Papers › An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

22 Oct 2020ICLR 2021 1arXiv:2010.11929archive 2025-07-28

Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby

While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional networks, or used to replace certain components of convolutional networks while keeping their overall structure in place. We show that this reliance on CNNs is not necessary and a pure transformer applied directly to sequences of image patches can perform very well on image classification tasks. When pre-trained on large amounts of data and transferred to multiple mid-sized or small image recognition benchmarks (ImageNet, CIFAR-100, VTAB, etc.), Vision Transformer (ViT) attains excellent results compared to state-of-the-art convolutional networks while requiring substantially fewer computational resources to train.

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 419 code samples: 418 from 76 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 419: 307 ran (of which 165 constructed an object rather than computing a result; 286 with no instrument failure: 8 honoured, 2 violated, 276 with no contract checked; 21 where Syntology's instrument failed) · 112 unverified. Where Syntology's instrument failed: 10 where our contract draft was wrong; 11 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 409 samples from 74 repositories, 303 ran (286 with no instrument failure; 17 where Syntology's instrument failed); community: 3 samples from 1 repository, 3 ran (0 with no instrument failure; 3 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 31 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. 6 of the 307 samples that ran have no recorded date.

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

google-research/vision_transformer officialmentioned in papermentioned on GitHubjaxSyntology: 6 samples, 0 ran · 6 unverified report
04RR/SOTA-Vision mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
Abdulrahman-Adel/Real-Life-Violence-Detection mentioned on GitHubtfSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
Aedelon/ViT-PyTorch-Replication mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
AlifAshrafee/ViT-pytorch-for-Cooking-State-Recognition mentioned on GitHubpytorchSyntology: 3 samples, 0 ran · 3 unverified report
BaiqiangGit/15minCode mentioned on GitHubpytorchSyntology: not harvested report
BebDong/MXNetSeg mentioned on GitHubmxnetApache-2.0Syntology: not harvested report
BrianPulfer/PapersReimplementations mentioned on GitHubpytorchSyntology: 5 samples, 5 ran (1 instrument-failed) · 0 unverified report
Burf/VisionTransformer-Tensorflow2 mentioned on GitHubtfSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
DominikBatic/EndoViT mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
HyeonhoonLee/MAIC2021_Sleep mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (arXiv:1905.11946; that paper's own run record: 198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified); nothing checks that they implement this paper's method. report
IMvision12/keras-vision-models mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (arXiv:2103.14030; that paper's own run record: 123 ran (of which 45 constructed an object rather than computing a result; 79 with no instrument failure: 6 honoured, 3 violated, 70 with no contract checked; 44 where Syntology's instrument failed) · 84 unverified); nothing checks that they implement this paper's method. report
Julien-pour/music_classifcation mentioned on GitHubpytorchSyntology: not harvested report
KatherLab/HIA mentioned on GitHubpytorchSyntology: not harvested report
Kevinz-code/CSRA mentioned on GitHubpytorchAGPL-3.0Syntology: not harvested report
KiUngSong/Vision mentioned on GitHubpytorchSyntology: 7 samples, 7 ran (0 instrument-failed) · 0 unverified report
Mayurji/Image-Classification-PyTorch mentioned on GitHubpytorchSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
Mind23-2/MindCode-1 mentioned on GitHubpaddleSyntology: not harvested report
Mind23-2/MindCode-89 mentioned on GitHubmindsporeSyntology: not harvested report
SHI-Labs/Compact-Transformers mentioned on GitHubpytorchSyntology: 7 samples, 7 ran (1 instrument-failed) · 0 unverified report
SforAiDl/vformer mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Vision Transformers for Dense Prediction (arXiv:2103.13413; that paper's own run record: 65 ran (of which 19 constructed an object rather than computing a result; 32 with no instrument failure: 0 honoured, 0 violated, 32 with no contract checked; 33 where Syntology's instrument failed) · 51 unverified) and ViViT: A Video Vision Transformer (arXiv:2103.15691; that paper's own run record: 14 ran (of which 10 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
SrinjaySarkar/ViT mentioned on GitHubpytorchSyntology: not harvested report
SupreethRao99/VisionTransformer mentioned on GitHubpytorchSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
TACJu/TransFG mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to TransFG: A Transformer Architecture for Fine-grained Recognition (arXiv:2103.07976; that paper's own run record: 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); nothing checks that they implement this paper's method. report
Thanusan19/Vision_Transformer mentioned on GitHubjaxApache-2.0Syntology: 11 samples, 8 ran (0 instrument-failed) · 3 unverified report
TheTensorDude/vision_transformer_tf mentioned on GitHubtfSyntology: 8 samples, 5 ran (1 instrument-failed) · 3 unverified report
UdbhavPrasad072300/Transformer-Implementation mentioned on GitHubpytorchMITSyntology: not harvested report
UdbhavPrasad072300/Transformer-Implementation-and-Language-Translation mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
UdbhavPrasad072300/Transformer-Implementations mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Training data-efficient image transformers & distillation through attention (arXiv:2012.12877; that paper's own run record: 12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
Ugenteraan/Masked-AutoEncoder-PyTorch mentioned on GitHubpytorchSyntology: 7 samples, 6 ran (0 instrument-failed) · 1 unverified report
Ugenteraan/Vanilla-ViT mentioned on GitHubpytorchSyntology: 9 samples, 6 ran (0 instrument-failed) · 3 unverified report
Westlake-AI/openmixup 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), Visualizing the Loss Landscape of Neural Nets (arXiv:1712.09913; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified), CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features (arXiv:1905.04899; that paper's own run record: 17 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
YanYan0716/vision_transform mentioned on GitHubtfSyntology: not harvested report
YousefGamal220/Vision-Transformers mentioned on GitHubpytorchSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
alililia/vit_base_Ascend mentioned on GitHubmindsporeApache-2.0Syntology: not harvested report
alililia/vit_base_GPU mentioned on GitHubmindsporeApache-2.0Syntology: not harvested report
asarigun/TransGAN mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
ashishpatel26/Vision-Transformer-Keras-Tensorflow-Pytorch-Examples mentioned on GitHubpytorchSyntology: not harvested report
asyml/vision-transformer-pytorch mentioned on GitHubjaxSyntology: 7 samples, 7 ran (0 instrument-failed) · 0 unverified report
bshantam97/Attention_Based_Networks mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
charchit7/Using_Transoformers mentioned on GitHubpytorchSyntology: not harvested report
conceptofmind/ViT-haiku mentioned on GitHubjaxSyntology: 6 samples, 0 ran · 6 unverified report
davisking/dlib-models mentioned on GitHubCC0-1.0Syntology: not harvested report
dispink/xpt mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
drumpt/ViT mentioned on GitHubpytorchSyntology: 7 samples, 7 ran (0 instrument-failed) · 0 unverified report
explainingai-code/VIT-Pytorch mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
facebookresearch/hiera mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles (arXiv:2306.00989; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
facebookresearch/vissl mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles (arXiv:1603.09246; that paper's own run record: 10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified), Unsupervised Representation Learning by Predicting Image Rotations (arXiv:1803.07728; that paper's own run record: 16 ran (of which 7 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified), BEiT: BERT Pre-Training of Image Transformers (arXiv:2106.08254; that paper's own run record: 6 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
faustomorales/vit-keras mentioned on GitHubtfSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
gimme1dollar/vision-transformer mentioned on GitHubSyntology: not harvested report
gmum/dl-mo-2021 mentioned on GitHubSyntology: not harvested report
gnoses/ViT_examples mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
haiyang-w/git mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
holdfire/CLS mentioned on GitHubpytorchSyntology: not harvested report
holdfire/FAS mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Training data-efficient image transformers & distillation through attention (arXiv:2012.12877; that paper's own run record: 12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified) and Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (arXiv:2103.14030; that paper's own run record: 123 ran (of which 45 constructed an object rather than computing a result; 79 with no instrument failure: 6 honoured, 3 violated, 70 with no contract checked; 44 where Syntology's instrument failed) · 84 unverified); nothing checks that they implement this paper's method. report
huggingface/transformers mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified), HuggingFace's Transformers: State-of-the-art Natural Language Processing (arXiv:1910.03771; that paper's own run record: 3 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; 3 where Syntology's instrument failed) · 0 unverified), DeBERTa: Decoding-enhanced BERT with Disentangled Attention (arXiv:2006.03654; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
innat/LearnedResizer-Vision-Transformer mentioned on GitHubtfSyntology: not harvested report
jacobgil/vit-explain mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
jaketae/mlp-mixer mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MLP-Mixer: An all-MLP Architecture for Vision (arXiv:2105.01601; that paper's own run record: 114 ran (of which 77 constructed an object rather than computing a result; 104 with no instrument failure: 2 honoured, 1 violated, 101 with no contract checked; 10 where Syntology's instrument failed) · 20 unverified); nothing checks that they implement this paper's method. report
james77777778/keras-image-models mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to GhostNetV3: Exploring the Training Strategies for Compact Models (arXiv:2404.11202; that paper's own run record: 3 ran (of which 0 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); nothing checks that they implement this paper's method. report
jeonsworld/ViT-pytorch mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
jiangtaoxie/So-ViT mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
jo1jun/Vision_Transformer mentioned on GitHubpytorchSyntology: not harvested report
junyongyou/triq mentioned on GitHubpytorchSyntology: 7 samples, 2 ran (0 instrument-failed) · 5 unverified report
kakaobrain/coyo-dataset mentioned on GitHubpytorchSyntology: not harvested report
kingcong/vit mentioned on GitHubmindsporenot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
konstantinos-p/image_classification_SOTA mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
leemsaebom/attention-guided-cam-visual-explanations-of-vision-transformer-guided-by-self-attention mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Quantifying Attention Flow in Transformers (arXiv:2005.00928; that paper's own run record: 2 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; 1 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
liuxingwt/CLS mentioned on GitHubpytorchSyntology: not harvested report
ludics/ViT-Retri mentioned on GitHubpytorchSyntology: 5 samples, 2 ran (0 instrument-failed) · 3 unverified report
lukas-blecher/LaTeX-OCR mentioned on GitHubpytorchMITSyntology: 11 samples, 6 ran (0 instrument-failed) · 5 unverified report
mahmoodlab/hipt mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
martinsbruveris/tensorflow-image-models mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MLP-Mixer: An all-MLP Architecture for Vision (arXiv:2105.01601; that paper's own run record: 114 ran (of which 77 constructed an object rather than computing a result; 104 with no instrument failure: 2 honoured, 1 violated, 101 with no contract checked; 10 where Syntology's instrument failed) · 20 unverified); nothing checks that they implement this paper's method. report
meowbutlerdev/ViT mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
modeeric/eegvit-tcnet mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
mtancak/PyTorch-ViT-Visual-Transformer mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
mtancak1/PyTorch-ViT-Visual-Transformer mentioned on GitHubpytorchSyntology: not harvested report
mujiyantosvc/Facial-Expression-Recognition-FER-for-Mental-Health-Detection- mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
nachiket273/VisTrans mentioned on GitHubpytorchSyntology: 10 samples, 5 ran (1 instrument-failed) · 5 unverified report
nachiket273/Vision_transformer_pytorch mentioned on GitHubpytorchSyntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report
nasa-impact/hls-foundation-os mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Masked Autoencoders Are Scalable Vision Learners (arXiv:2111.06377; that paper's own run record: 86 ran (of which 40 constructed an object rather than computing a result; 68 with no instrument failure: 8 honoured, 0 violated, 60 with no contract checked; 18 where Syntology's instrument failed) · 51 unverified); nothing checks that they implement this paper's method. report
nateraw/lightning-vision-transformer mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
naver-ai/pflayer mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
nima1999nikkhah/ViT-Hybrid mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
protonx-engineering/vit mentioned on GitHubtfSyntology: not harvested report
purbayankar/Hyperspectral-Vision-Transformer mentioned on GitHubpytorchSyntology: not harvested report
qiaopTDUN/mae-repo mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
quanmario0311/ViT_PyTorch mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
rayanramoul/Visual-Transformer-PyTorch mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
ruiqirichard/eegeyenet-vit mentioned on GitHubpytorchSyntology: not harvested report
rwightman/pytorch-image-models mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (arXiv:2006.08217; that paper's own run record: 4 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; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
s-chh/pytorch-scratch-vision-transformer-vit mentioned on GitHubpytorchSyntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report
sangHa0411/VIT mentioned on GitHubpytorchSyntology: 7 samples, 6 ran (0 instrument-failed) · 1 unverified report
sayannath/ViT-Image-Classification mentioned on GitHubApache-2.0Syntology: not harvested report
shahrukhx01/ocr-test mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified); nothing checks that they implement this paper's method. report
skchen1993/TrangFG mentioned on GitHubpytorchSyntology: 8 samples, 5 ran (0 instrument-failed) · 3 unverified report
sliao-mi-luku/Galaxy-Zoo-Classification mentioned on GitHubpytorchMITSyntology: not harvested report
smitheric95/MoCoViT-PyTorch mentioned on GitHubpytorchSyntology: not harvested report
smu-ivpl/DeepfakeDetection mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
sneakatyou/ViT-Tensorflow-2.0 mentioned on GitHubtfSyntology: not harvested report
staghado/vit.cpp mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
stevenwalton/scs-cct mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
tahmid0007/VisionTransformer mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
timH6502/VisionTransformer-PyTorch mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
tintn/vision-transformer-from-scratch mentioned on GitHubpytorchSyntology: 10 samples, 7 ran (0 instrument-failed) · 3 unverified report
ttt496/VisionTransformer mentioned on GitHubjaxSyntology: 5 samples, 0 ran · 5 unverified report
tw-yuhsi/a-new-perspective-for-shuttlecock-hitting-event-detection mentioned on GitHubpytorchSyntology: not harvested report
uygarkurt/ViT-PyTorch mentioned on GitHubpytorchSyntology: not harvested report
wangguanan/light-reid mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
wish44165/A-New-Perspective-for-Shuttlecock-Hitting-Event-Detection mentioned on GitHubpytorchSyntology: not harvested report
woctezuma/steam-CLIP mentioned on GitHubMITSyntology: not harvested report
zpc-666/Paddle-R-Drop mentioned on GitHubpaddleApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to R-Drop: Regularized Dropout for Neural Networks (arXiv:2106.14448; that paper's own run record: 4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
BR-IDL/PaddleViT paddleSyntology: not harvested report
DavidLandup0/deepvision pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EfficientNetV2: Smaller Models and Faster Training (arXiv:2104.00298; that paper's own run record: 55 ran (of which 14 constructed an object rather than computing a result; 43 with no instrument failure: 11 honoured, 0 violated, 32 with no contract checked; 12 where Syntology's instrument failed) · 24 unverified) and SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers (arXiv:2105.15203; that paper's own run record: 66 ran (of which 22 constructed an object rather than computing a result; 52 with no instrument failure: 1 honoured, 2 violated, 49 with no contract checked; 14 where Syntology's instrument failed) · 20 unverified); nothing checks that they implement this paper's method. report
HzcIrving/DeepLearning_PlayGround pytorchSyntology: 7 samples, 4 ran (1 instrument-failed) · 3 unverified report
MindSpore-scientific/code-7 Syntology: not harvested report
OML-Team/open-metric-learning pytorchSyntology: 12 samples, 9 ran (2 instrument-failed) · 3 unverified report
Oguzhanercan/Vision-Transformers Syntology: not harvested report
PaddlePaddle/PASSL paddleApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DINOv2: Learning Robust Visual Features without Supervision (arXiv:2304.07193; that paper's own run record: 39 ran (of which 13 constructed an object rather than computing a result; 32 with no instrument failure: 2 honoured, 0 violated, 30 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
PaddlePaddle/PLSC paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Token Merging: Your ViT But Faster (arXiv:2210.09461; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
PaddlePaddle/PaddleClas paddleApache-2.0Syntology: not harvested report
The-AI-Summer/self_attention pytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
ZhouDaShan123/vit mindsporeApache-2.0Syntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
affjljoo3581/deit3-jax jaxSyntology: 7 samples, 3 ran (0 instrument-failed) · 4 unverified report
ahmed-alllam/Equinox jaxSyntology: 8 samples, 4 ran (0 instrument-failed) · 4 unverified report
alibaba/EasyCV pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to End-to-End Object Detection with Transformers (arXiv:2005.12872; that paper's own run record: 70 ran (of which 45 constructed an object rather than computing a result; 62 with no instrument failure: 2 honoured, 1 violated, 59 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified), Training data-efficient image transformers & distillation through attention (arXiv:2012.12877; that paper's own run record: 12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified), Masked Autoencoders Are Scalable Vision Learners (arXiv:2111.06377; that paper's own run record: 86 ran (of which 40 constructed an object rather than computing a result; 68 with no instrument failure: 8 honoured, 0 violated, 60 with no contract checked; 18 where Syntology's instrument failed) · 51 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
arkel23/PyTorch-Pretrained-ViT pytorchSyntology: 37 samples, 31 ran (4 instrument-failed) · 6 unverified report
avinash31d/paper-implementations tfSyntology: not harvested report
emla2805/vision-transformer tfSyntology: not harvested report
facebookresearch/ClassyVision pytorchSyntology: 9 samples, 5 ran (0 instrument-failed) · 4 unverified report
gupta-abhay/ViT pytorchSyntology: 7 samples, 5 ran (0 instrument-failed) · 2 unverified report
jankrepl/mildlyoverfitted jaxSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
kamalkraj/Vision-Transformer tfSyntology: 8 samples, 6 ran (1 instrument-failed) · 2 unverified report
keras-team/keras-cv tfSyntology: not harvested report
keras-team/keras-io tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to The Forward-Forward Algorithm: Some Preliminary Investigations (arXiv:2212.13345; that paper's own run record: 18 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 2 violated, 9 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
kornia/kornia pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer (arXiv:2110.02178; that paper's own run record: 53 ran (of which 31 constructed an object rather than computing a result; 44 with no instrument failure: 1 honoured, 0 violated, 43 with no contract checked; 9 where Syntology's instrument failed) · 15 unverified); nothing checks that they implement this paper's method. report
labmlai/annotated_deep_learning_paper_implementations pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Playing Atari with Deep Reinforcement Learning (arXiv:1312.5602; that paper's own run record: 64 ran (of which 24 constructed an object rather than computing a result; 46 with no instrument failure: 5 honoured, 0 violated, 41 with no contract checked; 18 where Syntology's instrument failed) · 53 unverified), Adam: A Method for Stochastic Optimization (arXiv:1412.6980; that paper's own run record: 27 ran (of which 7 constructed an object rather than computing a result; 23 with no instrument failure: 4 honoured, 2 violated, 17 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified), Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 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; 5 where Syntology's instrument failed) · 2 unverified) and 12 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
lucidrains/vit-pytorch pytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
lukemelas/PyTorch-Pretrained-ViT pytorchSyntology: 11 samples, 10 ran (0 instrument-failed) · 1 unverified report
mashaan14/VisionTransformer-MNIST pytorchSyntology: not harvested report
mdmhriday/vision-transformers pytorchSyntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report
megvii-research/basecls Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ResMLP: Feedforward networks for image classification with data-efficient training (arXiv:2105.03404; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
mindspore-ecosystem/mindcv mindsporeSyntology: not harvested report
open-mmlab/mmclassification pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Reversible Vision Transformers (arXiv:2302.04869; that paper's own run record: 24 ran (of which 5 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
pytorch/vision pytorchSyntology: 10 samples, 6 ran (0 instrument-failed) · 4 unverified report
ra1ph2/Vision-Transformer pytorchSyntology: not harvested report
septmars/DL pytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection (arXiv:2503.02424; that paper's own run record: 4 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; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
seujung/pytorch-vit pytorchBSD-2-ClauseSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
soumik12345/Vision-Transformer tfSyntology: not harvested report
towhee-io/towhee pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Perceiver: General Perception with Iterative Attention (arXiv:2103.03206; that paper's own run record: 41 ran (of which 20 constructed an object rather than computing a result; 30 with no instrument failure: 0 honoured, 2 violated, 28 with no contract checked; 11 where Syntology's instrument failed) · 14 unverified), LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval (arXiv:2103.08784; that paper's own run record: 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) and 9 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
tuvovan/Vision_Transformer_Keras tfSyntology: not harvested report
uzi0espil/research-papers-implementation tfSyntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified report
xiuyu0000/new_papers_codes mindsporeSyntology: not harvested report
xiuyu0000/papers_with_examples mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Lite-HRNet: A Lightweight High-Resolution Network (arXiv:2104.06403; that paper's own run record: 13 ran (of which 2 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. report
zer0sh0t/artificial_intelligence pytorchSyntology: not harvested report
gitlab.com/birder/birder 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

419 samples harvested: 307 ran (of which 165 constructed an object rather than computing a result; 286 with no instrument failure: 8 honoured, 2 violated, 276 with no contract checked; 21 where Syntology's instrument failed) · 112 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

8ran · honoured contract
2ran · violated contract
10ran · our draft was wrong
11ran; the contract check could not run
276ran
112unverified

Licence: 154 of the 419 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 76 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. 1 sample is listed last, in a group without a repository. “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 82 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.

google-research/vision_transformer official repository 6 samples, 0 ran · 6 unverified
AddPositionEmbs vit_jax/models_vit.py unverified Apache-2.0 (permissive) · 6ff7674fd4a1e78f · report
Encoder in 278 papers vit_jax/models_vit.py unverified Apache-2.0 (permissive) · d04af6e387bb311f · report
Encoder1DBlock vit_jax/models_vit.py unverified Apache-2.0 (permissive) · 2af127aced976756 · report
IdentityLayer in 7 papers vit_jax/models_vit.py unverified Apache-2.0 (permissive) · 145a84ea745a049d · report
MlpBlock in 9 papers vit_jax/models_vit.py unverified Apache-2.0 (permissive) · 8ce4cd665a6aa6ba · report
VisionTransformer in 53 papers vit_jax/models_vit.py unverified Apache-2.0 (permissive) · bd276b1048e360eb · report
04RR/SOTA-Vision community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
MultiHeadSelfAttention in 17 papers ViT.py ran fingerprinted no licence file found · pointer only · d55ce4c4028d4526 · report fixture: signature x:Tensor/3/float, mask:NoneType/0/? · returned Tensor · level recorded 2026-09-24
TransformerBlock in 73 papers ViT.py ran no licence file found · pointer only · 625ba3d0632ccbe7 · report fixture: returned TransformerBlock · level recorded 2026-09-22
TransformerEncoder in 96 papers ViT.py ran no licence file found · pointer only · 134208def7ab098a · report fixture: returned TransformerEncoder · level recorded 2026-09-22
ViT in 10 papers ViT.py ran no licence file found · pointer only · d731587d6e142b9b · report fixture: returned ViT · level recorded 2026-09-22
Abdulrahman-Adel/Real-Life-Violence-Detection community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
MHA in 5 papers src/models/model_01.py ran no licence file found · pointer only · ca90f65590baa86d · report fixture: returned MHA · level recorded 2026-09-22
MLP in 375 papers src/models/model_01.py ran no licence file found · pointer only · 9c26e415cce13732 · report fixture: returned MLP · level recorded 2026-09-22
Projection in 10 papers src/models/model_01.py ran no licence file found · pointer only · 6869723b450cdb3e · report fixture: returned Projection · level recorded 2026-09-22
TransformerEncoder in 96 papers src/models/model_01.py ran no licence file found · pointer only · 894b2c3643a958ca · report fixture: returned TransformerEncoder · level recorded 2026-09-22
VisionTransformer in 53 papers src/models/model_01.py unverified no licence file found · pointer only · e37137b1becc1165 · report
Aedelon/ViT-PyTorch-Replication community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
PatchEmbedding in 25 papers python_files/modules.py ran · metamorphic tier: deterministic MIT (permissive) · ffe7a41ff6c1d31f · report fixture: returned PatchEmbedding · level recorded 2026-09-22
ViT in 10 papers python_files/modules.py ran · metamorphic tier: deterministic MIT (permissive) · a00fdbf5db4c324e · report fixture: returned ViT · level recorded 2026-09-22
AlifAshrafee/ViT-pytorch-for-Cooking-State-Recognition community (archive-listed) 3 samples, 0 ran · 3 unverified
Embeddings in 15 papers models/modeling.py unverified MIT (permissive) · b5fcd7ed78f606f9 · report
Transformer in 173 papers models/modeling.py unverified MIT (permissive) · 00b904015377ff38 · report
VisionTransformer in 53 papers models/modeling.py unverified MIT (permissive) · 7fc8f8faa831f7f2 · report
BrianPulfer/PapersReimplementations community (archive-listed) 5 samples, 5 ran (1 instrument-failed) · 0 unverified
MyMSA src/cv/vit/vit_torch.py ran fingerprinted MIT (permissive) · 09e107c3fe162d2e · report fixture: returned MyMSA · level recorded 2026-09-22
MyViT src/cv/vit/vit_torch.py ran MIT (permissive) · e7b7aac0381fa91a · report fixture: returned MyViT · level recorded 2026-09-22
MyViTBlock src/cv/vit/vit_torch.py ran MIT (permissive) · 04e920afd62b7a39 · report fixture: returned MyViTBlock · level recorded 2026-09-22
get_positional_embeddings src/cv/vit/vit_torch.py ran · honoured contract fingerprinted MIT (permissive) · 2c03aebe822ef336 · report fixture: signature sequence_length:int/0/int, d:int/0/int · returned Tensor · level recorded 2026-09-22
patchify in 32 papers
census: 6 implementations from 8 papers, 6 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 4, kind float, dtype float32
src/cv/vit/vit_torch.py ran; the contract check could not run (RAISES) MIT (permissive) · 49c15b51568e396b · report fixture: signature images:Tensor/4/float, n_patches:int/0/int · returned Tensor · level recorded 2026-09-22
Burf/VisionTransformer-Tensorflow2 community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
MultiHeadSelfAttention in 17 papers vit/vit.py ran MIT (permissive) · 36d6e2f710d562d7 · report fixture: returned MultiHeadSelfAttention · level recorded 2026-09-22
TransformerBlock in 73 papers vit/vit.py ran MIT (permissive) · 608cb341e62af9a7 · report fixture: returned TransformerBlock · level recorded 2026-09-22
VisionTransformer in 53 papers vit/vit.py unverified MIT (permissive) · 18eba67fe6d3f33b · report
DominikBatic/EndoViT community (archive-listed) 1 sample, 0 ran · 1 unverified
VisionTransformer in 53 papers pretraining/mae/models_vit.py unverified no licence file found · pointer only · d3f0ee5f79046d1b · report
KiUngSong/Vision community (archive-listed) 7 samples, 7 ran (0 instrument-failed) · 0 unverified
EncoderBlock in 23 papers ViT/ViT_pytorch.py ran no licence file found · pointer only · 0341cd2b3c276bd3 · report fixture: returned EncoderBlock · level recorded 2026-09-22
FFN in 37 papers ViT/ViT_pytorch.py ran no licence file found · pointer only · 3e91eaf662a4bb21 · report fixture: returned FFN · level recorded 2026-09-22
Head in 14 papers ViT/ViT_pytorch.py ran no licence file found · pointer only · c694be0d1f02316c · report fixture: returned Head · level recorded 2026-09-22
MultiHeadAttention in 124 papers
census: 9 implementations from 7 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
ViT/ViT_pytorch.py ran fingerprinted no licence file found · pointer only · a78ee14b916decd1 · report fixture: signature x:Tensor/3/float, mask:NoneType/0/? · returned Tensor · level recorded 2026-09-24
PatchEmbedding in 25 papers ViT/ViT_pytorch.py ran no licence file found · pointer only · f4edb177e106f2f4 · report fixture: returned PatchEmbedding · level recorded 2026-09-22
ResidualAdd in 5 papers ViT/ViT_pytorch.py ran fingerprinted no licence file found · pointer only · 1da67eb7a61c1090 · report fixture: returned ResidualAdd · level recorded 2026-09-22
ViT in 10 papers ViT/ViT_pytorch.py ran no licence file found · pointer only · 94c914f501b4c9b2 · report fixture: returned ViT · level recorded 2026-09-22
Mayurji/Image-Classification-PyTorch community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
ViT.py ran GPL-3.0 (copyleft) · pointer only · 99a27bf8a6745bca · report fixture: returned Attention · level recorded 2026-09-22
FeedForward in 198 papers ViT.py ran fingerprinted GPL-3.0 (copyleft) · pointer only · df9f71cc75ae43fd · report fixture: returned FeedForward · level recorded 2026-09-22
PreNorm in 34 papers ViT.py ran GPL-3.0 (copyleft) · pointer only · 72339629e5f6be32 · report fixture: returned PreNorm · level recorded 2026-09-22
Transformers ViT.py ran GPL-3.0 (copyleft) · pointer only · f3e1dd83e789378c · report fixture: returned Transformers · level recorded 2026-09-22
ViT in 10 papers ViT.py ran GPL-3.0 (copyleft) · pointer only · 9c5bd92a34ef2ce0 · report fixture: returned ViT · level recorded 2026-09-22
SHI-Labs/Compact-Transformers community (archive-listed) 7 samples, 7 ran (1 instrument-failed) · 0 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
src/vit.py ran Apache-2.0 (permissive) · fb209281f7dc7ae4 · report fixture: returned Attention · level recorded 2026-09-22
DropPath in 75 papers
census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket
src/vit.py ran fingerprinted Apache-2.0 (permissive) · e96ac00ca379ee0e · report fixture: returned DropPath · level recorded 2026-09-22
Tokenizer in 16 papers src/vit.py ran fingerprinted Apache-2.0 (permissive) · 89f043dddf4da04c · report fixture: returned Tokenizer · level recorded 2026-09-22
TransformerClassifier src/vit.py ran Apache-2.0 (permissive) · 1a12cd3f4f72dc4c · report fixture: returned TransformerClassifier · level recorded 2026-09-22
TransformerEncoderLayer in 90 papers src/vit.py ran Apache-2.0 (permissive) · 2f168ea21eac6721 · report fixture: returned TransformerEncoderLayer · level recorded 2026-09-22
ViTLite src/vit.py ran Apache-2.0 (permissive) · eab482a168de4ac8 · report fixture: returned ViTLite · level recorded 2026-09-22
drop_path in 325 papers
census: 27 implementations from 61 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 2, kind float, dtype float32
src/vit.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · 6bb7492655ecbda4 · report fixture: signature x:Tensor/2/float, drop_prob:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22
SupreethRao99/VisionTransformer community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
FeedForward in 198 papers PyTorch/ViTModel.py ran · metamorphic tier: invariant MIT (permissive) · 4670212914e5cb73 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
ViT in 10 papers PyTorch/ViTModel.py ran MIT (permissive) · ddbba52e3e0c3fde · report fixture: signature img:Tensor/4/float, mask:NoneType/0/? · returned Tensor · level recorded 2026-09-24
Transformer in 173 papers PyTorch/ViTModel.py unverified MIT (permissive) · 79efe5cfa7a44c52 · report
Thanusan19/Vision_Transformer community (archive-listed) 11 samples, 8 ran (0 instrument-failed) · 3 unverified
argparser in 5 papers vit_jax/flags.py ran Apache-2.0 (permissive) · 394a62fbbb1cef3a · report fixture: signature known_models:dict/0/?, known_datasets:dict/0/? · returned ArgumentParser · level recorded 2026-09-24
checkExistanceAndEmptiness vit_jax/ViT_python_generator.py ran Apache-2.0 (permissive) · 817cf71a50e1ad40 · report fixture: signature output_file_path:str/0/str, doOverwrite:bool/0/bool · returned tuple · level recorded 2026-09-24
create_learning_rate_schedule vit_jax/hyper.py ran Apache-2.0 (permissive) · e30cad5784f49849 · report fixture: signature total_steps:int/0/int, base:float/0/float, decay_type:str/0/str, warmup_steps:int/0/int, linear_end:float/0/float · returned function · level recorded 2026-09-24
load in 392 papers vit_jax/checkpoint.py ran Apache-2.0 (permissive) · 0f21e0a5d632f6bf · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-24
lr_prefetch_iter vit_jax/hyper.py ran Apache-2.0 (permissive) · 7724f5f5baf1a30b · report fixture: signature lr_fn:callable/0/?, first_step:int/0/int, total_steps:int/0/int, prefetch_to_device:int/0/int, devices:NoneType/0/? · returned generator · level recorded 2026-09-24
prefetch vit_jax/input_pipeline.py ran Apache-2.0 (permissive) · 77d0de584a749653 · report fixture: signature dataset:SimpleDataset/0/?, n_prefetch:int/0/int · returned generator · level recorded 2026-09-24
recover_tree vit_jax/checkpoint.py ran Apache-2.0 (permissive) · 687547f1152f783b · report fixture: signature keys:list/1/str, values:list/1/Tensor · returned dict · level recorded 2026-09-24
setup_logger in 122 papers vit_jax/logging_ViT.py ran Apache-2.0 (permissive) · 2b62b00fb766df7b · report fixture: signature log_dir:str/0/str · returned Logger · level recorded 2026-09-24
accumulate_gradient vit_jax/hyper.py unverified Apache-2.0 (permissive) · 63b5f9a971e0dd3f · report
tree_flatten_with_names vit_jax/checkpoint.py unverified Apache-2.0 (permissive) · 3c0cd228402fe995 · report
weight_standardize vit_jax/models_resnet.py unverified Apache-2.0 (permissive) · 32d6b90336c93851 · report
TheTensorDude/vision_transformer_tf community (archive-listed) 8 samples, 5 ran (1 instrument-failed) · 3 unverified
ClassToken vit.py ran MIT (permissive) · 5283ae7455001543 · report fixture: returned ClassToken · level recorded 2026-09-22
Multihead_attention vit.py ran MIT (permissive) · 4ea751912efdeefd · report fixture: returned Multihead_attention · level recorded 2026-09-22
PatchEmbeddings in 5 papers vit.py ran MIT (permissive) · f649c17f27f54d0f · report fixture: returned PatchEmbeddings · level recorded 2026-09-22
load_config in 389 papers vit.py ran · our draft was wrong MIT (permissive) · 88cc4322193ded60 · report fixture: signature CONFIG_FILEPATH:str/0/str · returned dict · level recorded 2026-09-22
viTPositionalEmbedding vit.py ran MIT (permissive) · d92c10a3eb92b4d6 · report fixture: returned viTPositionalEmbedding · level recorded 2026-09-22
PointWiseFeedForwardNetwork vit.py unverified MIT (permissive) · c1361ce8574f90b4 · report
TransformerEncoder in 96 papers vit.py unverified MIT (permissive) · 719d09d203720f94 · report
viT vit.py unverified MIT (permissive) · 733ebfa8b2c9484b · report
UdbhavPrasad072300/Transformer-Implementation-and-Language-Translation community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
MultiHeadAttention in 124 papers
census: 9 implementations from 7 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
transformer_package/models/transformer.py ran · metamorphic tier: deterministic MIT (permissive) · 61787a7f1ca16779 · report fixture: returned MultiHeadAttention · level recorded 2026-09-22
VisionEncoder transformer_package/models/transformer.py ran · metamorphic tier: deterministic MIT (permissive) · bacfe561400c3879 · report fixture: returned VisionEncoder · level recorded 2026-09-22
ViT in 10 papers transformer_package/models/transformer.py unverified MIT (permissive) · fdf82b035ef6efc5 · report
Ugenteraan/Masked-AutoEncoder-PyTorch community (archive-listed) 7 samples, 6 ran (0 instrument-failed) · 1 unverified
FeedForwardBlock in 7 papers models/mae.py ran licence not identified · pointer only · 73a3a01717367dce · report fixture: signature input:Tensor/2/float · returned Tensor · level recorded 2026-09-24
MultiHeadAttention in 124 papers
census: 9 implementations from 7 papers, 9 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 2 of 3, arg 1: rank 3, kind float, dtype float32
models/mae.py ran · metamorphic tier: invariant licence not identified · pointer only · f6a1ed2d7f5be2dc · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
models/mae.py ran fingerprinted licence not identified · pointer only · 013fd37dfe095c3b · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
RandomMasking models/mae.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 3e123bc95a64ab4e · report fixture: signature x:Tensor/3/float · returned tuple · level recorded 2026-09-22
TransformerBlock in 73 papers models/mae.py ran · metamorphic tier: invariant licence not identified · pointer only · ca9596fc7f3f63a7 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
TransformerNetwork models/mae.py ran · metamorphic tier: invariant licence not identified · pointer only · 81b886e4fe869e9d · report fixture: signature input:Tensor/3/float · returned Tensor · level recorded 2026-09-22
MaskedAutoEncoder models/mae.py unverified licence not identified · pointer only · 74773d441dc10797 · report
Ugenteraan/Vanilla-ViT community (archive-listed) 9 samples, 6 ran (0 instrument-failed) · 3 unverified
FeedForwardEncoderBlock ViT/ViT.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 26b6ab7027777b32 · report fixture: signature input:Tensor/2/float · returned Tensor · level recorded 2026-09-22
MLPHead in 5 papers ViT/ViT.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · b337d893396aff7a · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
MultiHeadAttentionEinops ViT/ViT.py ran · metamorphic tier: invariant MIT (permissive) · dc3582c51e2fe52f · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
PatchEmbedding in 25 papers ViT/ViT.py ran MIT (permissive) · 054df1e2f70d626c · report fixture: signature batched_tensor_images:Tensor/4/float · returned Tensor · level recorded 2026-09-24
PositionalEncoder in 10 papers ViT/ViT.py ran · metamorphic tier: well formed MIT (permissive) · 781fed83feefbb41 · report fixture: returned Tensor · level recorded 2026-09-22
TransformerEncoderBlock in 9 papers ViT/ViT.py ran · metamorphic tier: invariant MIT (permissive) · 079c8ff8067ac323 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
ImagePatchMLP ViT/ViT.py unverified MIT (permissive) · cdbb6cc93f4b0ccb · report
TransformerEncoderNetwork ViT/ViT.py unverified MIT (permissive) · 599a34196909b353 · report
VisionTransformer in 53 papers ViT/ViT.py unverified MIT (permissive) · 953f99d43181a4e6 · report
YousefGamal220/Vision-Transformers community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
AttentionModel in 8 papers vision_transformer.py ran · metamorphic tier: deterministic no licence file found · pointer only · b527c73fd851cfee · report fixture: returned AttentionModel · level recorded 2026-09-22
BuildingBlock vision_transformer.py ran · metamorphic tier: deterministic no licence file found · pointer only · 126556b716f982c1 · report fixture: returned BuildingBlock · level recorded 2026-09-22
MLP in 375 papers vision_transformer.py ran · metamorphic tier: deterministic no licence file found · pointer only · fa3109866a421409 · report fixture: returned MLP · level recorded 2026-09-22
PatchEmbedding in 25 papers vision_transformer.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 69703cf0b78f4fcd · report fixture: returned PatchEmbedding · level recorded 2026-09-22
VisionTransformer in 53 papers vision_transformer.py ran · metamorphic tier: deterministic no licence file found · pointer only · b186094acc970ace · report fixture: returned VisionTransformer · level recorded 2026-09-22
asarigun/TransGAN community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
models.py ran MIT (permissive) · f817c1f38785cb41 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
Encoder_Block models.py ran MIT (permissive) · a5c892087ae3cab9 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
MLP in 375 papers models.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 8b9f46a6d61b24f2 · report fixture: returned MLP · level recorded 2026-09-22
TransformerEncoder in 96 papers models.py ran · metamorphic tier: deterministic MIT (permissive) · 0e36b2dfec0a4cc5 · report fixture: returned TransformerEncoder · level recorded 2026-09-22
asyml/vision-transformer-pytorch community (archive-listed) 7 samples, 7 ran (0 instrument-failed) · 0 unverified
Encoder in 278 papers src/model.py ran Apache-2.0 (permissive) · 87a7da8255824960 · report fixture: returned Encoder · level recorded 2026-09-22
EncoderBlock in 23 papers src/model.py ran Apache-2.0 (permissive) · be6b45c4b5087cd0 · report fixture: returned EncoderBlock · level recorded 2026-09-22
LinearGeneral src/model.py ran Apache-2.0 (permissive) · 9129885a793dea80 · report fixture: returned LinearGeneral · level recorded 2026-09-22
MlpBlock in 9 papers src/model.py ran Apache-2.0 (permissive) · 211b9690042c26c5 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
PositionEmbs src/model.py ran Apache-2.0 (permissive) · ec412e2656b1565a · report fixture: returned PositionEmbs · level recorded 2026-09-22
SelfAttention in 66 papers src/model.py ran Apache-2.0 (permissive) · 3dffc591a6481874 · report fixture: returned SelfAttention · level recorded 2026-09-22
VisionTransformer in 53 papers src/model.py ran Apache-2.0 (permissive) · 3b44acd70cadcf44 · report fixture: returned VisionTransformer · level recorded 2026-09-22
bshantam97/Attention_Based_Networks community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
EncoderBlock in 23 papers vision_transformer.py ran · metamorphic tier: invariant no licence file found · pointer only · 32185c117e4e5926 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
MLP in 375 papers vision_transformer.py ran · metamorphic tier: invariant no licence file found · pointer only · 921025fed7e22466 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
MultiHeadAttention in 124 papers
census: 9 implementations from 7 papers, 9 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 2 of 3, arg 1: rank 3, kind float, dtype float32
vision_transformer.py ran · metamorphic tier: invariant no licence file found · pointer only · 6082f915e0ac604c · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
vision_transformer.py ran · metamorphic tier: invariant no licence file found · pointer only · 81eeb98072149f16 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
VisionTransformer in 53 papers vision_transformer.py unverified no licence file found · pointer only · fca973fc1fa56318 · report
conceptofmind/ViT-haiku community (archive-listed) 6 samples, 0 ran · 6 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
vit.py unverified MIT (permissive) · 67e042f60cb0eb8a · report
FeedForward in 198 papers vit.py unverified MIT (permissive) · 1dbcf429d75f0464 · report
IdentityLayer in 7 papers vit.py unverified MIT (permissive) · 8006254bdcb47e21 · report
PreNorm in 34 papers vit.py unverified MIT (permissive) · 53414144a714bf36 · report
Transformer in 173 papers vit.py unverified MIT (permissive) · dfeaf3afe023f28b · report
VitBase vit.py unverified MIT (permissive) · 3290351ae5e72fe6 · report
dispink/xpt community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
MaskedAutoencoderViT in 14 papers src/models/mae_vit.py ran · metamorphic tier: deterministic MIT (permissive) · 3fc7aef63e94d614 · report fixture: returned MaskedAutoencoderViT · level recorded 2026-09-22
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
src/models/mae_vit.py ran · metamorphic tier: deterministic MIT (permissive) · 5cca4ba1d44c607a · report fixture: returned PatchEmbed · level recorded 2026-09-22
get_1d_sincos_pos_embed in 16 papers src/models/mae_vit.py ran · honoured contract fingerprinted MIT (permissive) · eab6c08e3fce2956 · report fixture: signature embed_dim:int/0/int, num_patches:int/0/int, cls_token:bool/0/bool · returned ndarray · level recorded 2026-09-22
drumpt/ViT community (archive-listed) 7 samples, 7 ran (0 instrument-failed) · 0 unverified
ClassificationHead in 12 papers model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 2bfce24bf8846119 · report fixture: returned ClassificationHead · level recorded 2026-09-22
FeedForwardBlock in 7 papers model.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 3e51ff20def421bb · report fixture: returned FeedForwardBlock · level recorded 2026-09-22
MultiHeadAttention in 124 papers
census: 9 implementations from 7 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 285f0cc9150c1c47 · report fixture: returned MultiHeadAttention · level recorded 2026-09-22
PatchEmbedding in 25 papers model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 8187c4e8de75ff9f · report fixture: returned PatchEmbedding · level recorded 2026-09-22
TransformerEncoder in 96 papers model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 0cdaa48d9c79b905 · report fixture: returned TransformerEncoder · level recorded 2026-09-22
TransformerEncoderBlock in 9 papers model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 52df59f709cbd077 · report fixture: returned TransformerEncoderBlock · level recorded 2026-09-22
ViT in 10 papers model.py ran · metamorphic tier: deterministic no licence file found · pointer only · b225bcdab9997d81 · report fixture: returned ViT · level recorded 2026-09-22
explainingai-code/VIT-Pytorch community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
model/transformer.py ran · metamorphic tier: deterministic no licence file found · pointer only · 998014b6f71af139 · report fixture: returned Attention · level recorded 2026-09-22
PatchEmbedding in 25 papers model/transformer.py ran no licence file found · pointer only · 08a197f4ac5cab24 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
TransformerLayer in 34 papers model/transformer.py ran · metamorphic tier: deterministic no licence file found · pointer only · 39a0e7e04a621bfd · report fixture: returned TransformerLayer · level recorded 2026-09-22
VIT model/transformer.py ran · metamorphic tier: deterministic no licence file found · pointer only · a1345ed95588ae6b · report fixture: returned VIT · level recorded 2026-09-22
faustomorales/vit-keras community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
interpret_image_size vit_keras/vit.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · a6d5b89d9b7d3d00 · report fixture: signature image_size_arg:int/0/int · returned tuple · level recorded 2026-09-22
build_model in 469 papers vit_keras/vit.py unverified Apache-2.0 (permissive) · b1da23dfc225c953 · report
gnoses/ViT_examples community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
Transformer in 173 papers vit_pytorch.py ran · metamorphic tier: deterministic no licence file found · pointer only · edeb719af70be8d6 · report fixture: returned Transformer · level recorded 2026-09-22
ViT in 10 papers vit_pytorch.py ran · metamorphic tier: deterministic no licence file found · pointer only · f56a3adb976220d9 · report fixture: returned ViT · level recorded 2026-09-22
jacobgil/vit-explain community (archive-listed) 1 sample, 0 ran · 1 unverified
grad_rollout vit_grad_rollout.py unverified MIT (permissive) · cb8cb0f36e74db72 · report
jeonsworld/ViT-pytorch community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
np2th in 31 papers
census: 2 implementations from 9 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
models/modeling.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 7d8eaf5537f699e4 · report fixture: signature weights:ndarray/4/float, conv:bool/0/bool · returned Tensor · level recorded, date not recorded
swish in 258 papers
census: 14 implementations from 37 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
models/modeling.py ran · our draft was wrong fingerprinted MIT (permissive) · 0f786c407fb1ee4c · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
jiangtaoxie/So-ViT community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ViTBlock sot_src/model/vitBlock.py ran · metamorphic tier: deterministic no licence file found · pointer only · 7ee0012316814be5 · report fixture: returned ViTBlock · level recorded 2026-09-22
junyongyou/triq community (archive-listed) 7 samples, 2 ran (0 instrument-failed) · 5 unverified
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
src/vit_iqa/ViT_pytorch/models/modeling.py ran MIT (permissive) · 4af23178d3041345 · report fixture: returned Block · level recorded 2026-09-22
ResNetV2 in 5 papers src/vit_iqa/ViT_pytorch/models/modeling.py ran MIT (permissive) · f06334f57a8bf625 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Embeddings in 15 papers src/vit_iqa/ViT_pytorch/models/modeling.py unverified MIT (permissive) · c307b98f19985795 · report
Encoder in 278 papers src/vit_iqa/ViT_pytorch/models/modeling.py unverified MIT (permissive) · 20d5453d1066485a · report
PreActBottleneck in 6 papers src/vit_iqa/ViT_pytorch/models/modeling.py unverified MIT (permissive) · fbc710326c33118c · report
Transformer in 173 papers src/vit_iqa/ViT_pytorch/models/modeling.py unverified MIT (permissive) · d7c865c36a140066 · report
VisionTransformer in 53 papers src/vit_iqa/ViT_pytorch/models/modeling.py unverified MIT (permissive) · 110bd6632560d038 · report
konstantinos-p/image_classification_SOTA community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
MultiHeadedAttention in 38 papers testing/models/ViTransformer.py ran · metamorphic tier: deterministic no licence file found · pointer only · a166a1e285a378b2 · report fixture: returned MultiHeadedAttention · level recorded 2026-09-22
attention in 144 papers
census: 11 implementations from 10 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
testing/models/ViTransformer.py ran · our draft was wrong no licence file found · pointer only · 98bf46cb18536d19 · report fixture: signature query:Tensor/3/float, key:Tensor/3/float, value:Tensor/3/float, dropout:callable/0/? · returned tuple · level recorded 2026-09-22
clones in 92 papers testing/models/ViTransformer.py ran · our draft was wrong no licence file found · pointer only · 22237c8ec0880bfd · report fixture: signature module:callable/0/?, N:int/0/int · returned ModuleList · level recorded 2026-09-22
ludics/ViT-Retri community (archive-listed) 5 samples, 2 ran (0 instrument-failed) · 3 unverified
ContrastiveLoss in 16 papers vit_retri/models/modeling.py ran MIT (permissive) · 33a1d26b73f77059 · report fixture: returned ContrastiveLoss · level recorded 2026-09-22
ResNetV2 in 5 papers vit_retri/models/modeling.py ran MIT (permissive) · feea3ff66b43bfbf · report fixture: returned ResNetV2 · level recorded 2026-09-22
Embeddings in 15 papers vit_retri/models/modeling.py unverified MIT (permissive) · a79858ea7aff31a2 · report
Transformer in 173 papers vit_retri/models/modeling.py unverified MIT (permissive) · 25f6b6dd838b1055 · report
VisionTransformer in 53 papers vit_retri/models/modeling.py unverified MIT (permissive) · f50ac01b2aea5cee · report
lukas-blecher/LaTeX-OCR community (archive-listed) 11 samples, 6 ran (0 instrument-failed) · 5 unverified
check_brackets pix2tex/dataset/extract_latex.py ran fingerprinted MIT (permissive) · 6f3ade550a54fdf7 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-24
clean_matches pix2tex/dataset/extract_latex.py ran MIT (permissive) · 411a7fa3f907e91e · report fixture: signature matches:list/1/str, min_chars:int/0/int · returned list · level recorded 2026-09-24
encode_image in 131 papers pix2tex/api/streamlit.py ran MIT (permissive) · b2cb3afa961b359c · report fixture: signature file:str/0/str · returned BytesIO · level recorded 2026-09-24
get_all_arxiv_ids pix2tex/dataset/arxiv.py ran fingerprinted MIT (permissive) · 26304c127c481571 · report fixture: signature text:str/0/str · returned list · level recorded 2026-09-24
get_encoder in 45 papers pix2tex/models/hybrid.py ran MIT (permissive) · cbf60284ff51ed55 · report fixture: signature args:Args/0/? · returned CustomVisionTransformer · level recorded 2026-09-24
setup_desktop pix2tex/setup_desktop.py ran MIT (permissive) · 83e1fc7d7198b1fd · report fixture: signature gui_file:str/0/str, icon_file:str/0/str · returned int · level recorded 2026-09-24
download in 53 papers pix2tex/dataset/arxiv.py unverified MIT (permissive) · 0f3b788b4413877f · report
get_model in 368 papers pix2tex/models/utils.py unverified MIT (permissive) · 55f415e814429e9b · report
process_args in 17 papers pix2tex/dataset/preprocessing/generate_latex_vocab.py unverified MIT (permissive) · bc8041a0341aa444 · report
read_tex_files pix2tex/dataset/arxiv.py unverified MIT (permissive) · 7dfceb44b06a1fdc · report
remove_labels pix2tex/dataset/extract_latex.py unverified MIT (permissive) · 5881a8cf3bdd5ce9 · report
mahmoodlab/hipt community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
HIPT_4K/vision_transformer.py ran · metamorphic tier: deterministic licence not identified · pointer only · 3806102629027da3 · report fixture: returned Attention · level recorded 2026-09-22
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
HIPT_4K/vision_transformer.py ran · metamorphic tier: deterministic licence not identified · pointer only · 65e124fb59929e7b · report fixture: returned Block · level recorded 2026-09-22
DropPath in 75 papers
census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket
HIPT_4K/vision_transformer.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · ad5f80b54573c0e0 · report fixture: returned DropPath · level recorded 2026-09-22
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
HIPT_4K/vision_transformer.py ran · metamorphic tier: deterministic licence not identified · pointer only · 9187f42531072c00 · report fixture: returned PatchEmbed · level recorded 2026-09-22
VisionTransformer in 53 papers HIPT_4K/vision_transformer.py unverified licence not identified · pointer only · 958ea05c3c1ae4ba · report
meowbutlerdev/ViT community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
vit.py ran fingerprinted no licence file found · pointer only · 03826c508404de86 · report fixture: signature x:Tensor/3/float, mask:NoneType/0/? · returned Tensor · level recorded 2026-09-24
FeedForward in 198 papers vit.py ran no licence file found · pointer only · 2b1fb378cc14dda7 · report fixture: returned FeedForward · level recorded 2026-09-22
Transformer in 173 papers vit.py ran no licence file found · pointer only · 9cefe5df7641351a · report fixture: returned Transformer · level recorded 2026-09-22
ViT in 10 papers vit.py ran no licence file found · pointer only · fe27fb10dc68506c · report fixture: returned ViT · level recorded 2026-09-22
modeeric/eegvit-tcnet community (archive-listed) 1 sample, 0 ran · 1 unverified
ViTBase models/ViTBase.py unverified no licence file found · pointer only · 8670aaace4332b94 · report
mtancak/PyTorch-ViT-Visual-Transformer community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
Encoder in 278 papers model.py ran no licence file found · pointer only · 5ab5e4d0ab686651 · report fixture: returned Encoder · level recorded 2026-09-22
MHA in 5 papers model.py ran no licence file found · pointer only · de3633db52c314c6 · report fixture: returned MHA · level recorded 2026-09-22
ViT in 10 papers model.py ran no licence file found · pointer only · c349e162dda4ee2b · report fixture: returned ViT · level recorded 2026-09-22
mujiyantosvc/Facial-Expression-Recognition-FER-for-Mental-Health-Detection- community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
CustomSwinTransformer utilities/train_model.py ran MIT (permissive) · ff3b3cb2fa5e8545 · report fixture: returned CustomSwinTransformer · level recorded 2026-09-22
nachiket273/VisTrans community (archive-listed) 10 samples, 5 ran (1 instrument-failed) · 5 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
vistrans/models/vit.py ran MIT (permissive) · 5f7f49ed28389849 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
Encoder in 278 papers vistrans/models/vit.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · f8b85038ed9400ec · report fixture: returned Encoder · level recorded 2026-09-22
EncoderLayer in 73 papers vistrans/models/vit.py ran · metamorphic tier: deterministic MIT (permissive) · 8720a0cb1f23c55c · report fixture: returned EncoderLayer · level recorded 2026-09-22
MLP in 375 papers vistrans/models/vit.py ran · metamorphic tier: deterministic MIT (permissive) · 05a6c50ee835b1ce · report fixture: returned MLP · level recorded 2026-09-22
adjust_conv_weights vistrans/models/vit.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 1f5b08213e7cf89f · report fixture: signature weights:Tensor/4/float, in_ch:int/0/int · returned Tensor · level recorded 2026-09-22
ViT in 10 papers vistrans/models/vit.py unverified MIT (permissive) · 051aa80b5054376c · report
VisionTransformer in 53 papers vistrans/models/vit.py unverified MIT (permissive) · 2d96b3b67dc31418 · report
get_pretrained_weights vistrans/models/vit.py unverified MIT (permissive) · 56c0c8e56a181423 · report
ntuple in 6 papers vistrans/models/vit.py unverified MIT (permissive) · 7b701d0ab4c91bf0 · report
nachiket273/Vision_transformer_pytorch community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
vit.py ran no licence file found · pointer only · 4e9b033c45eda05d · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
vit.py ran · metamorphic tier: deterministic no licence file found · pointer only · 908f6f29e84e7834 · report fixture: returned Block · level recorded 2026-09-22
ImgPatches vit.py ran · metamorphic tier: deterministic no licence file found · pointer only · d66470a54f20a7a7 · report fixture: returned ImgPatches · level recorded 2026-09-22
MLP in 375 papers vit.py ran · metamorphic tier: deterministic no licence file found · pointer only · 501263e9688cd1fd · report fixture: returned MLP · level recorded 2026-09-22
Transformer in 173 papers vit.py ran · metamorphic tier: deterministic no licence file found · pointer only · fa4b1e78be3a1623 · report fixture: returned Transformer · level recorded 2026-09-22
ViT in 10 papers vit.py ran · metamorphic tier: deterministic no licence file found · pointer only · aeb451a2ca6a384e · report fixture: returned ViT · level recorded 2026-09-22
nateraw/lightning-vision-transformer community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
vit.py ran · metamorphic tier: deterministic MIT (permissive) · 82e3e86f7ef279d6 · report fixture: returned Block · level recorded 2026-09-22
MultiheadAttention in 44 papers vit.py ran · metamorphic tier: deterministic MIT (permissive) · 28d07cea36220258 · report fixture: returned MultiheadAttention · level recorded 2026-09-22
Transformer in 173 papers vit.py ran · metamorphic tier: deterministic MIT (permissive) · ddf39179956e840a · report fixture: returned Transformer · level recorded 2026-09-22
VisionTransformer in 53 papers vit.py ran · metamorphic tier: deterministic MIT (permissive) · 78aca8814a1f8d16 · report fixture: returned VisionTransformer · level recorded 2026-09-22
naver-ai/pflayer community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
vit_pf.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 111794c24e7fff19 · report fixture: returned Block · level recorded 2026-09-22
EffLayer vit_pf.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 6809cf195b936e15 · report fixture: returned EffLayer · level recorded 2026-09-22
EffTransformer vit_pf.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 2522fc9fcfe416c4 · report fixture: returned EffTransformer · level recorded 2026-09-22
nima1999nikkhah/ViT-Hybrid community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
MultiHeadSelfAttention in 17 papers ViT-Hybrid.py ran no licence file found · pointer only · 15459d47883ae1eb · report fixture: returned MultiHeadSelfAttention · level recorded 2026-09-22
TransformerBlock in 73 papers ViT-Hybrid.py ran no licence file found · pointer only · 472347df45454b8a · report fixture: returned TransformerBlock · level recorded 2026-09-22
ViT in 10 papers ViT-Hybrid.py ran no licence file found · pointer only · 138334827a9f4dc3 · report fixture: returned ViT · level recorded 2026-09-22
qiaopTDUN/mae-repo community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ViT in 10 papers vit_pytorch/vit.py ran fingerprinted no licence file found · pointer only · defe150a2927af39 · report fixture: returned ViT · level recorded 2026-09-22
quanmario0311/ViT_PyTorch community (archive-listed) 2 samples, 0 ran · 2 unverified
Transformer in 173 papers model.py unverified MIT (permissive) · de8c71de5b24650f · report
ViT in 10 papers model.py unverified MIT (permissive) · 45874b50ee4eee3a · report
rayanramoul/Visual-Transformer-PyTorch community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
MultiHeadSelfAttention in 17 papers src/models.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 37fc76128226736c · report fixture: returned MultiHeadSelfAttention · level recorded 2026-09-22
ViT in 10 papers src/models.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 1231e62c1adf0b34 · report fixture: returned ViT · level recorded 2026-09-22
VitBlock src/models.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 3b0ee2b8c75d0cb5 · report fixture: returned VitBlock · level recorded 2026-09-22
calculate_positional_embeddings src/models.py ran · honoured contract Apache-2.0 (permissive) · 9c35c7ced350b3ae · report fixture: signature sequence_length:int/0/int, d:int/0/int · returned Tensor · level recorded 2026-09-22
transform_image_to_patch src/models.py unverified Apache-2.0 (permissive) · a96d5de1e576e908 · report
s-chh/pytorch-scratch-vision-transformer-vit community (archive-listed) 6 samples, 4 ran (0 instrument-failed) · 2 unverified
Classifier in 72 papers model.py ran MIT (permissive) · 97bb28e127fe8a6e · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
EmbedLayer model.py ran · metamorphic tier: invariant MIT (permissive) · 236da9f27dd5c92f · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Encoder in 278 papers model.py ran MIT (permissive) · 92f27ff91aeb4722 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
SelfAttention in 66 papers model.py ran · metamorphic tier: invariant MIT (permissive) · af6edd8062f762fa · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
VisionTransformer in 53 papers model.py unverified MIT (permissive) · c5610b768e912553 · report
vit_init_weights model.py unverified MIT (permissive) · 52a6621d75fb86eb · report
sangHa0411/VIT community (archive-listed) 7 samples, 6 ran (0 instrument-failed) · 1 unverified
Encoder in 278 papers model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 663995617b3eb222 · report fixture: returned Encoder · level recorded 2026-09-22
EncoderBlock in 23 papers model.py ran · metamorphic tier: deterministic no licence file found · pointer only · ce7cae4240dc4421 · report fixture: returned EncoderBlock · level recorded 2026-09-22
FeedForward in 198 papers model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 1444e79df77330f0 · report fixture: returned FeedForward · level recorded 2026-09-22
MultiHeadAttention in 124 papers
census: 9 implementations from 7 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
model.py ran no licence file found · pointer only · 816585d560db3f1d · report fixture: signature q_in:Tensor/3/float, k_in:Tensor/3/float, v_in:Tensor/3/float, m_in:NoneType/0/? · returned Tensor · level recorded 2026-09-24
PatchFlatten model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 676c76852946dcf9 · report fixture: returned PatchFlatten · level recorded 2026-09-22
PositionEmbedding in 7 papers model.py ran fingerprinted no licence file found · pointer only · a67eb3bda2872789 · report fixture: signature f_tensor:Tensor/3/float · returned Tensor · level recorded 2026-09-24
VIT model.py unverified no licence file found · pointer only · 4b4411972674cc39 · report
skchen1993/TrangFG community (archive-listed) 8 samples, 5 ran (0 instrument-failed) · 3 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
models/modeling.py ran · metamorphic tier: deterministic MIT (permissive) · 4112d886f96a0258 · report fixture: signature hidden_states:Tensor/3/float · returned tuple · level recorded 2026-09-22
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
models/modeling.py ran MIT (permissive) · 8711444686518b7c · report fixture: signature x:Tensor/3/float · returned tuple · level recorded 2026-09-24
Embeddings in 15 papers models/modeling.py ran · metamorphic tier: invariant MIT (permissive) · 6cdae3f419a63138 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
LabelSmoothing models/modeling.py ran · metamorphic tier: invariant MIT (permissive) · ec35e0927e66ad2c · report fixture: signature x:Tensor/2/float, target:Tensor/1/int · returned Tensor · level recorded 2026-09-22
Part_Attention models/modeling.py ran MIT (permissive) · fa1aa6f6065a3378 · report fixture: signature x:list/1/Tensor · returned tuple · level recorded 2026-09-24
Encoder in 278 papers models/modeling.py unverified MIT (permissive) · 6647470e9f82eb74 · report
Transformer in 173 papers models/modeling.py unverified MIT (permissive) · 70fa7fd247c01f16 · report
VisionTransformer in 53 papers models/modeling.py unverified MIT (permissive) · 951da7c89ffaf2ef · report
smu-ivpl/DeepfakeDetection community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
VisionTransformer in 53 papers facebook_deit.py ran no licence file found · pointer only · cf2cdfee402d4881 · report fixture: returned VisionTransformer · level recorded 2026-09-22
staghado/vit.cpp community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ViTSTR extensions/vitstr.cpp/convert-pth-to-ggml.py ran · metamorphic tier: invariant MIT (permissive) · 0252f14dd76710b1 · report fixture: signature x:Tensor/4/float, seqlen:int/0/int · returned Tensor · level recorded 2026-09-22
stevenwalton/scs-cct community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
SCSAttention src/vit.py ran Apache-2.0 (permissive) · 8395067ef1060f36 · report fixture: returned SCSAttention · level recorded 2026-09-22
TransformerClassifier src/vit.py ran Apache-2.0 (permissive) · d95ac7e8dcad5a26 · report fixture: returned TransformerClassifier · level recorded 2026-09-22
TransformerEncoderLayer in 90 papers src/vit.py ran Apache-2.0 (permissive) · 211aaa8ef68bf255 · report fixture: returned TransformerEncoderLayer · level recorded 2026-09-22
ViTLite src/vit.py ran Apache-2.0 (permissive) · d2c979f9c5c66be3 · report fixture: returned ViTLite · level recorded 2026-09-22
tahmid0007/VisionTransformer community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
ImageTransformer Google_ViT.py ran no licence file found · pointer only · 467a2adbf1bb7985 · report fixture: returned ImageTransformer · level recorded 2026-09-22
LayerNormalize Google_ViT.py ran no licence file found · pointer only · 23c4bb58f0b38bd6 · report fixture: returned LayerNormalize · level recorded 2026-09-22
MLP_Block in 5 papers Google_ViT.py ran no licence file found · pointer only · caa4f910273a4b2d · report fixture: returned MLP_Block · level recorded 2026-09-22
Transformer in 173 papers Google_ViT.py ran no licence file found · pointer only · 6c370b05b44059ce · report fixture: returned Transformer · level recorded 2026-09-22
timH6502/VisionTransformer-PyTorch community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
MultiHeadAttention in 124 papers
census: 9 implementations from 7 papers, 9 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 2 of 3, arg 1: rank 3, kind float, dtype float32
src/ViT.py ran · metamorphic tier: invariant no licence file found · pointer only · 6bad9911ea340c54 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
TransformerEncoder in 96 papers src/ViT.py ran no licence file found · pointer only · a1cfd3050af64173 · report fixture: returned TransformerEncoder · level recorded 2026-09-22
ViT in 10 papers src/ViT.py ran no licence file found · pointer only · e695bb4416d49d79 · report fixture: returned ViT · level recorded 2026-09-22
tintn/vision-transformer-from-scratch community (archive-listed) 10 samples, 7 ran (0 instrument-failed) · 3 unverified
AttentionHead vit.py ran · metamorphic tier: deterministic MIT (permissive) · b4bfa3287132b6de · report fixture: signature x:Tensor/3/float · returned tuple · level recorded 2026-09-22
Embeddings in 15 papers vit.py ran · metamorphic tier: invariant MIT (permissive) · fe1bfe65727fc610 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
FasterMultiHeadAttention vit.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 66910025be91b62c · report fixture: signature x:Tensor/3/float, output_attentions:bool/0/bool · returned tuple · level recorded 2026-09-22
MLP in 375 papers vit.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 638425272b57c6c3 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
MultiHeadAttention in 124 papers
census: 9 implementations from 7 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
vit.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 53dab365fc08769e · report fixture: signature x:Tensor/3/float, output_attentions:bool/0/bool · returned tuple · level recorded 2026-09-22
NewGELUActivation vit.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · bf9cef9e1ceb59b7 · report fixture: signature input:Tensor/2/float · returned Tensor · level recorded 2026-09-22
PatchEmbeddings in 5 papers vit.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · fc40a0952d8870be · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Encoder in 278 papers vit.py unverified MIT (permissive) · eb4e38c211f5872e · report
ViTForClassfication vit.py unverified MIT (permissive) · 80270c8e1af03db4 · report
ttt496/VisionTransformer community (archive-listed) 5 samples, 0 ran · 5 unverified
AddPositionEmbs vit_jax/models.py unverified Apache-2.0 (permissive) · e466973477cb197b · report
Encoder in 278 papers vit_jax/models.py unverified Apache-2.0 (permissive) · f3cfcd9a6f4b8dee · report
Encoder1DBlock vit_jax/models.py unverified Apache-2.0 (permissive) · 58d24d8e618153e9 · report
MlpBlock in 9 papers vit_jax/models.py unverified Apache-2.0 (permissive) · 655ad1b00df17771 · report
VisionTransformer in 53 papers vit_jax/models.py unverified Apache-2.0 (permissive) · 51d3b9873cfbdfba · report
wangguanan/light-reid community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
lightreid/models/backbones/transformers/vit_timm.py ran no licence file found · pointer only · f9eebdcbcec2008d · report fixture: returned Block · level recorded 2026-09-22
VisionTransformer in 53 papers lightreid/models/backbones/transformers/vit_timm.py ran no licence file found · pointer only · d1e7240963528e63 · report fixture: returned VisionTransformer · level recorded 2026-09-22
_init_vit_weights in 9 papers lightreid/models/backbones/transformers/vit_timm.py unverified no licence file found · pointer only · 26d4bd0ece4e237e · report
HzcIrving/DeepLearning_PlayGround community (archive-listed) 7 samples, 4 ran (1 instrument-failed) · 3 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
VIT/Model.py ran MIT (permissive) · e65111831b48a20f · report fixture: returned Attention · level recorded 2026-09-22
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
VIT/Model.py ran MIT (permissive) · 0c8c99ad8b44657f · report fixture: signature x:Tensor/3/float · returned tuple · level recorded 2026-09-24
ImageEmbeddings in 7 papers VIT/Model.py ran MIT (permissive) · d13a44be08217e01 · report fixture: returned ImageEmbeddings · level recorded 2026-09-22
np2th in 31 papers
census: 2 implementations from 9 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
VIT/Model.py ran; the contract check could not run (RAISES) MIT (permissive) · 749c76cd00ed3a80 · report fixture: signature weights:ndarray/4/float, conv:bool/0/bool · returned Tensor · level recorded 2026-09-22
Encoder in 278 papers VIT/Model.py unverified MIT (permissive) · 7eae7f481d7d3b63 · report
Transformer in 173 papers VIT/Model.py unverified MIT (permissive) · b9208ebd1f770032 · report
VITransModel VIT/Model.py unverified MIT (permissive) · d5a52a3389742f57 · report
OML-Team/open-metric-learning community (archive-listed) 12 samples, 9 ran (2 instrument-failed) · 3 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
oml/models/vit_dino/external_v2/vision_transformer.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 49d02e769ff703f2 · report fixture: returned Attention · level recorded 2026-09-22
BlockChunk oml/models/vit_dino/external_v2/vision_transformer.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 9af82963dffa88ab · report fixture: returned BlockChunk · level recorded 2026-09-22
DropPath in 75 papers
census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket
oml/models/vit_dino/external_v2/vision_transformer.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 1d3ee770ca7b30c9 · report fixture: returned DropPath · level recorded 2026-09-22
LayerScale in 15 papers oml/models/vit_dino/external_v2/vision_transformer.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · ab8cf50d6a117f90 · report fixture: returned LayerScale · level recorded 2026-09-22
Mlp in 102 papers oml/models/vit_dino/external_v2/vision_transformer.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 117f497351823aa8 · report fixture: returned Mlp · level recorded 2026-09-22
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
oml/models/vit_dino/external_v2/vision_transformer.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 2cc36e6c101abe2d · report fixture: returned PatchEmbed · level recorded 2026-09-22
drop_add_residual_stochastic_depth in 26 papers oml/models/vit_dino/external_v2/vision_transformer.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 6b47b72596f1a5c3 · report fixture: signature x:Tensor/3/float, residual_func:callable/0/?, sample_drop_ratio:float/0/float · returned Tensor · level recorded 2026-09-22
named_apply in 32 papers oml/models/vit_dino/external_v2/vision_transformer.py ran · our draft was wrong Apache-2.0 (permissive) · 3e92d5b816f50e2e · report fixture: signature fn:callable/0/?, module:callable/0/?, name:str/0/str, depth_first:bool/0/bool, include_root:bool/0/bool · returned SimpleModel · level recorded 2026-09-22
use_fused_attn oml/models/vit_dino/external_v2/vision_transformer.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 9c44bb34ebc00ba5 · report fixture: returned bool · level recorded 2026-09-22
DinoVisionTransformer oml/models/vit_dino/external_v2/vision_transformer.py unverified Apache-2.0 (permissive) · fce8f3e4b02ccba2 · report
init_weights_vit_timm in 6 papers oml/models/vit_dino/external_v2/vision_transformer.py unverified Apache-2.0 (permissive) · 9c07111952a8132e · report
The-AI-Summer/self_attention community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
expand_to_batch self_attention_cv/vit/vit.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 4429c4f5d33938e5 · report fixture: signature tensor:Tensor/3/float, desired_size:int/0/int · returned Tensor · level recorded 2026-09-22
ViT in 10 papers self_attention_cv/vit/vit.py unverified MIT (permissive) · 0cc37cf06f3729da · report
ZhouDaShan123/vit community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
extract_embeddings in 9 papers src/npz_converter.py ran Apache-2.0 (permissive) · 0ed2369c3f959ad2 · report fixture: signature ref_ws:dict/0/? · returned dict · level recorded 2026-09-24
extract_encoder_weights src/npz_converter.py ran Apache-2.0 (permissive) · cb55b5ce20677f49 · report fixture: signature ref_ws:dict/0/?, index:int/0/int · returned dict · level recorded 2026-09-24
linear_warmup_lr in 10 papers src/lr.py ran fingerprinted Apache-2.0 (permissive) · 8a0d4718d0f91120 · report fixture: signature current_step:int/0/int, warmup_steps:int/0/int, base_lr:float/0/float, init_lr:float/0/float · returned float · level recorded 2026-09-24
lr_steps_imagenet src/lr.py ran Apache-2.0 (permissive) · 8df05ae5b2f2b14e · report fixture: signature _cfg:Config/0/?, steps_per_epoch:int/0/int · returned ndarray · level recorded 2026-09-24
warmup_cosine_annealing_lr in 5 papers src/lr.py ran Apache-2.0 (permissive) · 8213653dae4eae8e · report fixture: signature lr5:float/0/float, steps_per_epoch:int/0/int, warmup_epochs:int/0/int, max_epoch:int/0/int, T_max:int/0/int, eta_min:float/0/float · returned ndarray · level recorded 2026-09-24
affjljoo3581/deit3-jax community (archive-listed) 7 samples, 3 ran (0 instrument-failed) · 4 unverified
ViTBase src/modeling.py ran Apache-2.0 (permissive) · ce9eaebe2bebbb8f · report fixture: returned ViTBase · level recorded 2026-09-22
ViTLayer src/modeling.py ran Apache-2.0 (permissive) · de141233145303ec · report fixture: returned ViTLayer · level recorded 2026-09-22
fixed_sincos2d_embeddings src/modeling.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 7bda71241cea2b85 · report fixture: signature ncols:int/0/int, nrows:int/0/int, dim:int/0/int · returned ArrayImpl · level recorded 2026-09-22
FeedForward in 198 papers src/modeling.py unverified Apache-2.0 (permissive) · 5d143bd9bacd190b · report
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
src/modeling.py unverified Apache-2.0 (permissive) · 9d57e2c2d9f1a7b5 · report
ViT in 10 papers src/modeling.py unverified Apache-2.0 (permissive) · 375467cdc03cf22c · report
ahmed-alllam/Equinox community (archive-listed) 8 samples, 4 ran (0 instrument-failed) · 4 unverified
doc_repr equinox/_doc_utils.py ran Apache-2.0 (permissive) · 7f3552cae27a748f · report fixture: signature obj:callable/0/?, string:str/0/str · returned function · level recorded 2026-09-24
hashable_combine equinox/_compile_utils.py ran Apache-2.0 (permissive) · e7b19a731b5d767d · report fixture: signature dynamic_leaves:list/1/Tensor, static:tuple/1/list · returned dict · level recorded 2026-09-24
hashable_filter equinox/_compile_utils.py ran Apache-2.0 (permissive) · cbca56882036eaeb · report fixture: signature pytree:dict/0/?, filter_fn:callable/0/? · returned tuple · level recorded 2026-09-24
hashable_partition equinox/_compile_utils.py ran Apache-2.0 (permissive) · c240c44d85f23a3b · report fixture: signature pytree:dict/0/?, filter_fn:callable/0/? · returned tuple · level recorded 2026-09-24
cached_filter_eval_shape equinox/_eval_shape.py unverified Apache-2.0 (permissive) · 227e26e79d89db80 · report
filter_eval_shape equinox/_eval_shape.py unverified Apache-2.0 (permissive) · 02d8f99bfd820b74 · report
filter_jvp equinox/_ad.py unverified Apache-2.0 (permissive) · 41f1158bca07e4af · report
filter_pure_callback equinox/_callback.py unverified Apache-2.0 (permissive) · 7c01a0e93d4a2886 · report
arkel23/PyTorch-Pretrained-ViT community (archive-listed) 37 samples, 31 ran (4 instrument-failed) · 6 unverified
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · d6d3c10e6aeb535b · report fixture: returned Block · level recorded 2026-09-22
ConvLayer in 26 papers pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · bac5c11bc0553d22 · report fixture: returned ConvLayer · level recorded 2026-09-22
ConvPatchingStem pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 2a3546412a06424f · report fixture: returned ConvPatchingStem · level recorded 2026-09-22
LearnedPositionalEmbedding1D pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 594cce618481c34c · report fixture: returned LearnedPositionalEmbedding1D · level recorded 2026-09-22
MultiHeadedSelfAttention in 5 papers pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · f248ced0066cd0ab · report fixture: returned MultiHeadedSelfAttention · level recorded 2026-09-22
PositionWiseFeedForward in 7 papers pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 70f627aa7f4853c5 · report fixture: returned PositionWiseFeedForward · level recorded 2026-09-22
Transformer in 173 papers pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 772f419921ed47f5 · report fixture: returned Transformer · level recorded 2026-09-22
ViTConfigExtended pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 751c351366be8421 · report fixture: returned ViTConfigExtended · level recorded 2026-09-22
as_tuple in 7 papers pytorch_pretrained_vit/model.py ran · honoured contract fingerprinted no licence file found · pointer only · 91d26d98a8c2bcac · report fixture: signature x:Tensor/2/float · returned tuple · level recorded 2026-09-22
drop_head_variant pytorch_pretrained_vit/model.py ran · our draft was wrong no licence file found · pointer only · 940661961d8b8781 · report fixture: signature config:dict/0/? · returned dict · level recorded 2026-09-22
get_b16_config pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 0244957372720000 · report fixture: returned dict · level recorded 2026-09-22
get_b32_config pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 8a9fb3fce9060134 · report fixture: returned dict · level recorded 2026-09-22
get_b4_config pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · b0106c74d0712327 · report fixture: returned dict · level recorded 2026-09-22
get_b8_config pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · d9e3a20a06c8566e · report fixture: returned dict · level recorded 2026-09-22
get_base_config pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · a2426e56644dce23 · report fixture: returned dict · level recorded 2026-09-22
get_bs16_config pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · b96af400210c0baa · report fixture: returned dict · level recorded 2026-09-22
get_bss16_config pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 5e8c727629dc439b · report fixture: returned dict · level recorded 2026-09-22
get_h14_config pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 49061a14573db1f9 · report fixture: returned dict · level recorded 2026-09-22
get_l16_config pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · fc78a7d742611cf1 · report fixture: returned dict · level recorded 2026-09-22
get_l32_config pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 0c63e27a0a2f00f9 · report fixture: returned dict · level recorded 2026-09-22
get_s16_config pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · bfb0e0bad018be12 · report fixture: returned dict · level recorded 2026-09-22
get_s32_config pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 43fb0fad9ef49df8 · report fixture: returned dict · level recorded 2026-09-22
get_s4_config pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 598ba9423fe665e6 · report fixture: returned dict · level recorded 2026-09-22
get_s8_config pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 94a821203c59b5cd · report fixture: returned dict · level recorded 2026-09-22
get_t16_config pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 3829e8ae50e23390 · report fixture: returned dict · level recorded 2026-09-22
get_t32_config pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 9bda5987ba3c7c8f · report fixture: returned dict · level recorded 2026-09-22
get_t4_config pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · e5d3710f5bbc2255 · report fixture: returned dict · level recorded 2026-09-22
get_t8_config pytorch_pretrained_vit/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · bed2ab22d759be10 · report fixture: returned dict · level recorded 2026-09-22
in1k_variant pytorch_pretrained_vit/model.py ran · our draft was wrong no licence file found · pointer only · 519ccd513d1a66b2 · report fixture: signature config:dict/0/? · returned dict · level recorded 2026-09-22
jax_to_pytorch pytorch_pretrained_vit/model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · dc17e61fe8c4cf46 · report fixture: signature k:str/0/str · returned str · level recorded 2026-09-22
resize_positional_embedding_ pytorch_pretrained_vit/model.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 759d7966d4058b8f · report fixture: signature posemb:Tensor/3/float, posemb_new:Tensor/3/float, has_class_token:bool/0/bool · returned Tensor · level recorded 2026-09-22
ViT in 10 papers pytorch_pretrained_vit/model.py unverified no licence file found · pointer only · bdda3645e9bc5ba3 · report
convert in 76 papers pytorch_pretrained_vit/model.py unverified no licence file found · pointer only · 9c2819548557ba56 · report
convert_single pytorch_pretrained_vit/model.py unverified no licence file found · pointer only · 97c346f9161a918c · report
download_load pytorch_pretrained_vit/model.py unverified no licence file found · pointer only · 5597cd0a34063332 · report
load_pretrained_weights in 20 papers pytorch_pretrained_vit/model.py unverified no licence file found · pointer only · 75d9bb6a77866f28 · report
maybe_print pytorch_pretrained_vit/model.py unverified no licence file found · pointer only · a9767da5f317f81b · report
facebookresearch/ClassyVision community (archive-listed) 9 samples, 5 ran (0 instrument-failed) · 4 unverified
ClassyHead classy_vision/models/vision_transformer.py ran · metamorphic tier: deterministic MIT (permissive) · 423c8d43bb402561 · report fixture: returned ClassyHead · level recorded 2026-09-22
ConvStemLayer classy_vision/models/vision_transformer.py ran · metamorphic tier: well formed MIT (permissive) · 886721604390e021 · report fixture: returned ConvStemLayer · level recorded 2026-09-22
Encoder in 278 papers classy_vision/models/vision_transformer.py ran · metamorphic tier: deterministic MIT (permissive) · cd17efa4361858a7 · report fixture: returned Encoder · level recorded 2026-09-22
EncoderBlock in 23 papers classy_vision/models/vision_transformer.py ran · metamorphic tier: deterministic MIT (permissive) · 5a11eb1ce59c052b · report fixture: returned EncoderBlock · level recorded 2026-09-22
MLPBlock in 17 papers classy_vision/models/vision_transformer.py ran · metamorphic tier: deterministic MIT (permissive) · 1f856d799d8ef261 · report fixture: returned MLPBlock · level recorded 2026-09-22
VisionTransformer in 53 papers classy_vision/models/vision_transformer.py unverified MIT (permissive) · 443bd35acbf7f0b2 · report
_ClassyModelAdapter classy_vision/models/vision_transformer.py unverified MIT (permissive) · 47f5bdfb51233601 · report
lecun_normal_init classy_vision/models/vision_transformer.py unverified MIT (permissive) · 0852226f61d20dcd · report
register_model in 68 papers classy_vision/models/vision_transformer.py unverified MIT (permissive) · f93eddee4749be98 · report
gupta-abhay/ViT community (archive-listed) 7 samples, 5 ran (0 instrument-failed) · 2 unverified
EmbeddingStem vit/vit.py ran · metamorphic tier: deterministic MIT (permissive) · 0bff27d821be8b25 · report fixture: returned EmbeddingStem · level recorded 2026-09-22
FeedForward in 198 papers vit/vit.py ran · metamorphic tier: deterministic MIT (permissive) · d703f6311d55cc3f · report fixture: returned FeedForward · level recorded 2026-09-22
OutputLayer in 6 papers vit/vit.py ran · metamorphic tier: deterministic MIT (permissive) · 872573b8593c5702 · report fixture: returned OutputLayer · level recorded 2026-09-22
PreNorm in 34 papers vit/vit.py ran · metamorphic tier: deterministic MIT (permissive) · ff2b7b152e2d628e · report fixture: returned PreNorm · level recorded 2026-09-22
Transformer in 173 papers vit/vit.py ran · metamorphic tier: deterministic MIT (permissive) · 4eeaefe3f8acabc0 · report fixture: returned Transformer · level recorded 2026-09-22
VisionTransformer in 53 papers vit/vit.py unverified MIT (permissive) · d022f0d80d7dc24f · report
jankrepl/mildlyoverfitted community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
github_adventures/vision_transformer/custom.py ran MIT (permissive) · e526ae2dd17da9d3 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
github_adventures/vision_transformer/custom.py ran · metamorphic tier: invariant MIT (permissive) · c559706fd8342db1 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
MLP in 375 papers github_adventures/vision_transformer/custom.py ran · metamorphic tier: invariant MIT (permissive) · 509efd435fbd7de0 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
github_adventures/vision_transformer/custom.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 029dccee9f606fea · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
VisionTransformer in 53 papers github_adventures/vision_transformer/custom.py unverified MIT (permissive) · f1b7003e1837294f · report
kamalkraj/Vision-Transformer community (archive-listed) 8 samples, 6 ran (1 instrument-failed) · 2 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
model.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · 5dba6c3975d89f90 · report fixture: signature x:EagerTensor/3/float · returned EagerTensor · level recorded 2026-09-22
FeedForward in 198 papers model.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 8b3edc18109082f5 · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
PreNorm in 34 papers model.py ran Apache-2.0 (permissive) · 5cd8fd667d56a02f · report fixture: signature x:EagerTensor/3/float · returned EagerTensor · level recorded 2026-09-24
Residual in 24 papers model.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · b308d5f20c384e2e · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input
model.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · a3ebed4aa179cd7f · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
get_activation in 218 papers model.py ran · our draft was wrong Apache-2.0 (permissive) · 04dfbbaba7483af1 · report fixture: signature identifier:str/0/str · returned function · level recorded 2026-09-22
Transformer in 173 papers model.py unverified Apache-2.0 (permissive) · ce2d3c2740d7b606 · report
ViT in 10 papers model.py unverified Apache-2.0 (permissive) · e9e0abc3f6ede535 · report
lucidrains/vit-pytorch community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
vit_pytorch/vit.py ran · metamorphic tier: invariant MIT (permissive) · 303b5fcf0f3b83ab · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
FeedForward in 198 papers vit_pytorch/vit.py ran · metamorphic tier: invariant MIT (permissive) · db72635193a2fc03 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Transformer in 173 papers vit_pytorch/vit.py ran · metamorphic tier: invariant MIT (permissive) · a9da6e0f61131262 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
ViT in 10 papers vit_pytorch/vit.py ran MIT (permissive) · 804e172ccca23ce5 · report fixture: signature img:Tensor/4/float · returned Tensor · level recorded 2026-09-24
pair in 101 papers vit_pytorch/vit.py unverified MIT (permissive) · 736b45d4b4e1b02c · report
lukemelas/PyTorch-Pretrained-ViT community (archive-listed) 11 samples, 10 ran (0 instrument-failed) · 1 unverified
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
pytorch_pretrained_vit/model.py ran no licence file found · pointer only · dd163b043f6772c8 · report fixture: returned Block · level recorded 2026-09-22
MultiHeadedSelfAttention in 5 papers pytorch_pretrained_vit/model.py ran no licence file found · pointer only · 12cebc72988df8e2 · report fixture: returned MultiHeadedSelfAttention · level recorded 2026-09-22
PositionalEmbedding1D pytorch_pretrained_vit/model.py ran no licence file found · pointer only · 230002d72e5e5756 · report fixture: returned PositionalEmbedding1D · level recorded 2026-09-22
Transformer in 173 papers pytorch_pretrained_vit/model.py ran fingerprinted no licence file found · pointer only · 482c04fd211c8a76 · report fixture: signature x:Tensor/3/float, mask:Tensor/2/bool · returned Tensor · level recorded 2026-09-24
get_b16_config pytorch_pretrained_vit/model.py ran no licence file found · pointer only · 3bc7a3a0fc1d2ac9 · report fixture: returned dict · level recorded 2026-09-22
get_b32_config pytorch_pretrained_vit/model.py ran no licence file found · pointer only · dc1ab7f114c91f47 · report fixture: returned dict · level recorded 2026-09-22
get_base_config pytorch_pretrained_vit/model.py ran no licence file found · pointer only · 1092edd3372e15e3 · report fixture: returned dict · level recorded 2026-09-22
get_l16_config pytorch_pretrained_vit/model.py ran no licence file found · pointer only · 3f62838757c21b1d · report fixture: returned dict · level recorded 2026-09-22
get_l32_config pytorch_pretrained_vit/model.py ran no licence file found · pointer only · cfd5d0f7388bcbb8 · report fixture: returned dict · level recorded 2026-09-22
load_pretrained_weights in 20 papers pytorch_pretrained_vit/model.py ran · honoured contract no licence file found · pointer only · 9d3da3ac9d5f15d2 · report fixture: signature model:callable/0/?, model_name:NoneType/0/?, weights_path:str/0/str, load_first_conv:bool/0/bool, load_fc:bool/0/bool, load_repr_layer:bool/0/bool, resize_positional_embedding:bool/0/bool, verbose:bool/0/bool, strict:bool/0/bool · returned _IncompatibleKeys · level recorded 2026-09-22
ViT in 10 papers pytorch_pretrained_vit/model.py unverified no licence file found · pointer only · a6c5dcf17fbcdeb3 · report
mdmhriday/vision-transformers community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
FeedForwardBlock in 7 papers models/vit.py ran · metamorphic tier: deterministic MIT (permissive) · 250ae33707fce8a4 · report fixture: returned FeedForwardBlock · level recorded 2026-09-22
MultiHeadAttention in 124 papers
census: 9 implementations from 7 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
models/vit.py ran MIT (permissive) · 32bc51f5c0550254 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
PatchEmbedding in 25 papers models/vit.py ran · metamorphic tier: deterministic MIT (permissive) · d65bbe0aa34f842f · report fixture: returned PatchEmbedding · level recorded 2026-09-22
Transformer in 173 papers models/vit.py ran · metamorphic tier: deterministic MIT (permissive) · 6f007e4f11af7b2a · report fixture: returned Transformer · level recorded 2026-09-22
TransformerBlock in 73 papers models/vit.py ran · metamorphic tier: deterministic MIT (permissive) · 136aaa7dc1143322 · report fixture: returned TransformerBlock · level recorded 2026-09-22
VisionTransformer in 53 papers models/vit.py ran · metamorphic tier: deterministic MIT (permissive) · 42dd7dea8413b92f · report fixture: returned VisionTransformer · level recorded 2026-09-22
pytorch/vision community (archive-listed) 10 samples, 6 ran (0 instrument-failed) · 4 unverified
ConvNormActivation in 5 papers torchvision/models/vision_transformer.py ran · metamorphic tier: deterministic fingerprinted BSD-3-Clause (permissive) · 4776b51b196152a8 · report fixture: returned ConvNormActivation · level recorded 2026-09-22
ConvStemConfig torchvision/models/vision_transformer.py ran · metamorphic tier: deterministic BSD-3-Clause (permissive) · 1212a18351c16c06 · report fixture: returned ConvStemConfig · level recorded 2026-09-22
EncoderBlock in 23 papers torchvision/models/vision_transformer.py ran · metamorphic tier: deterministic BSD-3-Clause (permissive) · 98bf127d64416382 · report fixture: returned EncoderBlock · level recorded 2026-09-22
MLP in 375 papers torchvision/models/vision_transformer.py ran · metamorphic tier: deterministic fingerprinted BSD-3-Clause (permissive) · 8a2c825d98be7cf1 · report fixture: returned MLP · level recorded 2026-09-22
MLPBlock in 17 papers torchvision/models/vision_transformer.py ran · metamorphic tier: deterministic BSD-3-Clause (permissive) · 7d66e8737fc5929b · report fixture: returned MLPBlock · level recorded 2026-09-22
_make_ntuple torchvision/models/vision_transformer.py ran · violated contract BSD-3-Clause (permissive) · 6e708d4102916a09 · report fixture: signature x:list/1/int, n:int/0/int · returned tuple · level recorded 2026-09-22
Conv2dNormActivation in 6 papers torchvision/models/vision_transformer.py unverified BSD-3-Clause (permissive) · 4b82eb7afdd244ac · report
Encoder in 278 papers torchvision/models/vision_transformer.py unverified BSD-3-Clause (permissive) · 11b5bf4147d0ab0d · report
VisionTransformer in 53 papers torchvision/models/vision_transformer.py unverified BSD-3-Clause (permissive) · 546b54df7bf1a2a7 · report
_log_api_usage_once in 8 papers torchvision/models/vision_transformer.py unverified BSD-3-Clause (permissive) · 0a0e309f9099b972 · report
seujung/pytorch-vit community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
patch_image model.py ran BSD-2-Clause (permissive) · 12b147e5bacc161d · report fixture: signature x:Tensor/4/float, size:int/0/int, N:int/0/int · returned Tensor · level recorded 2026-09-24
str2bool in 533 papers trainer.py ran · violated contract BSD-2-Clause (permissive) · 7c508037b40522af · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded
add_train_parser trainer.py unverified BSD-2-Clause (permissive) · f97a44821d0118d0 · report
uzi0espil/research-papers-implementation community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
Augmentation Vision Transformer/models.py ran no licence file found · pointer only · 436acd4bdbe997d2 · report fixture: returned Augmentation · level recorded 2026-09-22
ClassToken Vision Transformer/models.py ran no licence file found · pointer only · 17713a3cee05e6cf · report fixture: returned ClassToken · level recorded 2026-09-22
MLPHead in 5 papers Vision Transformer/models.py ran no licence file found · pointer only · dfc0aa99be911685 · report fixture: returned MLPHead · level recorded 2026-09-22
PatchEncoder in 5 papers Vision Transformer/models.py ran no licence file found · pointer only · 8c5965ae4514cb92 · report fixture: returned PatchEncoder · level recorded 2026-09-22
TransformerBlock in 73 papers Vision Transformer/models.py ran no licence file found · pointer only · 621c33d160c8772b · report fixture: returned TransformerBlock · level recorded 2026-09-22
build_vit Vision Transformer/models.py unverified no licence file found · pointer only · e2037d573231d6aa · report
baofff/U-ViT community 3 samples, 3 ran (3 instrument-failed) · 0 unverified
patchify in 32 papers
census: 6 implementations from 8 papers, 6 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 4, kind float, dtype float32
libs/uvit.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 7a7de2a8e080f047 · report fixture: signature imgs:Tensor/4/float, patch_size:int/0/int · returned Tensor · level recorded, date not recorded
timestep_embedding in 79 papers
census: 22 implementations from 27 papers, 6 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind float, dtype float32
libs/uvit.py ran · our draft was wrong fingerprinted MIT (permissive) · 262b18d8278dcf70 · report fixture: signature timesteps:Tensor/1/float, dim:int/0/int, max_period:int/0/int · returned Tensor · level recorded, date not recorded
unpatchify in 18 papers libs/uvit.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 82e1ad8a9b00554e · report fixture: signature x:Tensor/3/float, channels:int/0/int · returned Tensor · level recorded, date not recorded
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
get_1d_sincos_pos_embed_from_grid in 75 papers
census: 8 implementations from 17 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 1, kind float, dtype float32
repository not located ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence of this copy not recorded · 5c8ea92d43ead77d · report fixture: signature embed_dim:int/0/int, pos:ndarray/1/float · returned ndarray · level recorded 2026-09-22

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.

68 assemblies on this paper: 68 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

68 sibling assemblies for Vision Transformer (ViT) (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 68 sibling assemblies; the other 56 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for Vision Transformer (ViT) (graph method: Vision Transformer (ViT)). 3 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) · 0 unverified. The assembly has not been run end-to-end.

one of 68 siblings

  1. MultiHeadedAttention entry · level 1 · ran · a166a1e285a378b2
  2. attention helper · level 1 · ran · our draft was wrong · 98bf46cb18536d19
  3. clones helper · level 1 · ran · our draft was wrong · 22237c8ec0880bfd

harvested Assembly for Vision Transformer (ViT) (graph method: Vision Transformer (ViT)). 8 bricks; individually on a fixture: 5 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 68 siblings

  1. viT entry · level 0 · unverified · 733ebfa8b2c9484b
  2. ClassToken helper · level 1 · ran · 5283ae7455001543
  3. PatchEmbeddings model · level 1 · ran · f649c17f27f54d0f
  4. TransformerEncoder model · level 0 · unverified · 719d09d203720f94
  5. load_config helper · level 1 · ran · our draft was wrong · 88cc4322193ded60
  6. viTPositionalEmbedding helper · level 1 · ran · d92c10a3eb92b4d6
  7. Multihead_attention model · level 1 · ran · 4ea751912efdeefd
  8. PointWiseFeedForwardNetwork helper · level 0 · unverified · c1361ce8574f90b4

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

one of 68 siblings

  1. MaskedAutoencoderViT entry · level 1 · ran · 3fc7aef63e94d614
  2. PatchEmbed helper · level 1 · ran · 5cca4ba1d44c607a
  3. get_1d_sincos_pos_embed helper · level 1 · ran · honoured contract · eab6c08e3fce2956
  4. get_1d_sincos_pos_embed_from_grid helper · level 1 · ran; the contract check could not run (RAISES) · 5c8ea92d43ead77d

harvested Assembly for Vision Transformer (ViT) (graph method: Vision Transformer (ViT)). 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 68 siblings

  1. VisionTransformer entry · level 0 · unverified · 18eba67fe6d3f33b
  2. TransformerBlock model · level 1 · ran · 608cb341e62af9a7
  3. MultiHeadSelfAttention model · level 1 · ran · 36d6e2f710d562d7

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

one of 68 siblings

  1. VisionTransformer entry · level 1 · ran · b186094acc970ace
  2. BuildingBlock model · level 1 · ran · 126556b716f982c1
  3. PatchEmbedding model · level 1 · ran · 69703cf0b78f4fcd
  4. AttentionModel model · level 1 · ran · b527c73fd851cfee
  5. MLP helper · level 1 · ran · fa3109866a421409

harvested Assembly for Vision Transformer (ViT) (graph method: Vision Transformer (ViT)). 10 bricks; individually on a fixture: 6 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 68 siblings

  1. VisionTransformer entry · level 0 · unverified · 546b54df7bf1a2a7
  2. Conv2dNormActivation helper · level 0 · unverified · 4b82eb7afdd244ac
  3. ConvStemConfig helper · level 1 · ran · 1212a18351c16c06
  4. Encoder model · level 0 · unverified · 11b5bf4147d0ab0d
  5. _log_api_usage_once helper · level 0 · unverified · 0a0e309f9099b972
  6. ConvNormActivation helper · level 1 · ran · 4776b51b196152a8
  7. EncoderBlock model · level 1 · ran · 98bf127d64416382
  8. _make_ntuple helper · level 1 · ran · violated contract · 6e708d4102916a09
  9. MLPBlock model · level 1 · ran · 7d66e8737fc5929b
  10. MLP helper · level 1 · ran · 8a2c825d98be7cf1

harvested Assembly for Vision Transformer (ViT) (graph method: Vision Transformer (ViT)). 9 bricks; individually on a fixture: 8 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 68 siblings

  1. VisionTransformer entry · level 0 · unverified · 958ea05c3c1ae4ba
  2. Block model · level 1 · ran · 65e124fb59929e7b
  3. PatchEmbed model · level 1 · ran · 9187f42531072c00
  4. trunc_normal_ helper · level 1 · ran; the contract check could not run · 915b71e73a54fc97
  5. Attention model · level 1 · ran · 3806102629027da3
  6. DropPath model · level 1 · ran · ad5f80b54573c0e0
  7. Mlp model · level 1 · ran · a1715055832f71fd
  8. drop_path helper · level 1 · ran; the contract check could not run · 55120f2026b56aa2
  9. _no_grad_trunc_normal_ helper · level 1 · ran; the contract check could not run · 32d549c7c63738c0

harvested Assembly for Vision Transformer (ViT) (graph method: Vision Transformer (ViT)). 6 bricks; individually on a fixture: 6 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 68 siblings

  1. VisionTransformer entry · level 1 · ran · 42dd7dea8413b92f
  2. PatchEmbedding model · level 1 · ran · d65bbe0aa34f842f
  3. Transformer model · level 1 · ran · 6f007e4f11af7b2a
  4. TransformerBlock model · level 1 · ran · 136aaa7dc1143322
  5. FeedForwardBlock model · level 1 · ran · 250ae33707fce8a4
  6. MultiHeadAttention model · level 1 · ran · 32bc51f5c0550254

harvested Assembly for Vision Transformer (ViT) (graph method: Vision Transformer (ViT)). 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 68 siblings

  1. ViTBlock entry · level 1 · ran · 7ee0012316814be5
  2. Attention model · level 1 · ran · 9af3eb132594e510
  3. Mlp model · level 1 · ran · a1715055832f71fd

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

one of 68 siblings

  1. VisionTransformer entry · level 1 · ran · 78aca8814a1f8d16
  2. Transformer model · level 1 · ran · ddf39179956e840a
  3. Block helper · level 1 · ran · 82e3e86f7ef279d6
  4. MultiheadAttention helper · level 1 · ran · 28d07cea36220258

harvested Assembly for Vision Transformer (ViT) (graph method: Vision Transformer (ViT)). 2 bricks; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 68 siblings

  1. build_model entry · level 0 · unverified · b1da23dfc225c953
  2. interpret_image_size helper · level 1 · ran · honoured contract · a6d5b89d9b7d3d00

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

one of 68 siblings

  1. TransformerEncoder entry · level 1 · ran · 0e36b2dfec0a4cc5
  2. Encoder_Block model · level 1 · ran · a5c892087ae3cab9
  3. Attention model · level 1 · ran · f817c1f38785cb41
  4. MLP model · level 1 · ran · 8b9f46a6d61b24f2
  1. VisionTransformer · 281cea3cca502a15 · 10 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. ViT · 2ef391e068a6e38f · 6 bricks; individually on a fixture: 5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 5 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
  3. VIT · 311f52c73f3b3718 · 4 bricks; individually on a fixture: 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
  4. EffTransformer · 3440e7c03e4fc6f5 · 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 · assemblies[15] in the JSON twin
  5. VIT · 372fa71c788ee4f8 · 7 bricks; individually on a fixture: 6 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[16] in the JSON twin
  6. ViT · 39a65dd95e6581ce · 7 bricks; individually on a fixture: 7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 7 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[17] in the JSON twin
  7. ViT · 3f84637ce9159430 · 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 · assemblies[18] in the JSON twin
  8. ViT · 40dd0b22e3ff6cc8 · 6 bricks; individually on a fixture: 6 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[19] in the JSON twin
  9. ViT · 41f510d057b3938f · 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 · assemblies[20] in the JSON twin
  10. DinoVisionTransformer · 4205c158a4ee9f0e · 14 bricks; individually on a fixture: 11 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified · The assembly has not been run end-to-end · assemblies[21] in the JSON twin
  11. ViT · 43b5bb2555e034e1 · 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 · assemblies[22] in the JSON twin
  12. VisionTransformer · 471f7ae85767bf76 · 10 bricks; individually on a fixture: 8 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[23] in the JSON twin
  13. ViT · 49d75a2915e96b79 · 5 bricks; individually on a fixture: 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[24] in the JSON twin
  14. VisionTransformer · 4fde6c72e47b514b · 19 bricks; individually on a fixture: 11 ran (of which 9 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified · The assembly has not been run end-to-end · assemblies[25] in the JSON twin
  15. ViT · 5139fdef4a04e708 · 2 bricks; individually on a fixture: 0 ran · 2 unverified · The assembly has not been run end-to-end · assemblies[26] in the JSON twin
  16. ViT · 53a09c88198eb48d · 39 bricks; individually on a fixture: 33 ran (of which 8 constructed an object rather than computing a result; 27 with no instrument failure: 1 honoured, 0 violated, 26 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified · The assembly has not been run end-to-end · assemblies[27] in the JSON twin
  17. ViTLite · 5cdf94cbb3209922 · 7 bricks; individually on a fixture: 7 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[28] in the JSON twin
  18. VisionTransformer · 5fffca188b12b210 · 5 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[29] in the JSON twin
  19. ViT · 6273e7432f584d26 · 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 · assemblies[30] in the JSON twin
  20. ViT · 668406bb934d7b4f · 7 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified · The assembly has not been run end-to-end · assemblies[31] in the JSON twin
  21. ViT · 6b32aefda317ea98 · 7 bricks; individually on a fixture: 7 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[32] in the JSON twin
  22. VitBase · 6f1483b30b126649 · 7 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, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified · The assembly has not been run end-to-end · assemblies[33] in the JSON twin
  23. VisionTransformer · 742ba80bb2bc1749 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[34] in the JSON twin
  24. VisionTransformer · 777d03a0a4b6e145 · 14 bricks; individually on a fixture: 9 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified · The assembly has not been run end-to-end · assemblies[35] in the JSON twin
  25. VITransModel · 8139b366fac74bde · 9 bricks; individually on a fixture: 6 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified · The assembly has not been run end-to-end · assemblies[36] in the JSON twin
  26. VisionTransformer · cb067c98f8cdd464 · 12 bricks; individually on a fixture: 9 ran (of which 1 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) · 3 unverified · The assembly has not been run end-to-end · assemblies[37] in the JSON twin
  27. VisionTransformer · d07323fe47a80bd1 · 9 bricks; individually on a fixture: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified · The assembly has not been run end-to-end · assemblies[38] in the JSON twin
  28. VisionTransformer · d68f4d8042e099b1 · 14 bricks; individually on a fixture: 10 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified · The assembly has not been run end-to-end · assemblies[39] in the JSON twin
  29. ViTBase · e26e77df4e19a9d8 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[40] in the JSON twin
  30. VisionTransformer · e889d4ab9168bd6f · 6 bricks; individually on a fixture: 0 ran · 6 unverified · The assembly has not been run end-to-end · assemblies[41] in the JSON twin
  31. VisionTransformer · edf2288f2e885f70 · 5 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[42] in the JSON twin
  32. ViT · f001db1162c4cfa1 · 8 bricks; individually on a fixture: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[43] in the JSON twin
  33. MaskedAutoEncoder · f183405ea140d862 · 8 bricks; individually on a fixture: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[44] in the JSON twin
  34. ViTSTR · f1f820b3bb6681e5 · 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[45] in the JSON twin
  35. VisionTransformer · f6c8770ae8034171 · 6 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[46] in the JSON twin
  36. ViTForClassfication · fbb8f7e7368d9b2e · 10 bricks; individually on a fixture: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified · The assembly has not been run end-to-end · assemblies[47] in the JSON twin
  37. CustomSwinTransformer · 84391864b4860c0f · 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 · assemblies[48] in the JSON twin
  38. VisionTransformer · 89176d519fbf3098 · 4 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) · 1 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 · assemblies[49] in the JSON twin
  39. ViT · 897052a61cbd647b · 4 bricks; individually on a fixture: 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[50] in the JSON twin
  40. ViTLite · 8d63dc7f718b7136 · 7 bricks; individually on a fixture: 7 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[51] in the JSON twin
  41. ViT · 90d94400ea760135 · 6 bricks; individually on a fixture: 6 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[52] in the JSON twin
  42. ViT · 93ba4b2eccf22f89 · 6 bricks; individually on a fixture: 6 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[53] in the JSON twin
  43. ViT · 9592aefefe5d7926 · 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 · assemblies[54] in the JSON twin
  44. ViT · 987f3c9bf268e92c · 3 bricks; individually on a fixture: 3 ran (of which 2 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 · The assembly has not been run end-to-end · assemblies[55] in the JSON twin
  45. ViT · 99ff4ad2e809a6ad · 6 bricks; individually on a fixture: 6 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[56] in the JSON twin
  46. MyViT · 9a6231d63cab935c · 5 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[57] in the JSON twin
  47. VisionTransformer · 9b00f9a84a3f341c · 15 bricks; individually on a fixture: 11 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified · The assembly has not been run end-to-end · assemblies[58] in the JSON twin
  48. ImageTransformer · a5ef75bd0da63327 · 6 bricks; individually on a fixture: 5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 5 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[59] in the JSON twin
  49. build_vit · aa72e01f226e0eb6 · 6 bricks; individually on a fixture: 5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 5 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[60] in the JSON twin
  50. VisionTransformer · b3f3375bec365640 · 6 bricks; individually on a fixture: 6 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[61] in the JSON twin
  51. VisionTransformer · b74828afc2029438 · 7 bricks; individually on a fixture: 7 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[62] in the JSON twin
  52. ViT · ba77081ab343f266 · 18 bricks; individually on a fixture: 16 ran (of which 4 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[63] in the JSON twin
  53. ViT · bd993cf1e537112a · 6 bricks; individually on a fixture: 4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[64] in the JSON twin
  54. VisionTransformer · c11c72fe287bdd08 · 6 bricks; individually on a fixture: 0 ran · 6 unverified · The assembly has not been run end-to-end · assemblies[65] in the JSON twin
  55. ViT · c2de68684413d969 · 5 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[66] in the JSON twin
  56. VisionTransformer · c6e919dda78b48fe · 5 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[67] 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="2010.11929") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Semantic Segmentationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
32 #2 of 6 Archive leaderboard report
Domain Generalization VizWiz-Classification ViT-16/L-224 Accuracy - All Images 49 #8 of 90 Archive leaderboard report
Domain Generalization VizWiz-Classification ViT-8/B-224 Accuracy - Clean Images 450 #90 of 90 Archive leaderboard report
Fine-Grained Image Classification Oxford-IIIT Pets ViT-B/16 Top-1 Error Rate 6.2% #19 of 19 Archive leaderboard report
Image Classification CIFAR-10 ViT-H/14 Percentage correct 99.5 #1 of 265 Archive leaderboard report
Image Classification CIFAR-10 ViT-L/16 Percentage correct 99.42 #4 of 265 Archive leaderboard report
Image Classification Flowers-102 Accuracy 99.68 #5 of 52 Archive leaderboard report
Image Classification ImageNet ViT-H/14 Top 1 Accuracy 88.55% #39 of 1060 Archive leaderboard report
Image Classification ImageNet ViT-L/16 Top 1 Accuracy 87.76% #74 of 1060 Archive leaderboard report
Image Classification ImageNet ViT-Large Top 1 Accuracy 24% #1055 of 1060 Archive leaderboard report
Image Classification ObjectNet ViT-H/14 Top-5 Accuracy 82.1 #106 of 106 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: Vision Transformer

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutFixResLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerVision Transformer

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