Papers › Unsupervised Data Augmentation for Consistency Training

Unsupervised Data Augmentation for Consistency Training

29 Apr 2019NeurIPS 2020 12arXiv:1904.12848archive 2025-07-28

Qizhe Xie, Zihang Dai, Eduard Hovy, Minh-Thang Luong, Quoc V. Le

Semi-supervised learning lately has shown much promise in improving deep learning models when labeled data is scarce. Common among recent approaches is the use of consistency training on a large amount of unlabeled data to constrain model predictions to be invariant to input noise. In this work, we present a new perspective on how to effectively noise unlabeled examples and argue that the quality of noising, specifically those produced by advanced data augmentation methods, plays a crucial role in semi-supervised learning. By substituting simple noising operations with advanced data augmentation methods such as RandAugment and back-translation, our method brings substantial improvements across six language and three vision tasks under the same consistency training framework. On the IMDb text classification dataset, with only 20 labeled examples, our method achieves an error rate of 4.20, outperforming the state-of-the-art model trained on 25,000 labeled examples. On a standard semi-supervised learning benchmark, CIFAR-10, our method outperforms all previous approaches and achieves an error rate of 5.43 with only 250 examples. Our method also combines well with transfer learning, e.g., when finetuning from BERT, and yields improvements in high-data regime, such as ImageNet, whether when there is only 10% labeled data or when a full labeled set with 1.3M extra unlabeled examples is used. Code is available at https://github.com/google-research/uda.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 52 code samples harvested from 12 repositories linked to this paper: 30 ran (of which 3 constructed an object rather than computing a result; 22 with no instrument failure: 2 honoured, 0 violated, 20 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 24 samples from 1 repository, 10 ran (10 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 28 samples from 11 repositories, 20 ran (12 with no instrument failure; 8 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 30 samples that ran has no recorded date.

20 repositories listed; official and paper-mentioned ones first.

google-research/uda officialmentioned in papertfApache-2.0Syntology: 24 samples, 10 ran (0 instrument-failed) · 14 unverified report
A-Telfer/AugKey mentioned on GitHubSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
ChingHuanChiu/sensitive mentioned on GitHubtfSyntology: not harvested report
PaulEmmanuelSotir/DeepCV mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
PhamNguyen97/TSA_pytorch mentioned on GitHubpytorchSyntology: not harvested report
PhamQuocHuy1101/UDA-Image-classification mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
SanghunYun/UDA_pytorch mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
SaraAmd/Semi-Supervised-Learning mentioned on GitHubpytorchSyntology: 4 samples, 1 ran (0 instrument-failed) · 3 unverified report
bhacquin/UDA_pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
ildoonet/unsupervised-data-augmentation mentioned on GitHubpytorchApache-2.0Syntology: 12 samples, 11 ran (4 instrument-failed) · 1 unverified report
joannayu25/NLP_Project_MIDS-W266 mentioned on GitHubtfSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
kekmodel/UDA-pytorch mentioned on GitHubpytorchSyntology: not harvested report
lantgabor/Unsupervised-Data-Augmentation-PyTorch mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
leblancdaniel/paraphraser mentioned on GitHubtfSyntology: not harvested report
mrvoh/meta_learning_multilingual_doc_classification mentioned on GitHubpytorchSyntology: not harvested report
peisuke/UnsupervisedDataAugmentation.pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
rwbfd/OpenCompetitionV2 mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
tomgoter/nlp_finalproject mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
uizard-technologies/realmix mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RealMix: Towards Realistic Semi-Supervised Deep Learning Algorithms (arXiv:1912.08766; that paper's own run record: 0 ran · 3 unverified); nothing checks that they implement this paper's method. report
sud0301/my_uda_pytorch pytorchSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

52 samples harvested: 30 ran (of which 3 constructed an object rather than computing a result; 22 with no instrument failure: 2 honoured, 0 violated, 20 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
4ran · our draft was wrong
4ran; the contract check could not run
20ran
22unverified

