Papers › MixMatch: A Holistic Approach to Semi-Supervised Learning

MixMatch: A Holistic Approach to Semi-Supervised Learning

6 May 2019NeurIPS 2019 12arXiv:1905.02249archive 2025-07-28

David Berthelot, Nicholas Carlini, Ian Goodfellow, Nicolas Papernot, Avital Oliver, Colin Raffel

Semi-supervised learning has proven to be a powerful paradigm for leveraging unlabeled data to mitigate the reliance on large labeled datasets. In this work, we unify the current dominant approaches for semi-supervised learning to produce a new algorithm, MixMatch, that works by guessing low-entropy labels for data-augmented unlabeled examples and mixing labeled and unlabeled data using MixUp. We show that MixMatch obtains state-of-the-art results by a large margin across many datasets and labeled data amounts. For example, on CIFAR-10 with 250 labels, we reduce error rate by a factor of 4 (from 38% to 11%) and by a factor of 2 on STL-10. We also demonstrate how MixMatch can help achieve a dramatically better accuracy-privacy trade-off for differential privacy. Finally, we perform an ablation study to tease apart which components of MixMatch are most important for its success.

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

No sample from the archive's official repository (google-research/mixmatch) is linked to this paper; the 63 samples below come from 17 community repositories. Syntology harvested code from google-research/mixmatch for another paper.

google-research/mixmatch: Syntology's graph links these samples to ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring (arXiv:1911.09785; that paper's own run record: 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) · 3 unverified); nothing checks that they implement this paper's method.

Syntology 63 code samples harvested from 17 repositories linked to this paper: 47 ran (of which 8 constructed an object rather than computing a result; 27 with no instrument failure: 8 honoured, 0 violated, 19 with no contract checked; 20 where Syntology's instrument failed) · 16 unverified. Where Syntology's instrument failed: 11 where our contract draft was wrong; 9 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 63 samples from 17 repositories, 47 ran (27 with no instrument failure; 20 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 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 47 samples that ran has no recorded date.

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

google-research/mixmatch officialmentioned in papermentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring (arXiv:1911.09785; that paper's own run record: 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) · 3 unverified); nothing checks that they implement this paper's method. report
DamianValle/ScarceClassifier mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
DonghwanKIM0101/CS492I_CV mentioned on GitHubpytorchSyntology: not harvested report
FelixAbrahamsson/mixmatch-pytorch mentioned on GitHubpytorchSyntology: 5 samples, 5 ran (4 instrument-failed) · 0 unverified report
Jeffkang-94/Mixmatch-pytorch-SSL mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Jeffkang-94/pytorch-MixMatch mentioned on GitHubpytorchSyntology: not harvested report
Shubhammawa/MixMatch-Semi-Supervised-Learning mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to mixup: Beyond Empirical Risk Minimization (arXiv:1710.09412; that paper's own run record: 36 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 22 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
TianheWu/LGPNet mentioned on GitHubpytorchSyntology: not harvested report
YU1ut/MixMatch-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
atinghosh/mixmatch_pytorch mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
dLutscher/MixMatch-TransferLearning mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
dhx000/DGM_project mentioned on GitHubtfSyntology: 10 samples, 5 ran (4 instrument-failed) · 5 unverified report
fbuchert/mixmatch-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
filaPro/visda2019 mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
gan3sh500/mixmatch-pytorch mentioned on GitHubpytorchSyntology: 5 samples, 3 ran (2 instrument-failed) · 2 unverified report
google-research/crest mentioned on GitHubtfSyntology: not harvested report
kevinghst/mixmatch mentioned on GitHubpytorchMITSyntology: 5 samples, 2 ran (1 instrument-failed) · 3 unverified report
ktran1/Manifold-attack mentioned on GitHubpytorchSyntology: not harvested report
ms903-github/MixMatch-imdb mentioned on GitHubpytorchMITSyntology: not harvested report
narendoraiswamy/MixMatch-pytorch-demo mentioned on GitHubpytorchMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
noachr/MixMatch-fastai mentioned on GitHubpytorchMITSyntology: not harvested report
ntozer/mixmatch-tensorflow2.0 mentioned on GitHubtfSyntology: 6 samples, 6 ran (4 instrument-failed) · 0 unverified report
perrying/realistic-ssl-evaluation-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
rit-git/Snippext_public mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
smkim7-kr/albu-MixMatch-pytorch mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
tinluu/Self-supervised-CV mentioned on GitHubpytorchSyntology: not harvested 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
viig99/mixmatch-freesound mentioned on GitHubpytorchMITSyntology: 8 samples, 5 ran (0 instrument-failed) · 3 unverified report
yuxi120407/mixmatch_tensorflow mentioned on GitHubtfSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
yuxi120407/semi-supervised_tensorflow2.0 mentioned on GitHubtfSyntology: 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

