SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.03006 · 2021

Unsupervised Selective Labeling for More Effective Semi-Supervised Learning

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 5 failures of our instrument; 1 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/2110.03006.json · badge: /api/ran/2110.03006.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
TonyLianLong/UnsupervisedSelectiveLabeling canonical (classifier label)
classifier basis not recorded on the link
7 ran · 1 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
TonyLianLong/UnsupervisedSelectiveLabeling/semisup-fixmatch-cifar/utils.py
code served (permissive licence) · get_code("18badd533b52adb3")
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

torch.manual_seed(0)

# Create a batch of 2 samples with 5 classes
batch_size = 2
num_classes = 5

# output: model predictions (logits) - shape (batch_size, num_classes)
output = torch.randn(batch_size, num_classes)

# target: ground truth class indices - shape (batch_size,)
target = torch.tensor([1, 3])

# topk: tuple of k values for which to compute precision@k
topk = (1, 3)

ARGS = {
    'output': output,
    'target': target,
    'topk': topk
}
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
build_wideresnet Ran
ran; our contract draft was wrong, not the code
TonyLianLong/UnsupervisedSelectiveLabeling/semisup-fixmatch-cifar/models/wideresnet.py
code served (permissive licence) · get_code("bc349fad528f976c")
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 WideResNet. 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 logging

logging.basicConfig(level=logging.INFO)

torch.manual_seed(0)

ARGS = {
    'depth': 28,
    'widen_factor': 2,
    'dropout': 0.0,
    'num_classes': 10
}
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 WideResNet — a WideResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a WideResNet 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
conv Ran
ran; our contract draft was wrong, not the code
TonyLianLong/UnsupervisedSelectiveLabeling/semisup-simclrv2/resnet.py
code served (permissive licence) · get_code("fb569f13818701fc")
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 = {
    "in_channels": 3,
    "out_channels": 16,
    "kernel_size": 3,
    "stride": 1,
    "bias": False,
}
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
evaluate_predictions Ran
ran; our contract draft was wrong, not the code
TonyLianLong/UnsupervisedSelectiveLabeling/usl-t_pretraining/usl-t-imagenet-pretrain.py
code served (permissive licence) · get_code("23374018ab9941b5")
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 torch
from sklearn import metrics

torch.manual_seed(0)

# Create small sample tensors for clustering evaluation
# predictions: cluster assignments (integer labels)
# targets: ground truth labels (integer labels)

predictions = torch.tensor([0, 0, 1, 1, 2, 2])
targets = torch.tensor([0, 0, 1, 1, 2, 2])

ARGS = {
    "predictions": predictions,
    "targets": targets,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
sklearn, 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
get_mean_and_std Ran
ran on a synthesized input
TonyLianLong/UnsupervisedSelectiveLabeling/semisup-fixmatch-cifar/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from zhouzihao11/CCL, is pointer only (licence: NONE) · get_code("8c82d522e7c85b05")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from zhouzihao11/CCL, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

mish Ran
ran; our contract draft was wrong, not the code
TonyLianLong/UnsupervisedSelectiveLabeling/semisup-fixmatch-cifar/models/wideresnet.py
pointer only (licence: MIT); the stored copy get_code serves, from zhouzihao11/CCL, is pointer only (licence: NONE) · get_code("0a7c46eb67c0c21b")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from zhouzihao11/CCL, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

name_to_params Ran
ran, honoured the contract we drafted
TonyLianLong/UnsupervisedSelectiveLabeling/semisup-simclrv2/resnet.py
code served (permissive licence) · get_code("0e80e018f0e62f7b")
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 torch

ARGS = {
    'checkpoint': 'r50_1x_sk1'
}
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, 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
get_resnet Not yet run
unverified (harvested, no recorded run)
TonyLianLong/UnsupervisedSelectiveLabeling/semisup-simclrv2/resnet.py
code served (permissive licence) · get_code("1f977428f41dd1e0")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 8 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 8 later) and 0 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
accuracy 19 other papers
2 dated earlier, 17 later
1805.08318 (2018-05)
Self-Attention Generative Adversarial Networks
2105.14148 (2021-05)
OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers
2111.13824 (2021-11)
FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer
and 16 more not named here
mish 15 other papers
3 dated earlier, 12 later
1908.00821 (2019-08)
Learning Lightweight Lane Detection CNNs by Self Attention Distillation
2001.07685 (2020-01)
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
2105.14148 (2021-05)
OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers
and 12 more not named here
build_wideresnet 6 other papers
1 dated earlier, 5 later
2001.07685 (2020-01)
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
2208.11870 (2022-08)
Fix-A-Step: Semi-supervised Learning from Uncurated Unlabeled Data
2307.11030 (2023-07)
Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering
and 3 more not named here
get_mean_and_std 5 other papers
1 dated earlier, 4 later
2105.14148 (2021-05)
OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers
2307.11030 (2023-07)
Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering
2402.13505 (2024-02)
SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning
and 2 more not named here
conv 1 other paper
1 later
2312.17243 (2023-12)
Unsupervised Universal Image Segmentation
evaluate_predictions 1 other paper
1 later
2312.17243 (2023-12)
Unsupervised Universal Image Segmentation
get_resnet 1 other paper
1 later
2312.17243 (2023-12)
Unsupervised Universal Image Segmentation
name_to_params 1 other paper
1 later
2312.17243 (2023-12)
Unsupervised Universal Image Segmentation

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

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

Abstract

Given an unlabeled dataset and an annotation budget, we study how to selectively label a fixed number of instances so that semi-supervised learning (SSL) on such a partially labeled dataset is most effective. We focus on selecting the right data to label, in addition to usual SSL's propagating labels from labeled data to the rest unlabeled data. This instance selection task is challenging, as without any labeled data we do not know what the objective of learning should be. Intuitively, no matter what the downstream task is, instances to be labeled must be representative and diverse: The former would facilitate label propagation to unlabeled data, whereas the latter would ensure coverage of the entire dataset. We capture this idea by selecting cluster prototypes, either in a pretrained feature space, or along with feature optimization, both without labels. Our unsupervised selective labeling consistently improves SSL methods over state-of-the-art active learning given labeled data, by 8 to 25 times in label efficiency. For example, it boosts FixMatch by 10% (14%) in accuracy on CIFAR-10 (ImageNet-1K) with 0.08% (0.2%) labeled data, demonstrating that small computation spent on selecting what data to label brings significant gain especially under a low annotation budget. Our work sets a new standard for practical and efficient SSL.

For agents

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

get_harvested_code_for_paper("2110.03006")
get_code_for_paper("2110.03006")
have("2110.03006")

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

curl https://syntology.ai/api/ran/2110.03006.json

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

[![Syntology run record](https://syntology.ai/api/ran/2110.03006.svg)](https://syntology.ai/paper/2110.03006)

Connect an agent — have() is free.