaptive Negative Learning (ANL). EML incorporates the prediction distribution of non-target classes into the optimization objective to avoid competition with target class, and thus generating more high-confidence predictions for selecting pseudo-label. ANL introduces the additional negative pseudo-label for all unlabeled data to leverage low-confidence examples. It adaptively allocates this label by dynamically evaluating the top-k performance of the model. EML and ANL do not introduce any additional parameter and hyperparameter. We integrate these techniques with FixMatch, and develop a simple yet powerful framework called FullMatch. Extensive experiments on several common SSL benchmarks (CIFAR-10/100, SVHN, STL-10 and ImageNet) demonstrate that FullMatch exceeds FixMatch by a large margin. Integrated with FlexMatch (an advanced FixMatch-based framework), we achieve state-of-the-art performance. Source code is available at https://github.com/megvii-research/FullMatch.

For agents

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

get_harvested_code_for_paper("2303.11066")
get_code_for_paper("2303.11066")
have("2303.11066")

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

curl https://syntology.ai/api/ran/2303.11066.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.11066.svg)](https://syntology.ai/paper/2303.11066)

Connect an agent — have() is free.