Licence: 17 of the 52 samples are pointer only, meaning Syntology does not serve that copy's text. For 8 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 12 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

google-research/uda official repository 24 samples, 10 ran (0 instrument-failed) · 14 unverified
build_vocab in 36 papers text/preprocess.py ran Apache-2.0 (permissive) · 98430a824c0f53a8 · report fixture: signature examples:list/1/Example · returned dict · level recorded 2026-09-25
create_cutout_mask image/randaugment/augmentation_transforms.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · a7723bf702941670 · report fixture: signature img_height:int/0/int, img_width:int/0/int, num_channels:int/0/int, size:int/0/int · returned tuple · level recorded 2026-09-25
format_sup_filename image/data.py ran Apache-2.0 (permissive) · d00f20643f490779 · report fixture: signature split:str/0/str, sup_size:int/0/int · returned str · level recorded 2026-09-25
format_sup_filename image/preprocess.py ran fingerprinted Apache-2.0 (permissive) · 5b70acc56bd3291f · report fixture: signature split:str/0/str, sup_size:int/0/int · returned str · level recorded 2026-09-25
format_unsup_filename image/data.py ran fingerprinted Apache-2.0 (permissive) · d90af0b30176ac15 · report fixture: signature aug_copy_num:int/0/int · returned str · level recorded 2026-09-25
kl_for_log_probs text/uda.py ran fingerprinted Apache-2.0 (permissive) · 1902057ba4826690 · report fixture: signature log_p:EagerTensor/2/float, log_q:EagerTensor/2/float · returned SymbolicTensor · level recorded 2026-09-25
random_flip in 12 papers image/randaugment/augmentation_transforms.py ran fingerprinted Apache-2.0 (permissive) · 6e1198a9c8c47438 · report fixture: signature x:ndarray/2/float · returned ndarray · level recorded 2026-09-25
split_sent_by_punc back_translate/split_paragraphs.py ran Apache-2.0 (permissive) · c6512991cdef483b · report fixture: signature sent:str/0/str, punc:str/0/str, offset:int/0/int · returned list · level recorded 2026-09-25
zero_pad in 9 papers image/randaugment/custom_ops.py ran fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 563e25e514f4a2a6 · report fixture: signature inputs:EagerTensor/4/float, in_filter:int/0/int, out_filter:int/0/int · returned EagerTensor · level recorded 2026-09-25
zero_pad_and_crop image/randaugment/augmentation_transforms.py ran fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · f3f5fce61e36ad06 · report fixture: signature img:ndarray/3/float, amount:int/0/int · returned ndarray · level recorded 2026-09-25
bert_attention text/bert/modeling.py unverified Apache-2.0 (permissive) · 63d1e64fcc8da86a · report
bert_embedding text/bert/modeling.py unverified Apache-2.0 (permissive) · 4cd09bb78a67af39 · report
bert_pooler text/bert/modeling.py unverified Apache-2.0 (permissive) · b041de8f4abb1b10 · report
construct_scalar_host_call image/utils.py unverified Apache-2.0 (permissive) · 914d0b8791ca87d0 · report
decay_weights image/utils.py unverified Apache-2.0 (permissive) · fb66342c3f664ee6 · report
divide_data_for_worker back_translate/split_paragraphs.py unverified Apache-2.0 (permissive) · 97c1d8a99764fb25 · report
get_TPU_estimator image/utils.py unverified Apache-2.0 (permissive) · 81e5d3b478f3469c · report
get_data_for_worker text/preprocess.py unverified Apache-2.0 (permissive) · d468fe223b1a25a2 · report
get_dataset in 285 papers image/data.py unverified Apache-2.0 (permissive) · b417179a5b5e0e14 · report
get_raw_data_filenames image/preprocess.py unverified Apache-2.0 (permissive) · 89985ecf00256155 · report
get_tsa_threshold text/uda.py unverified Apache-2.0 (permissive) · 6895a8402ea9ee79 · report
global_avg_pool image/randaugment/custom_ops.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 17411729594afb42 · report
hidden_to_logits text/uda.py unverified Apache-2.0 (permissive) · 0175d515a039d4f8 · report
variable in 12 papers image/randaugment/custom_ops.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · f6b18b79eccd8391 · report
A-Telfer/AugKey community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
MagnitudePolicy augkey/randaug.py ran MIT (permissive) · 36741a983d72bd68 · report fixture: returned MagnitudePolicy · level recorded 2026-09-22
RandAugment augkey/randaug.py ran MIT (permissive) · 5722c1e755019115 · report fixture: returned RandAugment · level recorded 2026-09-22
PaulEmmanuelSotir/DeepCV community (archive-listed) 1 sample, 0 ran · 1 unverified
jensen_shannon_divergence_consistency_loss src/deepcv/meta/contrastive.py unverified MIT (permissive) · 36c684d7fa0846c8 · report
PhamQuocHuy1101/UDA-Image-classification community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_unsupervised_loss engine.py ran · our draft was wrong no licence file found · pointer only · bfec53e668f92651 · report fixture: signature unsup_logits:Tensor/2/float, aug_logits:Tensor/2/float, criterion:callable/0/?, beta:float/0/float, teta:float/0/float · returned Tensor · level recorded 2026-09-22
SanghunYun/UDA_pytorch community (archive-listed) 1 sample, 0 ran · 1 unverified
