Papers › FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

21 Jan 2020NeurIPS 2020 12arXiv:2001.07685archive 2025-07-28

Kihyuk Sohn, David Berthelot, Chun-Liang Li, Zizhao Zhang, Nicholas Carlini, Ekin D. Cubuk, Alex Kurakin, Han Zhang, Colin Raffel

Semi-supervised learning (SSL) provides an effective means of leveraging unlabeled data to improve a model's performance. In this paper, we demonstrate the power of a simple combination of two common SSL methods: consistency regularization and pseudo-labeling. Our algorithm, FixMatch, first generates pseudo-labels using the model's predictions on weakly-augmented unlabeled images. For a given image, the pseudo-label is only retained if the model produces a high-confidence prediction. The model is then trained to predict the pseudo-label when fed a strongly-augmented version of the same image. Despite its simplicity, we show that FixMatch achieves state-of-the-art performance across a variety of standard semi-supervised learning benchmarks, including 94.93% accuracy on CIFAR-10 with 250 labels and 88.61% accuracy with 40 -- just 4 labels per class. Since FixMatch bears many similarities to existing SSL methods that achieve worse performance, we carry out an extensive ablation study to tease apart the experimental factors that are most important to FixMatch's success. We make our code available at https://github.com/google-research/fixmatch.

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

The archive's official repository (google-research/fixmatch) was not harvested; the 74 samples below come from 18 community repositories.

Syntology 74 code samples harvested from 18 repositories linked to this paper: 53 ran (of which 13 constructed an object rather than computing a result; 25 with no instrument failure: 3 honoured, 2 violated, 20 with no contract checked; 28 where Syntology's instrument failed) · 21 unverified. Where Syntology's instrument failed: 15 where our contract draft was wrong; 13 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 74 samples from 18 repositories, 53 ran (25 with no instrument failure; 28 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 2 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 53 samples that ran has no recorded date.

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

google-research/fixmatch officialmentioned in papermentioned on GitHubtfApache-2.0Syntology: not harvested report
A-Telfer/AugKey mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Unsupervised Data Augmentation for Consistency Training (arXiv:1904.12848; that paper's own run record: 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); nothing checks that they implement this paper's method. report
AhmadQasim/FixMatch mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
Celiali/FixMatch mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
CoinCheung/fixmatch mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
CoinCheung/fixmatch-pytorch mentioned on GitHubpytorchSyntology: 10 samples, 9 ran (8 instrument-failed) · 1 unverified report
DonghwanKIM0101/CS492I_CV mentioned on GitHubpytorchSyntology: not harvested report
KaiyangZhou/ssdg-benchmark mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Semi-Supervised Domain Generalization with Stochastic StyleMatch (arXiv:2106.00592; that paper's own run record: 4 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; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
LeeDoYup/FixMatch-pytorch mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
OFRIN/Tensorflow_FixMatch mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
S-HuaBomb/FixMatch-Paddle mentioned on GitHubpaddleApache-2.0Syntology: 5 samples, 5 ran (3 instrument-failed) · 0 unverified report
SaraAmd/Semi-Supervised-Learning mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
Trayan7/FixMatch-with-Soft-Labels mentioned on GitHubtfApache-2.0Syntology: not harvested report
Valentyn1997/semi-supervised-text-classification mentioned on GitHubpytorchSyntology: not harvested report
Zhongying-Deng/NorMatch mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
amazon-research/exponential-moving-average-normalization mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
fbuchert/fixmatch-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
gomezzz/MSMatch mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
gomezzz/distmsmatch mentioned on GitHubpytorchSyntology: 4 samples, 3 ran (2 instrument-failed) · 1 unverified report
google-research/crest mentioned on GitHubtfSyntology: not harvested report
johnchenresearch/SSL mentioned on GitHubtfApache-2.0Syntology: 5 samples, 1 ran (0 instrument-failed) · 4 unverified report
kekmodel/FixMatch-pytorch mentioned on GitHubpytorchSyntology: 19 samples, 15 ran (10 instrument-failed) · 4 unverified report
phanav/fixmatch-fastai mentioned on GitHubpytorchSyntology: not harvested report
ptrckhmmr/learning-to-defer-with-limited-expert-predictions mentioned on GitHubpytorchSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
valencebond/FixMatch_pytorch mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
miquelmarti/DenseFixMatch pytorchSyntology: 5 samples, 1 ran (0 instrument-failed) · 4 unverified 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

74 samples harvested: 53 ran (of which 13 constructed an object rather than computing a result; 25 with no instrument failure: 3 honoured, 2 violated, 20 with no contract checked; 28 where Syntology's instrument failed) · 21 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.

3ran · honoured contract
2ran · violated contract
15ran · our draft was wrong
13ran; the contract check could not run
20ran
21unverified

Licence: 17 of the 74 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 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 18 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 9 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.

AhmadQasim/FixMatch community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
RandAugmentMC dataset/randaugment.py ran MIT (permissive) · 4e833a8fd83394d8 · report fixture: signature img:Image/0/? · returned Image · level recorded 2026-09-24
CutoutAbs dataset/randaugment.py unverified MIT (permissive) · f4c8609e68ec56f7 · report
Celiali/FixMatch community (archive-listed) 1 sample, 0 ran · 1 unverified
CTAugment augmentations/ctaugment.py unverified MIT (permissive) · d177a39181ef07d4 · report
CoinCheung/fixmatch community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
BasicBlockPreAct model.py ran fingerprinted MIT (permissive) · 8d3a0f01f7775c34 · report fixture: returned BasicBlockPreAct · level recorded 2026-09-22
WideResnet model.py ran fingerprinted MIT (permissive) · b8e244cd7c2d12ef · report fixture: returned WideResnet · level recorded 2026-09-22
WideResnetBackbone model.py ran fingerprinted MIT (permissive) · 03b0c8a89d29142b · report fixture: returned WideResnetBackbone · level recorded 2026-09-22
CoinCheung/fixmatch-pytorch community (archive-listed) 10 samples, 9 ran (8 instrument-failed) · 1 unverified
autocontrast_func in 17 papers randaugment.py ran; the contract check could not run (RAISES) MIT (permissive) · 78ca1debd9c4ed87 · report fixture: signature img:ndarray/3/int, cutoff:int/0/int · returned ndarray · level recorded 2026-09-22
contrast_func randaugment.py ran · violated contract MIT (permissive) · 3cbade2baaefb1c2 · report fixture: signature img:ndarray/3/int, factor:float/0/float · returned ndarray · level recorded 2026-09-22
cutout_func randaugment.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 8a873e1fbc0db2dd · report fixture: signature img:ndarray/3/int, pad_size:int/0/int, replace:tuple/1/int · returned ndarray · level recorded 2026-09-22
equalize_func in 17 papers randaugment.py ran; the contract check could not run (RAISES) MIT (permissive) · 4c53169f63a1fcef · report fixture: signature img:ndarray/3/int · returned ndarray · level recorded 2026-09-22
sharpness_func randaugment.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 8d81faa31f390340 · report fixture: signature img:ndarray/3/int, factor:float/0/float · returned ndarray · level recorded 2026-09-22
shear_x_func randaugment.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 19aacbdbdaa4747b · report fixture: signature img:ndarray/3/int, factor:float/0/float, fill:tuple/1/int · returned ndarray · level recorded 2026-09-22
shear_y_func randaugment.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 6514adf4f71311fc · report fixture: signature img:ndarray/3/int, factor:float/0/float, fill:tuple/1/int · returned ndarray · level recorded 2026-09-22
translate_x_func randaugment.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · adebf590ca9fbf8b · report fixture: signature img:ndarray/3/int, offset:int/0/int, fill:tuple/1/int · returned ndarray · level recorded 2026-09-22
translate_y_func randaugment.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 24b6eed27679e385 · report fixture: signature img:ndarray/3/int, offset:int/0/int, fill:tuple/1/int · returned ndarray · level recorded 2026-09-22
RandomAugment randaugment.py unverified MIT (permissive) · e996de42bfddf014 · report
LeeDoYup/FixMatch-pytorch community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
FixMatch models/fixmatch/fixmatch.py ran MIT (permissive) · 95de992b4cf43fd7 · report fixture: returned FixMatch · level recorded 2026-09-22
consistency_loss in 19 papers models/fixmatch/fixmatch.py ran; the contract check could not run (RAISES) MIT (permissive) · 4a5f8edc558790c2 · report fixture: signature logits_w:Tensor/2/float, logits_s:Tensor/2/float, name:str/0/str, T:float/0/float, p_cutoff:float/0/float, use_hard_labels:bool/0/bool · returned tuple · level recorded 2026-09-22
OFRIN/Tensorflow_FixMatch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
WideResNet in 13 papers core/backbone/wideresnet.py ran no licence file found · pointer only · b16158758833e962 · report fixture: returned WideResNet · level recorded 2026-09-22
S-HuaBomb/FixMatch-Paddle community (archive-listed) 5 samples, 5 ran (3 instrument-failed) · 0 unverified
AutoContrast in 30 papers dataset/randaugment.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · c6e7c3451c85404f · report fixture: signature img:Image/0/? · returned Image · level recorded 2026-09-24
Brightness in 31 papers dataset/randaugment.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 0d1a8d6ce2015fc7 · report fixture: signature img:Image/0/?, v:int/0/int, max_v:float/0/float, bias:float/0/float · returned Image · level recorded 2026-09-24
Color in 29 papers dataset/randaugment.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 32cb3f5760fa593e · report fixture: signature img:Image/0/?, v:int/0/int, max_v:int/0/int, bias:int/0/int · returned Image · level recorded 2026-09-24
calculate_gain in 14 papers models/initializers.py ran Apache-2.0 (permissive) · 96901d00bcfc5b79 · report fixture: signature nonlinearity:str/0/str, param:float/0/float · returned float · level recorded 2026-09-24
x_u_split in 5 papers dataset/cifar.py ran Apache-2.0 (permissive) · 26e39e7c49b447ad · report fixture: signature args:Args/0/?, labels:ndarray/1/int · returned tuple · level recorded 2026-09-24
SaraAmd/Semi-Supervised-Learning community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
ConsistencyRegularization ssl_lib/algs/consistency.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 3476a989bf303448 · report fixture: returned ConsistencyRegularization · level recorded 2026-09-22
sharpening ssl_lib/algs/consistency.py ran · our draft was wrong fingerprinted no licence file found · pointer only · c52f15cee62d6c7a · report fixture: signature soft_labels:Tensor/2/float, temp:float/0/float · returned Tensor · level recorded 2026-09-22
tempereture_softmax ssl_lib/algs/consistency.py ran · honoured contract fingerprinted no licence file found · pointer only · 75653ad24ddcda46 · report fixture: signature logits:Tensor/2/float, tau:float/0/float · returned Tensor · level recorded 2026-09-22
Zhongying-Deng/NorMatch community (archive-listed) 2 samples, 0 ran · 2 unverified
test in 377 papers train_fixmatch.py unverified MIT (permissive) · e516133a9e28be90 · report
train in 522 papers train_fixmatch.py unverified MIT (permissive) · 92bbaed54dcdae65 · report
amazon-research/exponential-moving-average-normalization community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
FixMatch models/fixmatch.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · f97994492ca55ef4 · report fixture: returned FixMatch · level recorded 2026-09-22
ResNet in 139 papers models/fixmatch.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 88b25a8a9dc5f114 · report fixture: returned ResNet · level recorded 2026-09-22
fbuchert/fixmatch-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) · 159f99b81bc70ebc · report fixture: signature img_size:int/0/int, padding:int/0/int, padding_mode:str/0/str · returned Compose · level recorded 2026-09-22
gomezzz/MSMatch community (archive-listed) 3 samples, 2 ran (2 instrument-failed) · 1 unverified
ce_loss in 34 papers models/fixmatch/fixmatch.py ran; the contract check could not run (RAISES) MIT (permissive) · 9723f46ec1689a37 · report fixture: signature logits:Tensor/2/float, targets:Tensor/1/int, use_hard_labels:bool/0/bool, reduction:str/0/str · returned Tensor · level recorded 2026-09-22
consistency_loss in 19 papers models/fixmatch/fixmatch.py ran; the contract check could not run (RAISES) MIT (permissive) · cc357ff67b149646 · report fixture: signature logits_w:Tensor/2/float, logits_s:Tensor/2/float, name:str/0/str, T:float/0/float, p_cutoff:float/0/float, use_hard_labels:bool/0/bool · returned tuple · level recorded 2026-09-22
FixMatch models/fixmatch/fixmatch.py unverified MIT (permissive) · bdc089534fcd34d6 · report
gomezzz/distmsmatch community (archive-listed) 4 samples, 3 ran (2 instrument-failed) · 1 unverified
FixMatch MSMatch/models/fixmatch/FixMatch.py ran MIT (permissive) · 18865f52ae76d33f · report fixture: returned FixMatch · level recorded 2026-09-22
consistency_loss in 19 papers MSMatch/models/fixmatch/FixMatch.py ran; the contract check could not run (RAISES) MIT (permissive) · 5efbd3f44ce7dcf5 · report fixture: signature logits_w:Tensor/2/float, logits_s:Tensor/2/float, name:str/0/str, T:float/0/float, p_cutoff:float/0/float, use_hard_labels:bool/0/bool · returned tuple · level recorded 2026-09-22
cross_entropy_loss in 58 papers MSMatch/models/fixmatch/FixMatch.py ran; the contract check could not run (RAISES) MIT (permissive) · 774112e52d064668 · report fixture: signature logits:Tensor/2/float, targets:Tensor/1/int, use_hard_labels:bool/0/bool, reduction:str/0/str · returned Tensor · level recorded 2026-09-22
johnchenresearch/SSL community (archive-listed) 5 samples, 1 ran (0 instrument-failed) · 4 unverified
safe_mean in 10 papers imagenet/training.py ran Apache-2.0 (permissive) · e220f362daa9561f · report fixture: signature losses:EagerTensor/1/float · returned EagerTensor · level recorded 2026-09-25
entropy_from_logits in 13 papers libml/layers.py unverified Apache-2.0 (permissive) · 0802d913d5d3694d · report
entropy_penalty in 7 papers libml/layers.py unverified Apache-2.0 (permissive) · d5592d7541ebcb31 · report
get_hparams in 9 papers imagenet/training.py unverified Apache-2.0 (permissive) · d418bfeffed76d00 · report
smart_shape in 7 papers libml/layers.py unverified Apache-2.0 (permissive) · 5d8684fa279a5f80 · report
kekmodel/FixMatch-pytorch community (archive-listed) 19 samples, 15 ran (10 instrument-failed) · 4 unverified
mish in 95 papers
census: 5 implementations from 8 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
models/wideresnet.py ran · our draft was wrong fingerprinted MIT (permissive) · 48dececd48e901d2 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
Brightness in 31 papers dataset/randaugment.py ran · our draft was wrong MIT (permissive) · f82e12f0d695e01b · report fixture: signature img:Image/0/?, v:int/0/int, max_v:float/0/float, bias:float/0/float · returned Image · level recorded 2026-09-22
Contrast in 5 papers dataset/randaugment.py ran · our draft was wrong MIT (permissive) · 3a6db236d683df14 · report fixture: signature img:Image/0/?, v:int/0/int, max_v:float/0/float, bias:int/0/int · returned Image · level recorded 2026-09-22
Equalize dataset/randaugment.py ran MIT (permissive) · b6210b47d844e910 · report fixture: signature img:Image/0/? · returned Image · level recorded 2026-09-22
Identity in 49 papers
census: 10 implementations from 13 papers, 4 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 2 of 4, arg 1: rank 4, kind float, dtype float32
dataset/randaugment.py ran · violated contract fingerprinted MIT (permissive) · 0847c9a3c04c392e · report fixture: signature img:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Posterize dataset/randaugment.py ran · our draft was wrong MIT (permissive) · 99a25ff737f67a63 · report fixture: signature img:Image/0/?, v:int/0/int, max_v:int/0/int, bias:int/0/int · returned Image · level recorded 2026-09-22
Rotate in 6 papers dataset/randaugment.py ran · our draft was wrong MIT (permissive) · db8a01288db8d302 · report fixture: signature img:Image/0/?, v:int/0/int, max_v:int/0/int, bias:int/0/int · returned Image · level recorded 2026-09-22
Sharpness dataset/randaugment.py ran · our draft was wrong MIT (permissive) · 6d5a3435d35550b8 · report fixture: returned Image · level recorded 2026-09-22
ShearX in 14 papers dataset/randaugment.py ran · our draft was wrong MIT (permissive) · c069bca31b82aa2c · report fixture: signature img:Image/0/?, v:int/0/int, max_v:int/0/int, bias:int/0/int · returned Image · level recorded 2026-09-22
ShearY in 14 papers dataset/randaugment.py ran · our draft was wrong MIT (permissive) · 47ddf827c80f0e32 · report fixture: signature img:Image/0/?, v:int/0/int, max_v:int/0/int, bias:float/0/float · returned Image · level recorded 2026-09-22
TranslateX in 13 papers dataset/randaugment.py ran · our draft was wrong MIT (permissive) · 623b2503761b36c6 · report fixture: signature img:Image/0/?, v:int/0/int, max_v:int/0/int, bias:int/0/int · returned Image · level recorded 2026-09-22
TranslateY dataset/randaugment.py ran · our draft was wrong MIT (permissive) · c34cf3418c8a3bb9 · report fixture: signature img:Image/0/?, v:int/0/int, max_v:int/0/int, bias:int/0/int · returned Image · level recorded 2026-09-22
_float_parameter dataset/randaugment.py ran · honoured contract fingerprinted MIT (permissive) · c0d914f7e98a27ad · report fixture: signature v:int/0/int, max_v:int/0/int · returned float · level recorded 2026-09-22
_int_parameter dataset/randaugment.py ran · honoured contract fingerprinted MIT (permissive) · 895dd68f0abd14a2 · report fixture: signature v:int/0/int, max_v:int/0/int · returned int · level recorded 2026-09-22
fixmatch_augment_pool dataset/randaugment.py ran MIT (permissive) · e34c59d1eb6d2adb · report fixture: returned list · level recorded 2026-09-22
AutoContrast in 30 papers dataset/randaugment.py unverified MIT (permissive) · 338c2ab566a96a45 · report
Color in 29 papers dataset/randaugment.py unverified MIT (permissive) · fbe48c6053d5de3b · report
Solarize dataset/randaugment.py unverified MIT (permissive) · 38a40a5989234d66 · report
build_wideresnet in 11 papers models/wideresnet.py unverified MIT (permissive) · 73e41df974d19846 · report
ptrckhmmr/learning-to-defer-with-limited-expert-predictions community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
AverageMeter in 26 papers Semi-Supervised/Train_FixMatch.py ran no licence file found · pointer only · 2c90584bcf844d28 · report fixture: returned AverageMeter · level recorded 2026-09-22
ema_model_update Semi-Supervised/Train_FixMatch.py unverified no licence file found · pointer only · dbdbabf6276becac · report
train_one_epoch in 50 papers Semi-Supervised/Train_FixMatch.py unverified no licence file found · pointer only · 0db7aa7734f05609 · report
valencebond/FixMatch_pytorch community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
BasicBlockPreAct models/model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 735c6ea4d3188cf3 · report fixture: returned BasicBlockPreAct · level recorded 2026-09-22
WideResnet models/model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · cee3484c4606263e · report fixture: returned WideResnet · level recorded 2026-09-22
WideResnetBackbone models/model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 6986978358272b46 · report fixture: returned WideResnetBackbone · level recorded 2026-09-22
miquelmarti/DenseFixMatch community (archive-listed) 5 samples, 1 ran (0 instrument-failed) · 4 unverified
OhemCrossEntropy2D ssl_methods/fixmatch.py ran no licence file found · pointer only · 657ea9d40ca81745 · report fixture: signature pred:Tensor/4/float, target:Tensor/3/int · returned Tensor · level recorded 2026-09-24
FixMatch ssl_methods/fixmatch.py unverified no licence file found · pointer only · 2a1f6b2401f82e41 · report
MultiLoss ssl_methods/fixmatch.py unverified no licence file found · pointer only · 980cb93dec539bfb · report
SSLModule ssl_methods/fixmatch.py unverified no licence file found · pointer only · 15c3f5ae1a117ead · report
log_fixmatch ssl_methods/fixmatch.py unverified no licence file found · pointer only · b9973e2e02f8fc7f · 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.

16 assemblies on this paper: 16 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

16 sibling assemblies for FixMatch (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 16 sibling assemblies; the other 4 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for FixMatch (graph method: FixMatch). 5 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) · 4 unverified. The assembly has not been run end-to-end.

one of 16 siblings

  1. FixMatch entry · level 0 · unverified · 2a1f6b2401f82e41
  2. MultiLoss loss · level 0 · unverified · 980cb93dec539bfb
  3. OhemCrossEntropy2D loss · level 1 · ran · 657ea9d40ca81745
  4. SSLModule helper · level 0 · unverified · 15c3f5ae1a117ead
  5. log_fixmatch helper · level 0 · unverified · b9973e2e02f8fc7f

harvested Assembly for FixMatch (graph method: FixMatch). 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 16 siblings

  1. FixMatch entry · level 1 · ran · f97994492ca55ef4
  2. ResNet model · level 1 · ran · 88b25a8a9dc5f114

harvested Assembly for FixMatch (graph method: FixMatch). 17 bricks; individually on a fixture: 14 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 16 siblings

  1. fixmatch_augment_pool entry · level 1 · ran · e34c59d1eb6d2adb
  2. AutoContrast data_transform · level 0 · unverified · 338c2ab566a96a45
  3. Brightness data_transform · level 1 · ran · our draft was wrong · f82e12f0d695e01b
  4. Color data_transform · level 0 · unverified · fbe48c6053d5de3b
  5. Contrast data_transform · level 1 · ran · our draft was wrong · 3a6db236d683df14
  6. Equalize data_transform · level 1 · ran · b6210b47d844e910
  7. Identity data_transform · level 1 · ran · violated contract · 0847c9a3c04c392e
  8. Posterize data_transform · level 1 · ran · our draft was wrong · 99a25ff737f67a63
  9. Rotate data_transform · level 1 · ran · our draft was wrong · db8a01288db8d302
  10. Sharpness data_transform · level 1 · ran · our draft was wrong · 6d5a3435d35550b8
  11. ShearX data_transform · level 1 · ran · our draft was wrong · c069bca31b82aa2c
  12. ShearY data_transform · level 1 · ran · our draft was wrong · 47ddf827c80f0e32
  13. Solarize data_transform · level 0 · unverified · 38a40a5989234d66
  14. TranslateX data_transform · level 1 · ran · our draft was wrong · 623b2503761b36c6
  15. TranslateY data_transform · level 1 · ran · our draft was wrong · c34cf3418c8a3bb9
  16. _float_parameter helper · level 1 · ran · honoured contract · c0d914f7e98a27ad
  17. _int_parameter helper · level 1 · ran · honoured contract · 895dd68f0abd14a2

harvested Assembly for FixMatch (graph method: FixMatch). 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 16 siblings

  1. WideResnet entry · level 1 · ran · cee3484c4606263e
  2. WideResnetBackbone model · level 1 · ran · 6986978358272b46
  3. BasicBlockPreAct model · level 1 · ran · 735c6ea4d3188cf3

harvested Assembly for FixMatch (graph method: FixMatch). 3 bricks; individually on a fixture: 3 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; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 16 siblings

  1. ConsistencyRegularization entry · level 1 · ran · 3476a989bf303448
  2. sharpening helper · level 1 · ran · our draft was wrong · c52f15cee62d6c7a
  3. tempereture_softmax helper · level 1 · ran · honoured contract · 75653ad24ddcda46

harvested Assembly for FixMatch (graph method: FixMatch). 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 16 siblings

  1. get_weak_augmentation entry · level 1 · ran · our draft was wrong · 159f99b81bc70ebc

harvested Assembly for FixMatch (graph method: FixMatch). 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 16 siblings

  1. WideResnet entry · level 1 · ran · b8e244cd7c2d12ef
  2. WideResnetBackbone model · level 1 · ran · 03b0c8a89d29142b
  3. BasicBlockPreAct model · level 1 · ran · 8d3a0f01f7775c34

harvested Assembly for FixMatch (graph method: FixMatch). 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 16 siblings

  1. WideResNet entry · level 1 · ran · b16158758833e962

harvested Assembly for FixMatch (graph method: FixMatch). 3 bricks; 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) · 2 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 16 siblings

  1. train_one_epoch entry · level 0 · unverified · 0db7aa7734f05609
  2. AverageMeter helper · level 1 · ran · 2c90584bcf844d28
  3. ema_model_update update_rule · level 0 · unverified · dbdbabf6276becac

harvested Assembly for FixMatch (graph method: FixMatch). 5 bricks; individually on a fixture: 2 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; 2 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 16 siblings

  1. train entry · level 0 · unverified · 92bbaed54dcdae65
  2. de_interleave helper · level 1 · ran · our draft was wrong · 27ae5d495ffa4282
  3. interleave helper · level 1 · ran · our draft was wrong · f6043e7798bcabbd
  4. save_checkpoint helper · level 0 · unverified · 853f415fdc5443ea
  5. test helper · level 0 · unverified · e516133a9e28be90

harvested Assembly for FixMatch (graph method: FixMatch). 19 bricks; individually on a fixture: 15 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 1 violated, 3 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 16 siblings

  1. RandAugmentMC entry · level 1 · ran · 4e833a8fd83394d8
  2. CutoutAbs data_transform · level 0 · unverified · f4c8609e68ec56f7
  3. fixmatch_augment_pool data_transform · level 1 · ran · e34c59d1eb6d2adb
  4. AutoContrast data_transform · level 0 · unverified · 338c2ab566a96a45
  5. Brightness data_transform · level 1 · ran · our draft was wrong · f82e12f0d695e01b
  6. Color data_transform · level 0 · unverified · fbe48c6053d5de3b
  7. Contrast data_transform · level 1 · ran · our draft was wrong · 3a6db236d683df14
  8. Equalize data_transform · level 1 · ran · b6210b47d844e910
  9. Identity data_transform · level 1 · ran · violated contract · 0847c9a3c04c392e
  10. Posterize data_transform · level 1 · ran · our draft was wrong · 99a25ff737f67a63
  11. Rotate data_transform · level 1 · ran · our draft was wrong · db8a01288db8d302
  12. Sharpness data_transform · level 1 · ran · our draft was wrong · 6d5a3435d35550b8
  13. ShearX data_transform · level 1 · ran · our draft was wrong · c069bca31b82aa2c
  14. ShearY data_transform · level 1 · ran · our draft was wrong · 47ddf827c80f0e32
  15. Solarize data_transform · level 0 · unverified · 38a40a5989234d66
  16. TranslateX data_transform · level 1 · ran · our draft was wrong · 623b2503761b36c6
  17. TranslateY data_transform · level 1 · ran · our draft was wrong · c34cf3418c8a3bb9
  18. _float_parameter helper · level 1 · ran · honoured contract · c0d914f7e98a27ad
  19. _int_parameter helper · level 1 · ran · honoured contract · 895dd68f0abd14a2

harvested Assembly for FixMatch (graph method: FixMatch). 4 bricks; individually on a fixture: 4 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; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 16 siblings

  1. FixMatch entry · level 1 · ran · 95de992b4cf43fd7
  2. Get_Scalar helper · level 1 · ran · 78afd5155edadae1
  3. ce_loss loss · level 1 · ran; the contract check could not run · 0c1d927c0e848f5c
  4. consistency_loss loss · level 1 · ran; the contract check could not run (RAISES) · 4a5f8edc558790c2
  1. FixMatch · ba71d6adcbe71a63 · 4 bricks; individually on a fixture: 3 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; 2 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. RandomAugment · c06be796a0b835e6 · 23 bricks; individually on a fixture: 21 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 18 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
  3. CTAugment · e2da4b3d62580515 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
  4. FixMatch · fe34058d0e8e51e5 · 5 bricks; individually on a fixture: 3 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; 2 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[15] 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="2001.07685") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image ClassificationPseudo LabelSemi-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Image Classification CIFAR-10, 100 Labels (OpenSet, 6/4) FixMatch Accuracy 70.2 #4 of 4 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 250 Labels FixMatch (CTA) Percentage error 5.07±0.33 #16 of 27 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 40 Labels FixMatch (CTA) Percentage error 11.39±3.35 #18 of 21 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 400 Labels (OpenSet, 6/4) FixMatch Accuracy 83.7 #4 of 4 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 4000 Labels FixMatch (CTA) Percentage error 4.31 #18 of 49 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 50 Labels (OpenSet, 6/4) FixMatch Accuracy 56.8 #4 of 4 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-100, 2500 Labels FixMatch (CTA, WRN-28-8) Percentage error 28.64±0.24 #16 of 16 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-100, 400 Labels FixMatch (CTA) Percentage error 49.95±3.01 #21 of 21 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data FixMatch Top 5 Accuracy 89.13% #54 of 75 Archive leaderboard report
Semi-Supervised Image Classification STL-10, 1000 Labels FixMatch (CTA) Accuracy 94.83±0.63 #6 of 13 Archive leaderboard report
Semi-Supervised Image Classification SVHN, 1000 labels FixMatch (CTA) Accuracy 97.64±0.19 #3 of 17 Archive leaderboard report
Semi-Supervised Image Classification SVHN, 40 Labels FixMatch (CTA) Percentage error 7.65±7.65 #4 of 5 Archive leaderboard report
Semi-Supervised Image Classification cifar-100, 10000 Labels FixMatch (RA, WRN-28-8) Percentage error 22.6 #16 of 29 Archive leaderboard report
Semi-Supervised Image Classification cifar-100, 10000 Labels FixMatch (CTA, WRN-28-8) Percentage error 23.18±0.11 #19 of 29 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

Introduced by this paper: FixMatch

FixMatch

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