63 samples harvested: 47 ran (of which 8 constructed an object rather than computing a result; 27 with no instrument failure: 8 honoured, 0 violated, 19 with no contract checked; 20 where Syntology's instrument failed) · 16 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.

8ran · honoured contract
11ran · our draft was wrong
9ran; the contract check could not run
19ran
16unverified

Licence: 34 of the 63 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 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 17 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”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

DamianValle/ScarceClassifier community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
Augment src/mixmatch.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · f64393cdb0ae8878 · report fixture: signature batch:Tensor/4/float · returned Tensor · level recorded 2026-09-22
RandomCrop src/mixmatch.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 3f2a5048d7bc9b95 · report fixture: signature img:Tensor/4/float · returned Tensor · level recorded 2026-09-22
MixMatch src/mixmatch.py unverified no licence file found · pointer only · 7397979be7d7eeb1 · report
FelixAbrahamsson/mixmatch-pytorch community (archive-listed) 5 samples, 5 ran (4 instrument-failed) · 0 unverified
guess_targets mixmatch_pytorch/mixmatch_batch.py ran · our draft was wrong no licence file found · pointer only · 568ec1709ff7ca07 · report fixture: signature features:Tensor/2/float, model:callable/0/?, output_transform:callable/0/?, K:int/0/int, T:float/0/float · returned Tensor · level recorded 2026-09-22
mixmatch_batch mixmatch_pytorch/mixmatch_batch.py ran · our draft was wrong no licence file found · pointer only · 3164897bcf3781a2 · report fixture: signature batch:dict/0/?, batch_unlabeled:dict/0/?, model:callable/0/?, output_transform:callable/0/?, K:int/0/int, T:float/0/float, beta:Beta/0/? · returned dict · level recorded 2026-09-22
mixup_samples mixmatch_pytorch/mixmatch_batch.py ran · our draft was wrong no licence file found · pointer only · 9d112ebaba96ddb1 · report fixture: signature x1:Tensor/2/float, y1:Tensor/2/float, x2:Tensor/2/float, y2:Tensor/2/float, beta:Beta/0/? · returned tuple · level recorded 2026-09-22
sharpen in 10 papers mixmatch_pytorch/mixmatch_batch.py ran · honoured contract fingerprinted no licence file found · pointer only · cbc1955a34800714 · report fixture: signature probabilities:Tensor/2/float, T:float/0/float · returned Tensor · level recorded 2026-09-22
tile_adjacent mixmatch_pytorch/mixmatch_batch.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · caacacf94d563a78 · report fixture: signature tensor:Tensor/1/int, K:int/0/int · returned Tensor · level recorded 2026-09-22
Jeffkang-94/Mixmatch-pytorch-SSL community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MixMatchLoss SSL_loss/mixmatch.py ran no licence file found · pointer only · 4de37e26980b9f34 · report fixture: returned MixMatchLoss · level recorded 2026-09-22
YU1ut/MixMatch-pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
WideResNet in 13 papers models/wideresnet.py ran MIT (permissive) · c3d0f2f3671b4bbc · report fixture: returned WideResNet · level recorded 2026-09-22
atinghosh/mixmatch_pytorch community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
BasicBlock in 126 papers
census: 6 implementations from 6 papers, 5 distinct outputs on one shared input
network_mod.py ran fingerprinted no licence file found · pointer only · e4dc4ca4b40de499 · report fixture: returned BasicBlock · level recorded 2026-09-22
NetworkBlock in 6 papers network_mod.py ran fingerprinted no licence file found · pointer only · 2950d5425e9dd18b · report fixture: returned NetworkBlock · level recorded 2026-09-22
Wide_ResNet in 5 papers network_mod.py ran no licence file found · pointer only · 8608707dd0f937bd · report fixture: returned Wide_ResNet · level recorded 2026-09-22
dLutscher/MixMatch-TransferLearning community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
SemiLoss utils/utils.py ran no licence file found · pointer only · 48a12c06cbdd6b70 · report fixture: returned SemiLoss · level recorded 2026-09-22
linear_rampup in 33 papers utils/utils.py ran · honoured contract fingerprinted no licence file found · pointer only · 0aaac678344cd89f · report fixture: signature current:int/0/int, rampup_length:int/0/int · returned float · level recorded 2026-09-22
dhx000/DGM_project community (archive-listed) 10 samples, 5 ran (4 instrument-failed) · 5 unverified
augment in 36 papers mixmatch/cycle_mixmatch.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 39827536f2c0ed9a · report fixture: signature x:ndarray/3/int, flip_code:int/0/int · returned ndarray · level recorded 2026-09-24
mixmatch mixmatch/cycle_mixmatch.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 4350f70a89ff949b · report fixture: signature model:MockModel/0/?, x:ndarray/4/float, y:ndarray/4/float, u:ndarray/4/float, T:float/0/float, K:int/0/int, alpha:float/0/float · returned tuple · level recorded 2026-09-22
mixup in 28 papers mixmatch/cycle_mixmatch.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 65eae886ef202b56 · report fixture: signature x1:ndarray/2/float, x2:ndarray/2/float, y1:ndarray/2/float, y2:ndarray/2/float, alpha:float/0/float · returned tuple · level recorded 2026-09-22
sharpen in 10 papers mixmatch/cycle_mixmatch.py ran · honoured contract fingerprinted no licence file found · pointer only · 63688837810c6e5a · report fixture: signature p:ndarray/1/float, T:float/0/float · returned ndarray · level recorded 2026-09-22
split_U mixmatch/cycle_mixmatch.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 3c7a33c95b913c66 · report fixture: signature XU:ndarray/3/float, XUy:ndarray/2/int, batch_size:int/0/int, K:int/0/int · returned tuple · level recorded 2026-09-24
augment_labelData mixmatch/cycle_mixmatch.py unverified no licence file found · pointer only · cd590be04d9864e1 · report
augment_unlabelData mixmatch/cycle_mixmatch.py unverified no licence file found · pointer only · 21f82c5babfc89be · report
expand_ulabel mixmatch/cycle_mixmatch.py unverified no licence file found · pointer only · 44bd7219e3206702 · report
guess_label_with_logit mixmatch/cycle_mixmatch.py unverified no licence file found · pointer only · 71516924003b7081 · report
split_X mixmatch/cycle_mixmatch.py unverified no licence file found · pointer only · 0accfa09823d9b0c · report
fbuchert/mixmatch-pytorch community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_weak_augmentation augmentation/augmentations.py ran · our draft was wrong MIT (permissive) · fbc0e34ee7b8cdb5 · report fixture: signature img_size:int/0/int, padding:int/0/int, padding_mode:str/0/str · returned Compose · level recorded 2026-09-22
gan3sh500/mixmatch-pytorch community (archive-listed) 5 samples, 3 ran (2 instrument-failed) · 2 unverified
mixup_mod mixmatch_utils.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 77308af8bcbb2b2b · report fixture: signature x1:ndarray/2/float, x2:ndarray/2/float, y1:ndarray/2/float, y2:ndarray/2/float, alpha:float/0/float · returned tuple · level recorded 2026-09-22
sharpen in 10 papers mixmatch_utils.py ran · honoured contract fingerprinted no licence file found · pointer only · 6d22d34f03eff901 · report fixture: signature x:Tensor/2/float, T:float/0/float · returned Tensor · level recorded 2026-09-22
to_categorical in 25 papers
census: 3 implementations from 5 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
mixmatch_utils.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 7ccbcdef1f97bdbf · report fixture: signature y:ndarray/1/int, num_classes:int/0/int, dtype:str/0/str · returned ndarray · level recorded 2026-09-22
label_guessing mixmatch_utils.py unverified no licence file found · pointer only · 0ad756f5a68bcd04 · report
mixmatch mixmatch_utils.py unverified no licence file found · pointer only · b11b94decd7ab296 · report
kevinghst/mixmatch community (archive-listed) 5 samples, 2 ran (1 instrument-failed) · 3 unverified
plot_overlap in 37 papers utils/logger.py ran · our draft was wrong MIT (permissive) · 50afa2863ffd9fde · report fixture: signature logger:MockLogger/0/?, names:NoneType/0/? · returned list · level recorded, date not recorded
train_val_split in 14 papers dataset/cifar10.py ran fingerprinted MIT (permissive) · 035b6b2199fe55d1 · report fixture: signature labels:list/1/int, n_labeled_per_class:int/0/int · returned tuple · level recorded 2026-09-24
get_cifar10 in 13 papers dataset/cifar10.py unverified MIT (permissive) · a0e25dd8565d9d94 · report
get_mean_and_std in 55 papers utils/misc.py unverified MIT (permissive) here; the stored copy is pointer only · 1d6e2edb8832d7b0 · report
normalise in 26 papers dataset/cifar10.py unverified MIT (permissive) here; the stored copy is pointer only · d2a4ac781b2a9628 · report
narendoraiswamy/MixMatch-pytorch-demo community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
categorize dataset/_cifar10.py ran fingerprinted MIT (permissive) · d687dcb3c4ba5861 · report fixture: signature cifar_targets:list/1/int · returned list · level recorded 2026-09-24
train_val_split in 14 papers dataset/_cifar10.py ran MIT (permissive) · 41670d21181a8756 · report fixture: signature labels:ndarray/1/int, n_labeled_per_class:int/0/int · returned tuple · level recorded 2026-09-24
get_cifar10 in 13 papers dataset/_cifar10.py unverified MIT (permissive) · 0f1e6cdf5451e58d · report
ntozer/mixmatch-tensorflow2.0 community (archive-listed) 6 samples, 6 ran (4 instrument-failed) · 0 unverified
augment in 36 papers mixmatch.py ran; the contract check could not run (RAISES) MIT (permissive) · 647302bd0cbc0cd4 · report fixture: signature x:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-22
guess_labels mixmatch.py ran · our draft was wrong MIT (permissive) · e364b83801e8d8c9 · report fixture: signature u_aug:list/1/EagerTensor, model:callable/0/?, K:int/0/int · returned EagerTensor · level recorded 2026-09-22
interleave in 9 papers mixmatch.py ran · our draft was wrong MIT (permissive) · dc463911b8db674e · report fixture: signature xy:list/1/EagerTensor, batch:int/0/int · returned list · level recorded 2026-09-22
mixmatch mixmatch.py ran; the contract check could not run (RAISES) MIT (permissive) · 91c88dac1ac09bee · report fixture: signature model:callable/0/?, x:EagerTensor/4/float, y:EagerTensor/2/float, u:EagerTensor/4/float, T:float/0/float, K:int/0/int, beta:EagerTensor/0/float · returned tuple · level recorded 2026-09-22
mixup in 28 papers mixmatch.py ran · honoured contract fingerprinted MIT (permissive) · de552909167b4340 · report fixture: signature x1:EagerTensor/2/float, x2:EagerTensor/2/float, y1:EagerTensor/2/float, y2:EagerTensor/2/float, beta:EagerTensor/0/float · returned tuple · level recorded 2026-09-22
sharpen in 10 papers mixmatch.py ran · honoured contract fingerprinted MIT (permissive) · 2777c70138515c4d · report fixture: signature p:EagerTensor/2/float, T:EagerTensor/0/float · returned EagerTensor · level recorded 2026-09-22