Classifier in 72 papers models.py unverified Apache-2.0 (permissive) · e46d15e93318b254 · report
SaraAmd/Semi-Supervised-Learning community (archive-listed) 4 samples, 1 ran (0 instrument-failed) · 3 unverified
RGB2RGBA ssl_lib/augmentation/augmentation_class.py ran · metamorphic tier: well formed no licence file found · pointer only · 1a1dcc06f81c3c75 · report fixture: signature x:Image/0/? · returned Image · level recorded 2026-09-22
RandAugment ssl_lib/augmentation/augmentation_class.py unverified no licence file found · pointer only · b9d05e119e47da9f · report
ReduceChannelwithNormalize ssl_lib/augmentation/augmentation_class.py unverified no licence file found · pointer only · 41b7d839c5008446 · report
StrongAugmentation ssl_lib/augmentation/augmentation_class.py unverified no licence file found · pointer only · 3458a17eb1c6c95f · report
bhacquin/UDA_pytorch community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
convert_examplesUDA_to_features run_uda.py ran · our draft was wrong no licence file found · pointer only · df213afe1b71adfd · report fixture: signature examples:list/1/str, max_seq_length:int/0/int, tokenizer:SimpleTokenizer/0/?, output_mode:str/0/str, label_list:NoneType/0/? · returned list · level recorded 2026-09-22
ildoonet/unsupervised-data-augmentation community (archive-listed) 12 samples, 11 ran (4 instrument-failed) · 1 unverified
ShearX in 14 papers augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed Apache-2.0 (permissive) · b92936d1f2ac3e6c · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
ShearY in 14 papers augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed Apache-2.0 (permissive) · 008c64b77c4ae4c9 · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
TranslateX in 13 papers augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed Apache-2.0 (permissive) · ab50d5bbcf589623 · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
argsort samplers/stratified_sampler.py ran fingerprinted Apache-2.0 (permissive) · cbc36864ed1d2c42 · report fixture: signature seq:list/1/int · returned list · level recorded 2026-09-24
conv3x3 in 1,376 papers networks/wideresnet.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 00e569acd6b45ef0 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
cross_entropy_smooth metrics.py ran Apache-2.0 (permissive) · f018413f261238f7 · report fixture: signature input:Tensor/2/float, target:Tensor/1/int, size_average:bool/0/bool, label_smoothing:float/0/float · returned Tensor · level recorded 2026-09-24
fisherYatesShuffle samplers/stratified_sampler.py ran fingerprinted Apache-2.0 (permissive) · 406265b8de6d26a2 · report fixture: signature arr:list/1/int · returned list · level recorded 2026-09-24
float_parameter in 36 papers archive.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 40d3c39a403ae1f7 · report fixture: signature level:int/0/int, maxval:float/0/float · returned float · level recorded 2026-09-24
get_logger in 383 papers common.py ran Apache-2.0 (permissive) · 6066adc7a58afde6 · report fixture: signature name:str/0/str, level:int/0/int · returned Logger · level recorded 2026-09-25
int_parameter in 35 papers archive.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 7900a3a6deef908b · report fixture: signature level:int/0/int, maxval:int/0/int · returned int · level recorded 2026-09-24
spotifyShuffle samplers/stratified_sampler.py ran fingerprinted Apache-2.0 (permissive) · 6cb91780680fb891 · report fixture: signature songs_list:list/1/str, artists_list:list/1/str · returned list · level recorded 2026-09-24
joannayu25/NLP_Project_MIDS-W266 community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
replace_with_length_check augmentation/sent_level_augment.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 64a6c97a5657e37a · report fixture: signature ori_text:str/0/str, new_text:str/0/str, use_min_length:int/0/int, use_max_length_diff_ratio:float/0/float · returned str · level recorded 2026-09-22
back_translation augmentation/sent_level_augment.py unverified no licence file found · pointer only · 2f093dc1c7296f6c · report
lantgabor/Unsupervised-Data-Augmentation-PyTorch community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
AverageMeter in 26 papers UDA.py ran Apache-2.0 (permissive) · 9355efdc819d943e · report fixture: returned AverageMeter · level recorded 2026-09-22
uda_train UDA.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · a359f54f3b9012c2 · report fixture: returned float · level recorded 2026-09-22
peisuke/UnsupervisedDataAugmentation.pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
UDALoss train_CIFAR10.py ran MIT (permissive) · e69c03b0ebf8765a · report fixture: signature model:callable/0/?, x:Tensor/2/float, x_h:Tensor/2/float · returned Tensor · level recorded 2026-09-24
tomgoter/nlp_finalproject community (archive-listed) 1 sample, 0 ran · 1 unverified
get_uda_classification_loss utils/function_builder.py unverified no licence file found · pointer only · 83a7585173c63bc5 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

