Papers › A Simple Framework for Contrastive Learning of Visual Representations

A Simple Framework for Contrastive Learning of Visual Representations

13 Feb 2020ICML 2020 1arXiv:2002.05709archive 2025-07-28

Ting Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey Hinton

This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms without requiring specialized architectures or a memory bank. In order to understand what enables the contrastive prediction tasks to learn useful representations, we systematically study the major components of our framework. We show that (1) composition of data augmentations plays a critical role in defining effective predictive tasks, (2) introducing a learnable nonlinear transformation between the representation and the contrastive loss substantially improves the quality of the learned representations, and (3) contrastive learning benefits from larger batch sizes and more training steps compared to supervised learning. By combining these findings, we are able to considerably outperform previous methods for self-supervised and semi-supervised learning on ImageNet. A linear classifier trained on self-supervised representations learned by SimCLR achieves 76.5% top-1 accuracy, which is a 7% relative improvement over previous state-of-the-art, matching the performance of a supervised ResNet-50. When fine-tuned on only 1% of the labels, we achieve 85.8% top-5 accuracy, outperforming AlexNet with 100X fewer labels.

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.

Syntology holds a reference implementation of SimCLR, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). For this implementation, level 3 is recorded, but its report lists no property test that passed on both. No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='SimCLR') (how to connect); the free check have('2002.05709') needs no token.

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

Code

Syntology 137 code samples harvested from 55 repositories linked to this paper: 115 ran (of which 33 constructed an object rather than computing a result; 89 with no instrument failure: 1 honoured, 1 violated, 87 with no contract checked; 26 where Syntology's instrument failed) · 22 unverified. Where Syntology's instrument failed: 21 where our contract draft was wrong; 5 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 2 ran (0 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 135 samples from 54 repositories, 113 ran (89 with no instrument failure; 24 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 21 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 6 of the 115 samples that ran have no recorded date.

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

google-research/simclr officialmentioned in papermentioned on GitHubtfSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
63days/SimCLR mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
AidenDurrant/MoCo-Pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Momentum Contrast for Unsupervised Visual Representation Learning (arXiv:1911.05722; that paper's own run record: 28 ran (of which 16 constructed an object rather than computing a result; 23 with no instrument failure: 0 honoured, 0 violated, 23 with no contract checked; 5 where Syntology's instrument failed) · 14 unverified); nothing checks that they implement this paper's method. report
AndrewAtanov/simclr-pytorch mentioned on GitHubpytorchMITSyntology: 13 samples, 11 ran (0 instrument-failed) · 2 unverified report
BalajiAI/SimCLR mentioned on GitHubpytorchMITSyntology: not harvested report
Daniel-H-99/SimCLR mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
HobbitLong/SupContrast mentioned on GitHubpytorchBSD-2-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Combating Bilateral Edge Noise for Robust Link Prediction (arXiv:2311.01196; that paper's own run record: 20 ran (of which 2 constructed an object rather than computing a result; 15 with no instrument failure: 3 honoured, 1 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 14 unverified); nothing checks that they implement this paper's method. report
JoonHyung-Park/SimCLR mentioned on GitHubpytorchSyntology: not harvested report
Liut2016/ecg-supcontrast mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Mind23-2/MindCode-76 mentioned on GitHubmindsporeSyntology: not harvested report
SaeedShurrab/SimSiam-pytorch mentioned on GitHubpytorchSyntology: not harvested 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
XG293/SupConLoss mentioned on GitHubpytorchBSD-2-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Supervised Contrastive Learning (arXiv:2004.11362; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
acholston/SimCLR mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
ae-foster/pytorch-simclr mentioned on GitHubpytorchMITSyntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report
alexk1704/scclv2 mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Supervised Contrastive Learning (arXiv:2004.11362; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
anonymousmlsubmission/datadistributiontransfer mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to The Role of Pre-training Data in Transfer Learning (arXiv:2302.13602; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
applecrumble123/SimCLR_pytorch mentioned on GitHubpytorchSyntology: not harvested report
asd08573064/SimCLR mentioned on GitHubtfMITSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
beresandras/contrastive-classification-keras mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
bjader/QSSL mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
brainimageanalysis/marmosetgeneatlas_adult mentioned on GitHubApache-2.0Syntology: not harvested report
caesarea38/doclangid mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
chingyaoc/DCL mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Debiased Contrastive Learning (arXiv:2007.00224; that paper's own run record: 0 ran · 1 unverified); nothing checks that they implement this paper's method. report
cjrd/self-supervised-pretraining mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Self-Supervised Pretraining Improves Self-Supervised Pretraining (arXiv:2103.12718; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
clabrugere/pytorch-scarf mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
cyrilvallez/image-manipulation-detection mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
danielzgsilva/MOT mentioned on GitHubpytorchSyntology: not harvested report
davidczy/supcon_gamma mentioned on GitHubpytorchBSD-2-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Supervised Contrastive Learning (arXiv:2004.11362; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
delyan-boychev/grad-cache-con-learning mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
dewenzeng/clsp mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
edreismd/convirt-pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
edureisMD/ConVIRT-pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
eminorhan/baby-vision mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Self-supervised learning through the eyes of a child (arXiv:2007.16189; that paper's own run record: 7 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; 1 where Syntology's instrument failed) · 4 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
filipbasara0/matryoshka-representation-learning mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
forcesh/SupContrast mentioned on GitHubpytorchSyntology: not harvested report
guerbet-ai/wsp-contrastive mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
hannaiiyanggit/unicon mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
hemakaraveenhansika/convirt mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
htdt/self-supervised mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
john-mlr/CIFAR-10-SimCLR mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
jramapuram/SimCLR mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
jwcalder/GraphLearningLayer mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
kawshik8/DL-project mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
krafton-ai/mini-batch-cl mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Large Batch Training of Convolutional Networks (arXiv:1708.03888; that paper's own run record: 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); nothing checks that they implement this paper's method. report
leftthomas/SimCLR mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
lightly-ai/lightly mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
liuch37/image-processing mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
mandiehyewon/goodviews_ecg mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
mariaauslander/capstone_fall20_irrigation mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
mdiephuis/simclr mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
ninatu/mood_challenge mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Anomaly Detection in Medical Imaging with Deep Perceptual Autoencoders (arXiv:2006.13265; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
open-mmlab/mmselfsup mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PixMIM: Rethinking Pixel Reconstruction in Masked Image Modeling (arXiv:2303.02416; 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
optimization-ai/sogclr mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
p3i0t/simclr-cifar10 mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
parkinkon1/simclr mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
phanav/simclr-presentation mentioned on GitHubSyntology: not harvested report
radiradev/contrastive-neutrino mentioned on GitHubpytorchSyntology: not harvested report
rahimentezari/datadistributiontransferlearning mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
rajatkoner08/oodformer mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
rdbch/simclr mentioned on GitHubpytorchSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
rdbch/tutorial_simclr mentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
reppy4620/SimCLR4Paint mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
rmastand/jetclr_ad mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Symmetries, Safety, and Self-Supervision (arXiv:2108.04253; that paper's own run record: 4 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; 4 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
roydenwa/cell-centroid-former mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
salarim/Semi-Supervised-CL mentioned on GitHubpytorchSyntology: not harvested report
sayakpaul/SimCLR-in-TensorFlow-2 mentioned on GitHubtfMITSyntology: not harvested report
serre-lab/prj_selfsup mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Big Self-Supervised Models are Strong Semi-Supervised Learners (arXiv:2006.10029; 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) · 2 unverified); nothing checks that they implement this paper's method. report
sidwa/ae_thesis mentioned on GitHubpytorchSyntology: not harvested report
spijkervet/simclr mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (3 instrument-failed) · 0 unverified report
ssumin6/SimCLR mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
sunjesse/SimCLR_pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
sylviesss/pytorch-simclr mentioned on GitHubpytorchSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
ta9ryuWalrus/simclr mentioned on GitHubtfSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
talipucar/PyFlow_SimCLR mentioned on GitHubpytorchSyntology: 8 samples, 5 ran (1 instrument-failed) · 3 unverified report
thunderInfy/simclr mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
ushmabhatt/Contrastive-Learning mentioned on GitHubtfSyntology: not harvested report
ut-vision/simhand mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training (arXiv:2502.15251; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
vturrisi/solo-learn mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improved Baselines with Momentum Contrastive Learning (arXiv:2003.04297; that paper's own run record: 28 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 1 violated, 20 with no contract checked; 7 where Syntology's instrument failed) · 15 unverified), Whitening for Self-Supervised Representation Learning (arXiv:2007.06346; that paper's own run record: 11 ran (of which 3 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified) and ReSSL: Relational Self-Supervised Learning with Weak Augmentation (arXiv:2107.09282; that paper's own run record: 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) · 0 unverified); nothing checks that they implement this paper's method. report
wilile26811249/SimCLR mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
wvangansbeke/Unsupervised-Classification mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
yoojungsun0/Psych239 mentioned on GitHubpytorchSyntology: not harvested report
zpf0117b/CLMB mentioned on GitHubpytorchMITSyntology: 9 samples, 9 ran (1 instrument-failed) · 0 unverified report
2023-MindSpore-1/ms-code-216 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code11 mindsporeSyntology: not harvested report
Mayurji/SimCLR pytorchSyntology: 2 samples, 0 ran · 2 unverified report
Pangoraw/GeoSSL pytorchSyntology: 5 samples, 4 ran (2 instrument-failed) · 1 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
code-implementation1/Code8 mindsporeSyntology: not harvested report
giakou4/pyfeats MITSyntology: 12 samples, 8 ran (0 instrument-failed) · 4 unverified report
giakou4/pyssl pytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified 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
nzw0301/simclr pytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
sthalles/SimCLR pytorchMITSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
tensorflow/models tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to 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), 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), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. 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

137 samples harvested: 115 ran (of which 33 constructed an object rather than computing a result; 89 with no instrument failure: 1 honoured, 1 violated, 87 with no contract checked; 26 where Syntology's instrument failed) · 22 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
21ran · our draft was wrong
5ran; the contract check could not run
87ran
22unverified

Licence: 52 of the 137 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 55 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 whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 18 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/simclr official repository 2 samples, 2 ran (2 instrument-failed) · 0 unverified
add_contrastive_loss objective.py ran · our draft was wrong Apache-2.0 (permissive) · c418940b96d1fe9e · report fixture: signature hidden:SymbolicTensor/2/float, hidden_norm:bool/0/bool, temperature:float/0/float, tpu_context:NoneType/0/?, weights:float/0/float · returned tuple · level recorded 2026-09-22
tpu_cross_replica_concat objective.py ran · our draft was wrong Apache-2.0 (permissive) · 7aac0de5d1568953 · report fixture: signature tensor:SymbolicTensor/2/float, tpu_context:TPUContext/0/? · returned SymbolicTensor · level recorded 2026-09-22
63days/SimCLR community (archive-listed) 1 sample, 0 ran · 1 unverified
SimCLR model.py unverified no licence file found · pointer only · ff90bea0467c6b51 · report
AndrewAtanov/simclr-pytorch community (archive-listed) 13 samples, 11 ran (0 instrument-failed) · 2 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
models/losses.py ran MIT (permissive) · 11bc56dd2ecb7644 · report fixture: signature logits:Tensor/2/float, labels:Tensor/2/int, k:int/0/int · returned Tensor · level recorded 2026-09-24
agg_all_metrics utils/utils.py ran MIT (permissive) · 2c4b4b78675c35ee · report fixture: signature outputs:list/1/dict · returned dict · level recorded 2026-09-24
get_color_distortion in 9 papers utils/datautils.py ran MIT (permissive) · 94226f82998bee03 · report fixture: signature s:float/0/float · returned Compose · level recorded 2026-09-25
mean_cumulative_gain models/losses.py ran MIT (permissive) · 439f4fcb999995b5 · report fixture: signature logits:Tensor/2/float, labels:Tensor/2/int, k:int/0/int · returned Tensor · level recorded 2026-09-25
only_value_error myexman/index.py ran MIT (permissive) · c404ad6b3c3cae86 · report fixture: signature conv:callable/0/? · returned function · level recorded 2026-09-24
pad in 85 papers utils/datautils.py ran MIT (permissive) · eab99ab911f1645a · report fixture: signature img:Image/0/?, size:int/0/int, mode:str/0/str · returned ndarray · level recorded 2026-09-25
represent_as_str myexman/parser.py ran MIT (permissive) · 0834c0be7a6b72e8 · report fixture: signature self:Representer/0/?, data:CustomObject/0/?, tostr:callable/0/? · returned ScalarNode · level recorded 2026-09-24
simpleroot myexman/parser.py ran MIT (permissive) · e098d0fbdbf83114 · report fixture: signature __file__:str/0/str · returned PosixPath · level recorded 2026-09-24
timing in 6 papers utils/utils.py ran MIT (permissive) · 7d95614711e96832 · report fixture: signature f:callable/0/? · returned function · level recorded 2026-09-24
viz_array_grid utils/utils.py ran MIT (permissive) · d77f6aa7bb727375 · report fixture: signature array:Tensor/4/float, rows:int/0/int, cols:int/0/int, padding:int/0/int, channels_last:bool/0/bool, normalize:bool/0/bool · returned ndarray · level recorded 2026-09-24
yaml_file myexman/parser.py ran fingerprinted MIT (permissive) · f823e0add18d7eec · report fixture: signature name:str/0/str · returned str · level recorded 2026-09-24
get_args in 84 papers myexman/index.py unverified MIT (permissive) · 5bd550cf0a598b22 · report
none2none myexman/index.py unverified MIT (permissive) · 459939c749c8fd3f · report
Daniel-H-99/SimCLR community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
Res18 model.py ran no licence file found · pointer only · 2f6dc2d5f30f106e · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Res18Block model.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 8556399cf0e482d3 · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Res18ConvLayer model.py ran no licence file found · pointer only · 24e7779cb2a243e3 · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-24
ShortCut model.py ran no licence file found · pointer only · b27ce753d440a134 · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Liut2016/ecg-supcontrast community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
SupConLoss in 21 papers losses.py ran · metamorphic tier: invariant BSD-2-Clause (permissive) · d8d1dd0aafb92f18 · report fixture: signature features:Tensor/3/float, labels:Tensor/1/int, mask:NoneType/0/? · returned Tensor · level recorded 2026-09-22
acholston/SimCLR community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ContLoss loss.py ran fingerprinted no licence file found · pointer only · 5ad08dec1ed71937 · report fixture: returned ContLoss · level recorded 2026-09-22
ae-foster/pytorch-simclr community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
BlurOrSharpen augmentation.py ran MIT (permissive) · 7937263b7909ba06 · report fixture: signature radius:float/0/float · returned RandomApply · level recorded 2026-09-24
ColourDistortion augmentation.py ran MIT (permissive) · d05210f656c96fc4 · report fixture: signature s:float/0/float · returned Compose · level recorded 2026-09-24
add_indices dataset.py ran MIT (permissive) · 4cc4c53bf5875d64 · report fixture: signature dataset_cls:callable/0/? · returned type · level recorded 2026-09-24
encode_train_set evaluate/lbfgs.py ran MIT (permissive) · 3615fd781c0e7e45 · report fixture: signature clftrainloader:list/1/tuple, device:str/0/str, net:callable/0/? · returned tuple · level recorded 2026-09-25
test in 377 papers evaluate/lbfgs.py ran MIT (permissive) · 3f1dd5d8d7b83513 · report fixture: signature testloader:list/1/tuple, device:str/0/str, net:callable/0/?, clf:callable/0/? · returned float · level recorded 2026-09-24
train_clf in 6 papers evaluate/lbfgs.py ran MIT (permissive) · 4ec61811bee71758 · report fixture: signature X:Tensor/2/float, y:Tensor/1/int, representation_dim:int/0/int, num_classes:int/0/int, device:str/0/str, reg_weight:float/0/float · returned Linear · level recorded 2026-09-24
asd08573064/SimCLR community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
contrastive_loss in 80 papers
census: 11 implementations from 18 papers, 7 distinct outputs across 3 buckets, one shared input per bucket
train_SSL.py ran MIT (permissive) · eac22c52c3120485 · report fixture: signature projections_1:EagerTensor/2/float, projections_2:EagerTensor/2/float, temperature:float/0/float · returned EagerTensor · level recorded 2026-09-24
parse_images dataset.py ran MIT (permissive) · 034143e2f3288a7c · report fixture: signature image_path:str/0/str · returned EagerTensor · level recorded 2026-09-24
beresandras/contrastive-classification-keras community (archive-listed) 1 sample, 0 ran · 1 unverified
SimCLR algorithms.py unverified MIT (permissive) · f81649524890dfe5 · report
bjader/QSSL community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
SimCLR moco/builder.py ran · metamorphic tier: deterministic MIT (permissive) · e78d903f294bb8e2 · report fixture: returned SimCLR · level recorded 2026-09-22
caesarea38/doclangid community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
apply_op in 5 papers src/core/augmentations.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 0809a27fc54eb733 · report fixture: signature image:Image/0/?, op_name:str/0/str, magnitude:float/0/float, interpolation:int/0/int, fill:int/0/int · returned Image · level recorded 2026-09-22
generate_op_meta src/core/augmentations.py ran · our draft was wrong no licence file found · pointer only · b621a5344f937d5e · report fixture: signature numb_magnitudes:int/0/int, image_size:int/0/int · returned dict · level recorded 2026-09-22
randaugment src/core/augmentations.py ran · our draft was wrong no licence file found · pointer only · 5b8da074d51c8e00 · report fixture: signature image:Image/0/?, ops:tuple/1/int, mag:tuple/1/int, numb_magnitudes:int/0/int, interpolation:InterpolationMode/0/?, fill:list/1/int · returned Image · level recorded 2026-09-22
clabrugere/pytorch-scarf community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
NTXent scarf/loss.py ran fingerprinted MIT (permissive) · 249ded5d814fb1fd · report fixture: returned NTXent · level recorded 2026-09-22
cyrilvallez/image-manipulation-detection community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
Bottleneck in 98 papers hashing/SimCLRv1/resnet_wider.py ran MIT (permissive) · e6a9a9260ef0a74a · report fixture: returned Bottleneck · level recorded 2026-09-22
ResNet in 139 papers hashing/SimCLRv1/resnet_wider.py unverified MIT (permissive) · ea2c3cf94bcdfef3 · report
delyan-boychev/grad-cache-con-learning community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
SupConLoss in 21 papers src/grad_cache_con_learning/losses.py ran Apache-2.0 (permissive) · 19bb24ecb5d473db · report fixture: signature features:Tensor/3/float, labels:Tensor/1/int, mask:NoneType/0/? · returned Tensor · level recorded 2026-09-24
dewenzeng/clsp community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ContrastiveHead models/resnet_sk.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 7d227e358ec14382 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
filipbasara0/matryoshka-representation-learning community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
_adapt_resnet_model mrl/encoders/models.py ran · our draft was wrong MIT (permissive) · 50709c4ec879ecc5 · report fixture: signature model:callable/0/? · returned MinimalResNet · level recorded 2026-09-22
guerbet-ai/wsp-contrastive community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
NTXenLoss losses.py ran fingerprinted licence not identified · pointer only · 4fa18a92d2d6193b · report fixture: returned NTXenLoss · level recorded 2026-09-22
hannaiiyanggit/unicon community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
SupConLoss in 21 papers losses.py ran Apache-2.0 (permissive) · a5dbd9a427e2bec3 · report fixture: signature features:Tensor/3/float, labels:Tensor/1/int, mask:NoneType/0/? · returned Tensor · level recorded 2026-09-24
hemakaraveenhansika/convirt community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
NTXentLoss in 5 papers loss/nt_xent.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · f3d9092135724cbd · report fixture: returned NTXentLoss · level recorded 2026-09-22
htdt/self-supervised community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
contrastive_loss in 80 papers
census: 11 implementations from 18 papers, 7 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 2 of 3, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
methods/contrastive.py ran; the contract check could not run (RAISES) no licence file found · pointer only · ba00312b3d5b70dc · report fixture: returned Tensor · level recorded 2026-09-22
Contrastive methods/contrastive.py unverified no licence file found · pointer only · d1deb5d7410ae0b7 · report
john-mlr/CIFAR-10-SimCLR community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
NT_Xent in 8 papers simclr/modules/nt_xent.py ran no licence file found · pointer only · f10b64ecf0f39804 · report fixture: signature z_i:Tensor/2/float, z_j:Tensor/2/float · returned Tensor · level recorded 2026-09-24
jramapuram/SimCLR community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
NTXent objective.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · dec5ae5526431e69 · report fixture: signature embedding1:Tensor/2/float, embedding2:Tensor/2/float, temperature:float/0/float, num_replicas:int/0/int · returned Tensor · level recorded 2026-09-22
all_gather in 119 papers objective.py ran · our draft was wrong MIT (permissive) · 2b5d65dc96c1a03b · report fixture: signature tensor:Tensor/2/float, expand_dim:int/0/int, num_replicas:int/0/int · returned Tensor · level recorded 2026-09-22
l2_normalize in 40 papers
census: 15 implementations from 13 papers, 5 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 2, kind float, dtype float32
objective.py ran · our draft was wrong fingerprinted MIT (permissive) · 6325cd34bc332e95 · report fixture: signature x:Tensor/2/float, dim:int/0/int, eps:float/0/float · returned Tensor · level recorded 2026-09-22
jwcalder/GraphLearningLayer community (archive-listed) 1 sample, 0 ran · 1 unverified
SupConLoss in 21 papers losses.py unverified MIT (permissive) · 0e2efd6b67f01d69 · report
kawshik8/DL-project community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
ImageSSLModels src/SSLmodels.py ran · metamorphic tier: deterministic no licence file found · pointer only · 0a6342453ea2f75f · report fixture: returned ImageSSLModels · level recorded 2026-09-22
SSLModel src/SSLmodels.py ran · metamorphic tier: deterministic no licence file found · pointer only · 54df182d9c00588a · report fixture: returned SSLModel · level recorded 2026-09-22
get_base_model in 10 papers src/SSLmodels.py ran · our draft was wrong no licence file found · pointer only · 8c4252f18f2e14a8 · report fixture: signature name:str/0/str · returned ResNet · level recorded 2026-09-22
leftthomas/SimCLR community (archive-listed) 1 sample, 0 ran · 1 unverified
train_val in 10 papers linear.py unverified no licence file found · pointer only · 667eaf3785a1c4a9 · report
lightly-ai/lightly community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
SimCLR lightly/models/simclr.py ran fingerprinted MIT (permissive) · dccd7194c3fa9092 · report fixture: returned SimCLR · level recorded 2026-09-22
SimCLRProjectionHead lightly/models/simclr.py ran MIT (permissive) · 2d22ec7eee6353ce · report fixture: returned SimCLRProjectionHead · level recorded 2026-09-22
liuch37/image-processing community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_color_distortion in 9 papers augmentation/color_distortion_pytorch.py ran · our draft was wrong Apache-2.0 (permissive) · 0adaf15a01b00920 · report fixture: signature s:float/0/float · returned Compose · level recorded 2026-09-22
mandiehyewon/goodviews_ecg community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_contrastive_loss utils/loss.py ran · our draft was wrong no licence file found · pointer only · 6181cfb7ba78942e · report fixture: signature args:Args/0/?, features:Tensor/2/float, group_labels:Tensor/1/int, device:device/0/? · returned Tensor · level recorded 2026-09-22
mariaauslander/capstone_fall20_irrigation community (archive-listed) 1 sample, 0 ran · 1 unverified
build_simclr_model simclr.py unverified no licence file found · pointer only · bb4e645996e12174 · report
mdiephuis/simclr community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
contrastive_loss in 80 papers
census: 11 implementations from 18 papers, 7 distinct outputs across 3 buckets, one shared input per bucket
loss.py ran fingerprinted MIT (permissive) · eb14839e65ee11cf · report fixture: signature xi:Tensor/2/float, xj:Tensor/2/float · returned Tensor · level recorded 2026-09-24
optimization-ai/sogclr community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
SimCLR sogclr/builder.py ran no licence file found · pointer only · b4045ab6673c8148 · report fixture: returned SimCLR · level recorded 2026-09-22
all_gather_layer sogclr/builder.py ran no licence file found · pointer only · 8e2cdb7569401c95 · report fixture: returned all_gather_layer · level recorded 2026-09-22
p3i0t/simclr-cifar10 community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
get_lr in 91 papers simclr.py ran · violated contract fingerprinted no licence file found · pointer only · 190117b425ab9fe1 · report fixture: signature step:int/0/int, total_steps:int/0/int, lr_max:float/0/float, lr_min:float/0/float · returned float64 · level recorded, date not recorded
SimCLR models.py ran fingerprinted no licence file found · pointer only · db46cc53970a4db1 · report fixture: returned SimCLR · level recorded 2026-09-22
nt_xent in 10 papers simclr.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 0931a280f76e561f · report fixture: signature x:Tensor/2/float, t:float/0/float · returned Tensor · level recorded, date not recorded
parkinkon1/simclr community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
add_contrastive_loss objective.py ran · our draft was wrong Apache-2.0 (permissive) · 8924ee1d1cde05c4 · report fixture: signature hidden:SymbolicTensor/2/float, hidden_norm:bool/0/bool, temperature:float/0/float, tpu_context:NoneType/0/?, weights:float/0/float · returned tuple · level recorded 2026-09-22
rahimentezari/datadistributiontransferlearning community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
SIMCLR src/models/simclr/models.py ran licence not identified · pointer only · f33e37ad81b7d344 · report fixture: signature aug1:Tensor/2/float, aug2:Tensor/2/float · returned dict · level recorded 2026-09-24
rajatkoner08/oodformer community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
SupConLoss in 21 papers losses.py ran no licence file found · pointer only · 1d1a1df3f3426c17 · report fixture: signature features:Tensor/3/float, labels:Tensor/1/int, mask:NoneType/0/? · returned Tensor · level recorded 2026-09-24
euclidean_dist in 69 papers
census: 12 implementations from 14 papers, 3 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
OOD_Distance.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · honoured contract fingerprinted licence of this copy not recorded · 57bbb1c2ae467a4f · report fixture: signature x:Tensor/2/float, support_mean:Tensor/2/float · returned Tensor · level recorded 2026-09-22
mahalanobis losses.py ran · our draft was wrong no licence file found · pointer only · ae6df0014dbc55c9 · report fixture: signature x:Tensor/2/float, support_mean:list/1/Tensor, inv_covmat:list/1/ndarray · returned Tensor · level recorded 2026-09-24
rdbch/simclr community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
MLP in 375 papers core/networks/simclr.py ran MIT (permissive) · 2a061ea2756788d0 · report fixture: returned MLP · level recorded 2026-09-22
ResNet in 139 papers core/networks/simclr.py ran MIT (permissive) · 8ae8bb52d6e02325 · report fixture: returned ResNet · level recorded 2026-09-22
Configurable core/networks/simclr.py unverified MIT (permissive) · 7fd8c4e94eb9d6f4 · report
SimCLR core/networks/simclr.py unverified MIT (permissive) · 04a16872e7176429 · report
rdbch/tutorial_simclr community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
same_padding in 10 papers core/nn/blocks/utils.py ran fingerprinted MIT (permissive) · 122255f68540f240 · report fixture: signature kSize:int/0/int, dilSize:int/0/int · returned tuple · level recorded 2026-09-24
simple_import core/nn/blocks/utils.py ran MIT (permissive) · c91376d1f880ecf3 · report fixture: signature name:str/0/str, pack:str/0/str · returned module · level recorded 2026-09-24
reppy4620/SimCLR4Paint community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
Flatten in 23 papers
census: 9 implementations from 9 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
modules/simclr.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · c6673456e63337b4 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
SimCLR modules/simclr.py ran no licence file found · pointer only · 4c7f0882280707e1 · report fixture: returned SimCLR · level recorded 2026-09-22
roydenwa/cell-centroid-former community (archive-listed) 1 sample, 0 ran · 1 unverified
SimCLR src/cellcentroidformer/self_supervised.py unverified no licence file found · pointer only · 708baa8232f99ac8 · report
spijkervet/simclr community (archive-listed) 4 samples, 4 ran (3 instrument-failed) · 0 unverified
SimCLR simclr/simclr.py ran · metamorphic tier: deterministic MIT (permissive) · 99b66383d6cd5bf7 · report fixture: returned SimCLR · level recorded 2026-09-22
create_data_loaders_from_arrays linear_evaluation.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 6842d0dec7d692ae · report fixture: signature X_train:ndarray/2/float, y_train:ndarray/1/int, X_test:ndarray/2/float, y_test:ndarray/1/int, batch_size:int/0/int · returned tuple · level recorded, date not recorded
get_features in 57 papers linear_evaluation.py ran · our draft was wrong MIT (permissive) · cb291d2ffc7590c7 · report fixture: signature simclr_model:callable/0/?, train_loader:list/1/tuple, test_loader:list/1/tuple, device:str/0/str · returned tuple · level recorded, date not recorded
inference in 65 papers linear_evaluation.py ran · our draft was wrong MIT (permissive) · e0f6be0e6d3d8c17 · report fixture: signature loader:list/1/tuple, simclr_model:callable/0/?, device:device/0/? · returned tuple · level recorded, date not recorded
ssumin6/SimCLR community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
SimCLR model.py ran no licence file found · pointer only · 4578ef90ebbe26cd · report fixture: returned SimCLR · level recorded 2026-09-22
sunjesse/SimCLR_pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
SimLoss loss.py ran fingerprinted no licence file found · pointer only · 00e45e65ec60a85c · report fixture: signature batch:Tensor/2/float · returned Tensor · level recorded 2026-09-24
sylviesss/pytorch-simclr community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
Dropout in 8 papers models/simclr.py ran fingerprinted no licence file found · pointer only · 43ca37aec47363d7 · report fixture: returned Dropout · level recorded 2026-09-22
DropoutNd in 5 papers models/simclr.py ran no licence file found · pointer only · 3cb087a414dec282 · report fixture: returned DropoutNd · level recorded 2026-09-22
ResnetEncoder models/simclr.py ran fingerprinted no licence file found · pointer only · 15c470cde64303bb · report fixture: returned ResnetEncoder · level recorded 2026-09-22
ResnetEncoderDropout models/simclr.py ran fingerprinted no licence file found · pointer only · 5069ef275d4321a2 · report fixture: returned ResnetEncoderDropout · level recorded 2026-09-22
SimCLRMain models/simclr.py ran fingerprinted no licence file found · pointer only · 3ac7ccd797e47c29 · report fixture: returned SimCLRMain · level recorded 2026-09-22
ta9ryuWalrus/simclr community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
add_contrastive_loss tf2/objective.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 92885c7117af82c9 · report fixture: signature hidden:EagerTensor/2/float, hidden_norm:bool/0/bool, temperature:float/0/float, strategy:NoneType/0/? · returned tuple · level recorded 2026-09-22
tpu_cross_replica_concat tf2/objective.py ran · our draft was wrong Apache-2.0 (permissive) · 5ef56dc923793fb3 · report fixture: signature tensor:EagerTensor/2/float, strategy:MockStrategy/0/? · returned EagerTensor · level recorded 2026-09-22
talipucar/PyFlow_SimCLR community (archive-listed) 8 samples, 5 ran (1 instrument-failed) · 3 unverified
CNNEncoder src/model.py ran fingerprinted no licence file found · pointer only · 0736b9b372d39725 · report fixture: signature x:Tensor/4/float · returned tuple · level recorded 2026-09-24
Identity in 49 papers
census: 10 implementations from 13 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
src/model.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · b77efc36f9b77b9b · report fixture: returned Identity · level recorded 2026-09-22
NTXentLoss in 5 papers src/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 93679e35512cbdb7 · report fixture: returned NTXentLoss · level recorded 2026-09-22
ResNet in 139 papers src/model.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · c541394f43fa9adc · report fixture: returned ResNet · level recorded 2026-09-22
global_ave_pool src/model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 6940670c59bb0cda · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
ContrastiveEncoder src/model.py unverified no licence file found · pointer only · f5ffc1cae804d1f7 · report
save_loss_plot src/model.py unverified no licence file found · pointer only · 75b95f2eaa47b97b · report
set_seed in 49 papers src/model.py unverified no licence file found · pointer only · 20855bdedf943b8f · report
thunderInfy/simclr community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
SimCLR simclr.py ran no licence file found · pointer only · 2c196dbc33af1e86 · report fixture: returned SimCLR · level recorded 2026-09-22
wilile26811249/SimCLR community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ResNetSimCLR model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 40a653c6651fc5d4 · report fixture: returned ResNetSimCLR · level recorded 2026-09-22
wvangansbeke/Unsupervised-Classification community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
SimCLRLoss losses/losses.py ran licence not identified · pointer only · 6db2a02555c7f204 · report fixture: signature features:Tensor/3/float · returned Tensor · level recorded 2026-09-22
zpf0117b/CLMB community (archive-listed) 9 samples, 9 ran (1 instrument-failed) · 0 unverified
clique_merge src/mergeclusters.py ran MIT (permissive) · 583552044648d2f0 · report fixture: signature contigsof:dict/0/?, threshold:float/0/float · returned dict · level recorded 2026-09-24
create_projection_kernel src/create_kernel.py ran MIT (permissive) · 5d283bdd3a74687f · report fixture: signature k:int/0/int · returned ndarray · level recorded 2026-09-24
create_rc_kernel src/create_kernel.py ran MIT (permissive) · c412bcc0dbd87516 · report fixture: signature k:int/0/int · returned ndarray · level recorded 2026-09-24
filter_clusters vamb/benchmark.py ran MIT (permissive) · 1f3daef400d7d53c · report fixture: signature clusters:dict/0/?, reference:MockReference/0/?, minsize:int/0/int, mincontigs:int/0/int, checkpresence:bool/0/bool · returned dict · level recorded 2026-09-24
get_adjusted_rand_score src/benchmark_old.py ran MIT (permissive) · 86b892b3b407785f · report fixture: signature clusters1:dict/0/?, clusters2:dict/0/? · returned float · level recorded 2026-09-24
hierarchical_merge src/mergeclusters.py ran MIT (permissive) · df7842ad80bc568e · report fixture: signature contigsof:dict/0/?, threshold:float/0/float · returned dict · level recorded 2026-09-24
pairs vamb/cluster.py ran MIT (permissive) · 9a021af106b97cf3 · report fixture: signature clustergenerator:ClusterGenerator/0/?, labels:ndarray/1/int · returned generator · level recorded 2026-09-24
reverse_complement src/create_kernel.py ran · our draft was wrong fingerprinted MIT (permissive) · cfd9492c2dbc3c97 · report fixture: signature nuc:str/0/str · returned str · level recorded 2026-09-24
subgraph_merge src/mergeclusters.py ran MIT (permissive) · c48a4ea6fafc859f · report fixture: signature contigsof:dict/0/?, threshold:float/0/float · returned dict · level recorded 2026-09-24
Mayurji/SimCLR community (archive-listed) 2 samples, 0 ran · 2 unverified
SimCLR SimCLR.py unverified GPL-3.0 (copyleft) · pointer only · aea60f5692813252 · report
save_checkpoint in 36 papers SimCLR.py unverified GPL-3.0 (copyleft) · pointer only · 7e7b54ff38780a53 · report
Pangoraw/GeoSSL community (archive-listed) 5 samples, 4 ran (2 instrument-failed) · 1 unverified
ResNetBackbone in 10 papers geossl/simclr.py ran fingerprinted MIT (permissive) · 7339ae06662b97a5 · report fixture: returned ResNetBackbone · level recorded 2026-09-22
SimCLR geossl/simclr.py ran MIT (permissive) · 965480d2c18b15a7 · report fixture: returned SimCLR · level recorded 2026-09-22
_get_weights_url geossl/simclr.py ran · our draft was wrong MIT (permissive) · 589ff9232fa952cc · report fixture: signature rn_model:str/0/str, dataset:str/0/str, method:str/0/str · returned str · level recorded 2026-09-22
nt_xent in 10 papers geossl/simclr.py ran · our draft was wrong MIT (permissive) · 56d873a0ee406a9d · report fixture: signature z:Tensor/2/float, perm:Tensor/1/int, tau:float/0/float · returned Tensor · level recorded 2026-09-22
BaseMethod in 6 papers geossl/simclr.py unverified MIT (permissive) · db566f0014cc2980 · report
giakou4/pyfeats community (archive-listed) 12 samples, 8 ran (0 instrument-failed) · 4 unverified
amfm_features pyfeats/multiscale/amfm.py ran fingerprinted MIT (permissive) · 3a7dd916ad6f6389 · report fixture: signature f:ndarray/2/float, bins:int/0/int · returned tuple · level recorded 2026-09-24
fdta pyfeats/multiscale/fdta.py ran MIT (permissive) · 07fd42842d206009 · report fixture: signature f:ndarray/2/float, mask:ndarray/2/float, s:int/0/int · returned tuple · level recorded 2026-09-24
grayscale_morphology_features pyfeats/morphological/grayscale_morphological_analysis.py ran MIT (permissive) · bcbf650b774f3bab · report fixture: signature f:ndarray/2/int, N:int/0/int · returned tuple · level recorded 2026-09-24
histogram in 7 papers pyfeats/histogram/histogram.py ran fingerprinted MIT (permissive) · a89e539d4a1fa3b2 · report fixture: signature f:ndarray/2/int, mask:ndarray/2/int, bins:int/0/int · returned tuple · level recorded 2026-09-24
multilevel_binary_morphology_features pyfeats/morphological/multilevel_binary_morphological_analysis.py ran MIT (permissive) · d3385cd7eed6a6f2 · report fixture: signature img:ndarray/2/int, mask:ndarray/2/int, N:int/0/int, thresholds:list/1/int · returned tuple · level recorded 2026-09-24
multiregion_histogram pyfeats/histogram/multiregion_histogram.py ran MIT (permissive) · 191b9a33cbd317cc · report fixture: signature f:ndarray/2/int, mask:ndarray/2/int, bins:int/0/int, num_eros:int/0/int, square_size:int/0/int · returned tuple · level recorded 2026-09-24
pad_image in 27 papers pyfeats/utilities.py ran MIT (permissive) · 98c1de629745feab · report fixture: signature f:ndarray/2/int, pad:int/0/int, fill_val:int/0/int · returned ndarray · level recorded 2026-09-24
wp_features pyfeats/multiscale/wp.py ran MIT (permissive) · b00d9ebb0254cfd3 · report fixture: signature f:ndarray/2/float, mask:ndarray/2/float, wavelet:str/0/str, maxlevel:int/0/int · returned tuple · level recorded 2026-09-24
correlogram pyfeats/histogram/correlogram.py unverified MIT (permissive) · ddf47684b8425901 · report
dwt_features pyfeats/multiscale/dwt.py unverified MIT (permissive) · 634317f9c741abd3 · report
gt_features pyfeats/multiscale/gt.py unverified MIT (permissive) · 9e33b14b41b316ca · report
swt_features pyfeats/multiscale/swt.py unverified MIT (permissive) · b81f9f44d8624e5f · report
giakou4/pyssl community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
Projector in 18 papers builders/simclr.py ran · metamorphic tier: deterministic MIT (permissive) · 626ad09af14b9cab · report fixture: returned Projector · level recorded 2026-09-22
SimCLR builders/simclr.py ran · metamorphic tier: deterministic MIT (permissive) · bf78992ef15b4628 · report fixture: returned SimCLR · level recorded 2026-09-22
nt_xent_loss builders/simclr.py ran · our draft was wrong fingerprinted MIT (permissive) · a3786294fb65e90e · report fixture: signature z1:Tensor/2/float, z2:Tensor/2/float, temperature:float/0/float · returned Tensor · level recorded 2026-09-22
nzw0301/simclr community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
NT_Xent in 8 papers loss.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · bc1d652d78503f98 · report fixture: returned NT_Xent · level recorded 2026-09-22
sthalles/SimCLR community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · b0f936d4d6ae3b8c · report fixture: signature output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int · returned list · level recorded, date not recorded

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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". 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. Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

48 assemblies on this paper: 47 harvested, 1 generated, listed in 2 groups (siblings lifted in one batch form one group).

generated Assembly for SimCLR (graph method: SimCLR), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer; level 3 is recorded, but its report lists no property test that passed on both.

label matches by construction: the code was generated for this method (not judged by a model)

  1. simclr_loss entry · level 3 · ran · violated contract · bd6ca4b121e2a4fad7498fea2fa28a5556396ac0fd8a2c7be9442d322334b04e

47 sibling assemblies for SimCLR (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 47 sibling assemblies; the other 35 are listed with their counts; every brick is in this page's JSON twin.

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

one of 47 siblings

  1. NT_Xent entry · level 1 · ran · f10b64ecf0f39804

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

one of 47 siblings

  1. SimCLR entry · level 1 · ran · e78d903f294bb8e2

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

one of 47 siblings

  1. SimCLR entry · level 1 · ran · bf78992ef15b4628
  2. Projector model · level 1 · ran · 626ad09af14b9cab
  3. nt_xent_loss loss · level 1 · ran · our draft was wrong · a3786294fb65e90e

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

one of 47 siblings

  1. SimCLR entry · level 0 · unverified · ff90bea0467c6b51

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

one of 47 siblings

  1. ContLoss entry · level 1 · ran · 5ad08dec1ed71937

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

one of 47 siblings

  1. get_contrastive_loss entry · level 1 · ran · our draft was wrong · 6181cfb7ba78942e

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

one of 47 siblings

  1. _adapt_resnet_model entry · level 1 · ran · our draft was wrong · 50709c4ec879ecc5

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

one of 47 siblings

  1. ImageSSLModels entry · level 1 · ran · 0a6342453ea2f75f
  2. SSLModel model · level 1 · ran · 54df182d9c00588a
  3. get_base_model helper · level 1 · ran · our draft was wrong · 8c4252f18f2e14a8

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

one of 47 siblings

  1. add_contrastive_loss entry · level 1 · ran · our draft was wrong · c418940b96d1fe9e
  2. tpu_cross_replica_concat helper · level 1 · ran · our draft was wrong · 7aac0de5d1568953

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

one of 47 siblings

  1. SupConLoss entry · level 1 · ran · 19bb24ecb5d473db

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

one of 47 siblings

  1. ResNetSimCLR entry · level 1 · ran · 40a653c6651fc5d4

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

one of 47 siblings

  1. NT_Xent entry · level 1 · ran · bc1d652d78503f98
  1. NTXentLoss · 48a983511b9b9b9c · 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[13] in the JSON twin
  2. SimCLR · 4caf88d9e34c4edc · 2 bricks; individually on a fixture: 2 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; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
  3. ContrastiveEncoder · 4d2df1c65b119a04 · 8 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) · 3 unverified · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
  4. build_simclr_model · 5428a3ad40871e82 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[16] in the JSON twin
  5. SimCLR · 5f5c075c0a317967 · 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[17] in the JSON twin
  6. NTXenLoss · 656d1538022d3718 · 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[18] in the JSON twin
  7. SimCLRMain · 696d255ac12a77cd · 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 · assemblies[19] in the JSON twin
  8. SupConLoss · 697afa14625c58d0 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[20] in the JSON twin
  9. SimCLR · 6d39813a40105290 · 4 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) · 2 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[21] in the JSON twin
  10. NTXent · 6e54fd938dd66934 · 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[22] in the JSON twin
  11. SimCLR · 7b60a2ca76165415 · 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[23] in the JSON twin
  12. SimCLR · 85e48cff362a360a · 5 bricks; individually on a fixture: 4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[24] in the JSON twin
  13. SimCLR · 88ae33c968440e57 · 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[25] in the JSON twin
  14. add_contrastive_loss · 88da07f5d29302af · 2 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[26] in the JSON twin
  15. SupConLoss · 89b433376fa3b4ec · 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[27] in the JSON twin
  16. SimCLR · 9ec0ec2c075ac5b4 · 2 bricks; individually on a fixture: 2 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; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[28] in the JSON twin
  17. add_contrastive_loss · 9f3fee0bf5354ab3 · 2 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[29] in the JSON twin
  18. SimCLR · aed31e8f9eeb48be · 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[30] in the JSON twin
  19. SimCLR · b2648be997c2fbfa · 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[31] in the JSON twin
  20. SimCLR · b3941522b138022e · 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[32] in the JSON twin
  21. ResNet · b4dcef0b1c665570 · 5 bricks; individually on a fixture: 4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[33] in the JSON twin
  22. contrastive_loss · be413eda7ac547e7 · 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[34] in the JSON twin
  23. randaugment · cde16c5182d2bf9a · 3 bricks; individually on a fixture: 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 · The assembly has not been run end-to-end · assemblies[35] in the JSON twin
  24. ContrastiveHead · d0f8533448215672 · 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[36] in the JSON twin
  25. SupConLoss · d2c26a141843614c · 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[37] in the JSON twin
  26. SimCLR · d67b3821e7f8d3be · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[38] in the JSON twin
  27. get_color_distortion · dc61815833e07512 · 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[39] in the JSON twin
  28. SimLoss · dd2d576d819a0c8f · 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[40] in the JSON twin
  29. SupConLoss · dff330bf79231cb8 · 3 bricks; individually on a fixture: 3 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; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[41] in the JSON twin
  30. Res18 · e03feaef42f6994d · 4 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) · 0 unverified · The assembly has not been run end-to-end · assemblies[42] in the JSON twin
  31. SIMCLR · e79b9aa097970146 · 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[43] in the JSON twin
  32. SimCLRLoss · e8606e5170a73918 · 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[44] in the JSON twin
  33. NTXent · e97fce06bde54ff2 · 3 bricks; individually on a fixture: 3 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; 2 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[45] in the JSON twin
  34. Contrastive · ea3062505390324d · 8 bricks; individually on a fixture: 4 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; 4 where Syntology's instrument failed) · 4 unverified · The assembly has not been run end-to-end · assemblies[46] in the JSON twin
  35. SimCLR · fc1efec3485b2ac0 · 4 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) · 3 unverified · The assembly has not been run end-to-end · assemblies[47] 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="2002.05709") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Contrastive LearningImage ClassificationObject RecognitionPerson Re-IdentificationSelf-Supervised Image ClassificationSelf-Supervised LearningSelf-Supervised Person Re-IdentificationSemi-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Contrastive Learning imagenet-1k ResNet50 ImageNet Top-1 Accuracy 69.3 #4 of 14 Archive leaderboard report
Image Classification Places205 SimCLR Top 1 Accuracy 53.3 #13 of 15 Archive leaderboard report
Object Recognition shape bias SimCLR (ResNet-50x2) shape bias 41.7 #12 of 18 Archive leaderboard report
Object Recognition shape bias SimCLR (ResNet-50x4) shape bias 40.7 #13 of 18 Archive leaderboard report
Object Recognition shape bias SimCLR (ResNet-50x1) shape bias 38.9 #14 of 18 Archive leaderboard report
Person Re-Identification SYSU-30k SimCLR (self-supervised) Rank-1 10.9 #8 of 10 Archive leaderboard report
Self-Supervised Image Classification ImageNet SimCLR (ResNet-50 4x) Number of Params 375M #60 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SimCLR (ResNet-50 4x) Top 1 Accuracy 76.5% #60 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SimCLR (ResNet-50 4x) Top 5 Accuracy 93.2% #60 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SimCLR (ResNet-50 2x) Number of Params 94M #86 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SimCLR (ResNet-50 2x) Top 1 Accuracy 74.2% #86 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SimCLR (ResNet-50 2x) Top 5 Accuracy 92.0% #86 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SimCLR (ResNet-50) Number of Params 24M #103 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SimCLR (ResNet-50) Top 1 Accuracy 69.3% #103 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SimCLR (ResNet-50) Top 5 Accuracy 89.0% #103 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) SimCLR (Resnet-50) Top 1 Accuracy 77.2% #63 of 65 Archive leaderboard report
Self-Supervised Person Re-Identification SYSU-30k SimCLR Rank-1 10.9 #4 of 4 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data SimCLR (ResNet-50 4×) Top 1 Accuracy 63.0% #33 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data SimCLR (ResNet-50 4×) Top 5 Accuracy 85.8% #33 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data SimCLR (ResNet-50 2×) Top 1 Accuracy 58.5% #40 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data SimCLR (ResNet-50 2×) Top 5 Accuracy 83.0% #40 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data SimCLR (ResNet-50) Top 1 Accuracy 48.3% #52 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data SimCLR (ResNet-50) Top 5 Accuracy 75.5% #52 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data SimCLR (ResNet-50 4×) Top 5 Accuracy 92.6% #48 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data SimCLR (ResNet-50 2×) Top 5 Accuracy 91.2% #50 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data SimCLR (ResNet-50) Top 5 Accuracy 87.8% #56 of 75 Archive leaderboard report

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

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockColorJitterConvolutionDense ConnectionsFeedforward NetworkGlobal Average PoolingKaiming InitializationLARSLinear Warmup With Linear DecayMax PoolingNT-XentRandom Gaussian BlurRandom Resized CropReLUResidual BlockResidual ConnectionSimCLRWeight Decay

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