perrying/realistic-ssl-evaluation-pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MixMatch lib/algs/mixmatch.py ran MIT (permissive) · 1733a4add804ce42 · report fixture: signature x:Tensor/2/float, y:Tensor/2/float, model:callable/0/?, mask:Tensor/1/float · returned Tensor · level recorded 2026-09-24
rit-git/Snippext_public community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
classifier_criterion snippext/mixmatchnl.py ran · our draft was wrong fingerprinted BSD-3-Clause (permissive) · 3cac74cd5cc4e2f1 · report fixture: signature pred_labeled:Tensor/2/float, y_labeled:Tensor/2/float · returned Tensor · level recorded 2026-09-22
mixmatch snippext/mixmatchnl.py ran · honoured contract BSD-3-Clause (permissive) · 9f0765feb50790dd · report fixture: signature model:callable/0/?, batch:tuple/1/NoneType, num_aug:int/0/int, alpha:float/0/float, alpha_aug:float/0/float, u_lambda:float/0/float · returned Tensor · level recorded 2026-09-22
tagging_criterion snippext/mixmatchnl.py ran · our draft was wrong fingerprinted BSD-3-Clause (permissive) · 670937fdbe1b61da · report fixture: signature pred_labeled:Tensor/2/float, y_labeled:Tensor/2/float · returned Tensor · level recorded 2026-09-22
smkim7-kr/albu-MixMatch-pytorch community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
interleave in 9 papers src/utils.py ran · our draft was wrong MIT (permissive) · 87035ef75e16edc6 · report fixture: signature xy:list/1/Tensor, batch:int/0/int · returned list · level recorded 2026-09-22
interleave_offsets src/utils.py ran · honoured contract fingerprinted MIT (permissive) · 73e81fa7395d8998 · report fixture: signature batch:int/0/int, nu:int/0/int · returned list · level recorded 2026-09-22
mixup in 28 papers src/utils.py ran · our draft was wrong MIT (permissive) · a083b3ef65c4a3c1 · report fixture: signature args:Args/0/?, all_imgs:Tensor/4/float, all_targets:Tensor/2/float · returned tuple · level recorded 2026-09-22
viig99/mixmatch-freesound community (archive-listed) 8 samples, 5 ran (0 instrument-failed) · 3 unverified
calculate_overall_lwlrap_sklearn analysis/compute_lwlrap.py ran fingerprinted MIT (permissive) · c9498d65f32e1148 · report fixture: signature truth:ndarray/2/float, scores:ndarray/2/float · returned float · level recorded 2026-09-24
collate_fn in 500 papers dataset/freesound.py ran MIT (permissive) · c9ad1e68bbc3805b · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-24
collate_fn_unlabbelled dataset/freesound.py ran MIT (permissive) · 45f16173aaa12967 · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-24
label_binarizer dataset/freesound.py ran MIT (permissive) · ad7aa34a23b546b2 · report fixture: signature data:list/1/list · returned MultiLabelBinarizer · level recorded 2026-09-24
should_apply_transform kaggle_submission.py ran fingerprinted MIT (permissive) · 06ac2737867f1b5b · report fixture: signature prob:float/0/float · returned bool · level recorded 2026-09-24
calculate_per_class_lwlrap analysis/compute_lwlrap.py unverified MIT (permissive) · 033283e1fa3d96fe · report
create_model in 163 papers kaggle_submission_checker.py unverified MIT (permissive) · f8b6744d7114ac81 · report
load_state_dict in 114 papers kaggle_submission.py unverified MIT (permissive) · 197f711034e07fc3 · report
yuxi120407/mixmatch_tensorflow community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
Residual3x3Unit model.py ran no licence file found · pointer only · a50bcc606f57701c · report fixture: returned Residual3x3Unit · level recorded 2026-09-22
ResidualBlock in 100 papers model.py ran no licence file found · pointer only · 251561e345918b21 · report fixture: returned ResidualBlock · level recorded 2026-09-22
WideResNet in 13 papers model.py unverified no licence file found · pointer only · 6e4bb6cf26d5d34d · 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.

14 assemblies on this paper: 14 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

14 sibling assemblies for MixMatch (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 14 sibling assemblies; the other 2 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for MixMatch (graph method: MixMatch). 3 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 14 siblings

  1. mixup entry · level 1 · ran · our draft was wrong · a083b3ef65c4a3c1
  2. interleave helper · level 1 · ran · our draft was wrong · 87035ef75e16edc6
  3. interleave_offsets helper · level 1 · ran · honoured contract · 73e81fa7395d8998

harvested Assembly for MixMatch (graph method: MixMatch). 7 bricks; individually on a fixture: 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 14 siblings

  1. mixmatch entry · level 1 · ran; the contract check could not run (RAISES) · 91c88dac1ac09bee
  2. augment data_transform · level 1 · ran; the contract check could not run (RAISES) · 647302bd0cbc0cd4
  3. guess_labels helper · level 1 · ran · our draft was wrong · e364b83801e8d8c9
  4. interleave helper · level 1 · ran · our draft was wrong · dc463911b8db674e
  5. mixup data_transform · level 1 · ran · honoured contract · de552909167b4340
  6. sharpen helper · level 1 · ran · honoured contract · 2777c70138515c4d
  7. interleave_offsets helper · level 1 · ran · honoured contract · 73e81fa7395d8998

harvested Assembly for MixMatch (graph method: MixMatch). 3 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) · 1 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 14 siblings

  1. WideResNet entry · level 0 · unverified · 6e4bb6cf26d5d34d
  2. Residual3x3Unit model · level 1 · ran · a50bcc606f57701c
  3. ResidualBlock model · level 1 · ran · 251561e345918b21

harvested Assembly for MixMatch (graph method: MixMatch). 5 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 14 siblings

  1. mixmatch_batch entry · level 1 · ran · our draft was wrong · 3164897bcf3781a2
  2. guess_targets helper · level 1 · ran · our draft was wrong · 568ec1709ff7ca07
  3. mixup_samples helper · level 1 · ran · our draft was wrong · 9d112ebaba96ddb1
  4. sharpen helper · level 1 · ran · honoured contract · cbc1955a34800714
  5. tile_adjacent helper · level 1 · ran; the contract check could not run (RAISES) · caacacf94d563a78

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

one of 14 siblings

  1. Wide_ResNet entry · level 1 · ran · 8608707dd0f937bd
  2. BasicBlock helper · level 1 · ran · e4dc4ca4b40de499
  3. NetworkBlock helper · level 1 · ran · 2950d5425e9dd18b

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

one of 14 siblings

  1. WideResNet entry · level 1 · ran · c3d0f2f3671b4bbc
  2. BasicBlock model · level 1 · ran · e4dc4ca4b40de499
  3. NetworkBlock model · level 1 · ran · 2950d5425e9dd18b

harvested Assembly for MixMatch (graph method: MixMatch). 3 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 14 siblings

  1. mixmatch entry · level 1 · ran · honoured contract · 9f0765feb50790dd
  2. classifier_criterion loss · level 1 · ran · our draft was wrong · 3cac74cd5cc4e2f1
  3. tagging_criterion loss · level 1 · ran · our draft was wrong · 670937fdbe1b61da

harvested Assembly for MixMatch (graph method: MixMatch). 1 brick; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 14 siblings

  1. MixMatchLoss entry · level 1 · ran · 4de37e26980b9f34

harvested Assembly for MixMatch (graph method: MixMatch). 5 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 14 siblings

  1. mixmatch entry · level 0 · unverified · b11b94decd7ab296
  2. label_guessing helper · level 0 · unverified · 0ad756f5a68bcd04
  3. mixup_mod helper · level 1 · ran; the contract check could not run (RAISES) · 77308af8bcbb2b2b
  4. sharpen helper · level 1 · ran · honoured contract · 6d22d34f03eff901
  5. to_categorical helper · level 1 · ran; the contract check could not run (RAISES) · 7ccbcdef1f97bdbf

harvested Assembly for MixMatch (graph method: MixMatch). 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 14 siblings

  1. get_weak_augmentation entry · level 1 · ran · our draft was wrong · fbc0e34ee7b8cdb5

harvested Assembly for MixMatch (graph method: MixMatch). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 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 14 siblings

  1. SemiLoss entry · level 1 · ran · 48a12c06cbdd6b70
  2. linear_rampup helper · level 1 · ran · honoured contract · 0aaac678344cd89f

harvested Assembly for MixMatch (graph method: MixMatch). 10 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 14 siblings

  1. mixmatch entry · level 1 · ran; the contract check could not run (RAISES) · 4350f70a89ff949b
  2. augment_labelData data_transform · level 0 · unverified · cd590be04d9864e1
  3. augment_unlabelData data_transform · level 0 · unverified · 21f82c5babfc89be
  4. expand_ulabel helper · level 0 · unverified · 44bd7219e3206702
  5. mixup data_transform · level 1 · ran; the contract check could not run (RAISES) · 65eae886ef202b56
  6. sharpen helper · level 1 · ran · honoured contract · 63688837810c6e5a
  7. split_U helper · level 1 · ran; the contract check could not run (RAISES) · 3c7a33c95b913c66
  8. split_X helper · level 0 · unverified · 0accfa09823d9b0c
  9. augment helper · level 1 · ran; the contract check could not run (RAISES) · 39827536f2c0ed9a
  10. guess_label_with_logit helper · level 0 · unverified · 71516924003b7081
  1. MixMatch · efba25fba581d794 · 3 bricks; individually on a fixture: 2 ran (of which 0 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) · 1 unverified · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. MixMatch · f48dde6f0dc63467 · 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 · assemblies[13] in the JSON twin

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="1905.02249") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image ClassificationSemi-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-10 MixMatch Percentage correct 95.05 #143 of 265 Archive leaderboard report
Image Classification CIFAR-100 MixMatch Percentage correct 74.1 #157 of 211 Archive leaderboard report
Image Classification STL-10 MixMatch Percentage correct 94.41 #22 of 117 Archive leaderboard report
Image Classification STL-10 IIC Percentage correct 88.80 #42 of 117 Archive leaderboard report
Image Classification STL-10 CutOut Percentage correct 87.36 #45 of 117 Archive leaderboard report
Image Classification SVHN MixMatch Percentage error 2.59 #37 of 62 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 1000 Labels MixMatch Accuracy 92.25 #1 of 9 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 2000 Labels MixMatch Accuracy 92.97 #1 of 4 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 250 Labels MixMatch Percentage error 11.08 #22 of 27 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 4000 Labels MixMatch Percentage error 6.24 #30 of 49 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 500 Labels MixMatch Accuracy 91.35 #1 of 1 Archive leaderboard report
Semi-Supervised Image Classification STL-10, 1000 Labels MixMatch Accuracy 89.82 #10 of 13 Archive leaderboard report
Semi-Supervised Image Classification STL-10, 5000 Labels MixMatch Accuracy 94.41 #1 of 1 Archive leaderboard report
Semi-Supervised Image Classification SVHN, 1000 labels MixMatch Accuracy 96.73 #7 of 17 Archive leaderboard report
Semi-Supervised Image Classification SVHN, 2000 Labels MixMatch Accuracy 96.96 #1 of 1 Archive leaderboard report
Semi-Supervised Image Classification SVHN, 250 Labels MixMatch Accuracy 96.22 #8 of 15 Archive leaderboard report
Semi-Supervised Image Classification SVHN, 4000 Labels MixMatch Accuracy 97.11 #1 of 1 Archive leaderboard report
Semi-Supervised Image Classification SVHN, 500 Labels MixMatch Accuracy 96.36 #2 of 6 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.

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