11 assemblies on this paper: 11 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

11 sibling assemblies for Unsupervised Data Augmentation for Consistency Training (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Unsupervised Data Augmentation for Consistency Training (graph method: Unsupervised Data Augmentation for Consistency Training). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. get_unsupervised_loss entry · level 1 · ran · our draft was wrong · bfec53e668f92651

harvested Assembly for Unsupervised Data Augmentation for Consistency Training (graph method: Unsupervised Data Augmentation for Consistency Training). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. uda_train entry · level 1 · ran; the contract check could not run (RAISES) · a359f54f3b9012c2
  2. AverageMeter helper · level 1 · ran · 9355efdc819d943e

harvested Assembly for Unsupervised Data Augmentation for Consistency Training (graph method: Unsupervised Data Augmentation for Consistency Training). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. jensen_shannon_divergence_consistency_loss entry · level 0 · unverified · 36c684d7fa0846c8

harvested Assembly for Unsupervised Data Augmentation for Consistency Training (graph method: Unsupervised Data Augmentation for Consistency Training). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. UDALoss entry · level 1 · ran · e69c03b0ebf8765a

harvested Assembly for Unsupervised Data Augmentation for Consistency Training (graph method: Unsupervised Data Augmentation for Consistency Training). 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. back_translation entry · level 0 · unverified · 2f093dc1c7296f6c
  2. replace_with_length_check data_transform · level 1 · ran · our draft was wrong · 64a6c97a5657e37a

harvested Assembly for Unsupervised Data Augmentation for Consistency Training (graph method: Unsupervised Data Augmentation for Consistency Training). 20 bricks; individually on a fixture: 20 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 20 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. augment_list entry · level 1 · ran · our draft was wrong · b1cd4e4b4bba7f8c
  2. AutoContrast data_transform · level 1 · ran · our draft was wrong · 4a0ac9d611e018bc
  3. Brightness data_transform · level 1 · ran; the contract check could not run · 993134d3c95bcf92
  4. Color data_transform · level 1 · ran; the contract check could not run · ccaa14b841bf44dc
  5. Contrast data_transform · level 1 · ran; the contract check could not run · 35f5a6d3913e6b0e
  6. Cutout data_transform · level 1 · ran; the contract check could not run · f90119cfdd38ef56
  7. CutoutAbs helper · level 1 · ran; the contract check could not run · 03ecbd868107e6f7
  8. Equalize data_transform · level 1 · ran · our draft was wrong · 4befb1744e90f3a1
  9. Invert data_transform · level 1 · ran · our draft was wrong · f5f0bf976dfcf068
  10. Posterize data_transform · level 1 · ran; the contract check could not run · d2a9bd74240b6944
  11. Posterize2 helper · level 1 · ran; the contract check could not run · 067680c1cc9f4b97
  12. Rotate data_transform · level 1 · ran · our draft was wrong · 21c6427b09f14649
  13. Sharpness data_transform · level 1 · ran; the contract check could not run · e1ccc58bf76a30b9
  14. ShearX data_transform · level 1 · ran; the contract check could not run (RAISES) · b92936d1f2ac3e6c
  15. ShearY data_transform · level 1 · ran; the contract check could not run (RAISES) · 008c64b77c4ae4c9
  16. Solarize data_transform · level 1 · ran; the contract check could not run · 70eab251c4b2bce2
  17. TranslateX data_transform · level 1 · ran; the contract check could not run (RAISES) · ab50d5bbcf589623
  18. TranslateXAbs helper · level 1 · ran; the contract check could not run · b1fc55be13be06e7
  19. TranslateY data_transform · level 1 · ran; the contract check could not run · d4b73cc9fa9b08ae
  20. TranslateYAbs helper · level 1 · ran; the contract check could not run · 15ceb820d17f0a5c

harvested Assembly for Unsupervised Data Augmentation for Consistency Training (graph method: Unsupervised Data Augmentation for Consistency Training). 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 11 siblings

  1. RandAugment entry · level 1 · ran · 5722c1e755019115
  2. MagnitudePolicy helper · level 1 · ran · 36741a983d72bd68

harvested Assembly for Unsupervised Data Augmentation for Consistency Training (graph method: Unsupervised Data Augmentation for Consistency Training). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. get_uda_classification_loss entry · level 0 · unverified · 83a7585173c63bc5

harvested Assembly for Unsupervised Data Augmentation for Consistency Training (graph method: Unsupervised Data Augmentation for Consistency Training). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. convert_examplesUDA_to_features entry · level 1 · ran · our draft was wrong · df213afe1b71adfd
  2. InputFeatures helper · level 1 · ran · a8d8657df9ba7457

harvested Assembly for Unsupervised Data Augmentation for Consistency Training (graph method: Unsupervised Data Augmentation for Consistency Training). 10 bricks; individually on a fixture: 9 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. Classifier entry · level 0 · unverified · e46d15e93318b254
  2. Transformer model · level 1 · ran · 4076b007bcd248ae
  3. Block helper · level 1 · ran · 2dcf1b4f0aa2fa9a
  4. Embeddings model · level 1 · ran · b036f3e72b73df3d
  5. LayerNorm model · level 1 · ran · b0f94b02a9a6c057
  6. MultiHeadedSelfAttention model · level 1 · ran · 05a7a0d5018b97f8
  7. PositionWiseFeedForward model · level 1 · ran · a10a2edb3945c395
  8. merge_last helper · level 1 · ran; the contract check could not run · d5e69fc7b0ee7c8c
  9. split_last helper · level 1 · ran; the contract check could not run · a4a5354a3138c8ef
  10. gelu helper · level 1 · ran · honoured contract · 62e7409a816626ac

harvested Assembly for Unsupervised Data Augmentation for Consistency Training (graph method: Unsupervised Data Augmentation for Consistency Training). 4 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. StrongAugmentation entry · level 0 · unverified · 3458a17eb1c6c95f
  2. RGB2RGBA helper · level 1 · ran · 1a1dcc06f81c3c75
  3. RandAugment helper · level 0 · unverified · b9d05e119e47da9f
  4. ReduceChannelwithNormalize helper · level 0 · unverified · 41b7d839c5008446

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1904.12848") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Data AugmentationImage AugmentationImage ClassificationSemi-Supervised Image ClassificationSentiment AnalysisText ClassificationTransfer Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet ResNet-50 (UDA) Top 1 Accuracy 79.04% #786 of 1060 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 4000 Labels UDA Percentage error 5.27 #25 of 49 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data UDA Top 5 Accuracy 88.52 #55 of 75 Archive leaderboard report
Semi-Supervised Image Classification SVHN, 1000 labels UDA Accuracy 97.54 #5 of 17 Archive leaderboard report
Sentiment Analysis Amazon Review Full BERT large Accuracy 65.83 #1 of 9 Archive leaderboard report
Sentiment Analysis Amazon Review Full BERT large finetune UDA Accuracy 62.88 #4 of 9 Archive leaderboard report
Sentiment Analysis Amazon Review Polarity BERT large Accuracy 97.37 #1 of 9 Archive leaderboard report
Sentiment Analysis Amazon Review Polarity BERT large finetune UDA Accuracy 96.5 #3 of 9 Archive leaderboard report
Sentiment Analysis IMDb BERT large finetune UDA Accuracy 95.8 #10 of 49 Archive leaderboard report
Sentiment Analysis IMDb BERT large Accuracy 95.49 #15 of 49 Archive leaderboard report
Sentiment Analysis Yelp Binary classification BERT large Error 1.89 #4 of 20 Archive leaderboard report
Sentiment Analysis Yelp Binary classification BERT large finetune UDA Error 2.05 #6 of 20 Archive leaderboard report
Sentiment Analysis Yelp Fine-grained classification BERT large Error 29.32 #3 of 17 Archive leaderboard report
Sentiment Analysis Yelp Fine-grained classification BERT large finetune UDA Error 32.08 #8 of 17 Archive leaderboard report
Text Classification Amazon-2 BERT Finetune + UDA Error 3.5 #2 of 4 Archive leaderboard report
Text Classification Amazon-5 BERT Finetune + UDA Error 37.12 #3 of 3 Archive leaderboard report
Text Classification DBpedia BERT large Error 0.68 #3 of 21 Archive leaderboard report
Text Classification DBpedia BERT large UDA Error 1.09 #14 of 21 Archive leaderboard report
Text Classification Yelp-2 BERT Finetune + UDA Accuracy 97.95% #3 of 5 Archive leaderboard report
Text Classification Yelp-5 BERT Finetune + UDA Accuracy 67.92% #6 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAdamAttentionAttention DropoutAverage PoolingBERTBatch NormalizationBottleneck Residual BlockConvolutionDense ConnectionsDropoutGlobal Average PoolingKaiming InitializationLayer NormalizationLinear LayerLinear Warmup With Linear DecayMax PoolingMulti-Head AttentionReLUResidual BlockResidual ConnectionSoftmaxWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections