{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/a-simple-framework-for-contrastive-learning","title":"A Simple Framework for Contrastive Learning of Visual Representations","arxiv_id":"2002.05709","date":"2020-02-13","proceeding":"ICML 2020 1","authors":["Ting Chen","Simon Kornblith","Mohammad Norouzi","Geoffrey Hinton"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2002.05709v3","url_pdf":"https://arxiv.org/pdf/2002.05709v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/google-research/simclr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/63days/SimCLR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/AidenDurrant/MoCo-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/AndrewAtanov/simclr-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/BalajiAI/SimCLR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/Daniel-H-99/SimCLR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/HobbitLong/SupContrast","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/JoonHyung-Park/SimCLR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/Liut2016/ecg-supcontrast","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/Mind23-2/MindCode-76","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/SaeedShurrab/SimSiam-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/Westlake-AI/openmixup","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/XG293/SupConLoss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/acholston/SimCLR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/ae-foster/pytorch-simclr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/alexk1704/scclv2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/anonymousmlsubmission/datadistributiontransfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/applecrumble123/SimCLR_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/asd08573064/SimCLR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/beresandras/contrastive-classification-keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/bjader/QSSL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/brainimageanalysis/marmosetgeneatlas_adult","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/caesarea38/doclangid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/chingyaoc/DCL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/cjrd/self-supervised-pretraining","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/clabrugere/pytorch-scarf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/cyrilvallez/image-manipulation-detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/danielzgsilva/MOT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/davidczy/supcon_gamma","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/delyan-boychev/grad-cache-con-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/dewenzeng/clsp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/edreismd/convirt-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/edureisMD/ConVIRT-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/eminorhan/baby-vision","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/facebookresearch/vissl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/filipbasara0/matryoshka-representation-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/forcesh/SupContrast","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/guerbet-ai/wsp-contrastive","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/hannaiiyanggit/unicon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/hemakaraveenhansika/convirt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/htdt/self-supervised","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/john-mlr/CIFAR-10-SimCLR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/jramapuram/SimCLR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/jwcalder/GraphLearningLayer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/kawshik8/DL-project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/krafton-ai/mini-batch-cl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/leftthomas/SimCLR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/lightly-ai/lightly","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/liuch37/image-processing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/mandiehyewon/goodviews_ecg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/mariaauslander/capstone_fall20_irrigation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/mdiephuis/simclr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/ninatu/mood_challenge","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/open-mmlab/mmselfsup","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/optimization-ai/sogclr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/p3i0t/simclr-cifar10","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/parkinkon1/simclr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/phanav/simclr-presentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/radiradev/contrastive-neutrino","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/rahimentezari/datadistributiontransferlearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/rajatkoner08/oodformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/rdbch/simclr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/rdbch/tutorial_simclr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/reppy4620/SimCLR4Paint","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/rmastand/jetclr_ad","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/roydenwa/cell-centroid-former","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/salarim/Semi-Supervised-CL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/sayakpaul/SimCLR-in-TensorFlow-2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/serre-lab/prj_selfsup","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/sidwa/ae_thesis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/spijkervet/simclr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/ssumin6/SimCLR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/sunjesse/SimCLR_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/sylviesss/pytorch-simclr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/ta9ryuWalrus/simclr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/talipucar/PyFlow_SimCLR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/thunderInfy/simclr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/ushmabhatt/Contrastive-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/ut-vision/simhand","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/vturrisi/solo-learn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/wilile26811249/SimCLR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/wvangansbeke/Unsupervised-Classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/yoojungsun0/Psych239","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/zpf0117b/CLMB","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/simclr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/2023-MindSpore-4/Code11/tree/main/simclr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/Mayurji/SimCLR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/Pangoraw/GeoSSL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/alibaba/EasyCV","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/code-implementation1/Code8/tree/main/simclr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/giakou4/pyfeats","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/giakou4/pyssl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/mindspore-ai/models/tree/master/official/cv/simclr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/nzw0301/simclr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/sthalles/SimCLR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-simple-framework-for-contrastive-learning","repo_url":"https://github.com/tensorflow/models/tree/master/official/vision/beta/projects/simclr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"self-supervised-image-classification","task_name":"Self-Supervised Image Classification"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"self-supervised-person-re-identification","task_name":"Self-Supervised Person Re-Identification"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"colorjitter","method_name":"ColorJitter"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"lars","method_name":"LARS"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"nt-xent","method_name":"NT-Xent"},{"method_slug":"random-gaussian-blur","method_name":"Random Gaussian Blur"},{"method_slug":"random-resized-crop","method_name":"Random Resized Crop"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"simclr","method_name":"SimCLR"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/contrastive-learning-on-imagenet-1k","task":"Contrastive Learning","dataset":"imagenet-1k","model":"ResNet50","rank_in_archive_order":4,"of":14,"metrics":{"ImageNet Top-1 Accuracy":"69.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-places205","task":"Image Classification","dataset":"Places205","model":"SimCLR","rank_in_archive_order":13,"of":15,"metrics":{"Top 1 Accuracy":"53.3"},"uses_additional_data":false},{"leaderboard":"/sota/object-recognition-on-shape-bias","task":"Object Recognition","dataset":"shape bias","model":"SimCLR (ResNet-50x2)","rank_in_archive_order":12,"of":18,"metrics":{"shape bias":"41.7"},"uses_additional_data":false},{"leaderboard":"/sota/object-recognition-on-shape-bias","task":"Object Recognition","dataset":"shape bias","model":"SimCLR (ResNet-50x4)","rank_in_archive_order":13,"of":18,"metrics":{"shape bias":"40.7"},"uses_additional_data":false},{"leaderboard":"/sota/object-recognition-on-shape-bias","task":"Object Recognition","dataset":"shape bias","model":"SimCLR (ResNet-50x1)","rank_in_archive_order":14,"of":18,"metrics":{"shape bias":"38.9"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-sysu-30k","task":"Person Re-Identification","dataset":"SYSU-30k","model":"SimCLR (self-supervised)","rank_in_archive_order":8,"of":10,"metrics":{" Rank-1":"10.9"},"uses_additional_data":true},{"leaderboard":"/sota/self-supervised-image-classification-on","task":"Self-Supervised Image Classification","dataset":"ImageNet","model":"SimCLR (ResNet-50 4x)","rank_in_archive_order":60,"of":144,"metrics":{"Number of Params":"375M","Top 1 Accuracy":"76.5%","Top 5 Accuracy":"93.2%"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-image-classification-on","task":"Self-Supervised Image Classification","dataset":"ImageNet","model":"SimCLR (ResNet-50 2x)","rank_in_archive_order":86,"of":144,"metrics":{"Number of Params":"94M","Top 1 Accuracy":"74.2%","Top 5 Accuracy":"92.0%"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-image-classification-on","task":"Self-Supervised Image Classification","dataset":"ImageNet","model":"SimCLR (ResNet-50)","rank_in_archive_order":103,"of":144,"metrics":{"Number of Params":"24M","Top 1 Accuracy":"69.3%","Top 5 Accuracy":"89.0%"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-image-classification-on-1","task":"Self-Supervised Image Classification","dataset":"ImageNet (finetuned)","model":"SimCLR (Resnet-50)","rank_in_archive_order":63,"of":65,"metrics":{"Top 1 Accuracy":"77.2%"},"uses_additional_data":true},{"leaderboard":"/sota/self-supervised-person-re-identification-on","task":"Self-Supervised Person Re-Identification","dataset":"SYSU-30k","model":"SimCLR","rank_in_archive_order":4,"of":4,"metrics":{" Rank-1":"10.9"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-1","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 1% labeled data","model":"SimCLR (ResNet-50 4×)","rank_in_archive_order":33,"of":65,"metrics":{"Top 1 Accuracy":"63.0%","Top 5 Accuracy":"85.8%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-1","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 1% labeled data","model":"SimCLR (ResNet-50 2×)","rank_in_archive_order":40,"of":65,"metrics":{"Top 1 Accuracy":"58.5%","Top 5 Accuracy":"83.0%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-1","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 1% labeled data","model":"SimCLR (ResNet-50)","rank_in_archive_order":52,"of":65,"metrics":{"Top 1 Accuracy":"48.3%","Top 5 Accuracy":"75.5%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-2","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 10% labeled data","model":"SimCLR (ResNet-50 4×)","rank_in_archive_order":48,"of":75,"metrics":{"Top 5 Accuracy":"92.6%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-2","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 10% labeled data","model":"SimCLR (ResNet-50 2×)","rank_in_archive_order":50,"of":75,"metrics":{"Top 5 Accuracy":"91.2%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-2","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 10% labeled data","model":"SimCLR (ResNet-50)","rank_in_archive_order":56,"of":75,"metrics":{"Top 5 Accuracy":"87.8%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2002.05709","atlas_url":"https://app.syntology.ai/?focus=2002.05709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.05709"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2002.05709"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_reference_implementation","arguments":{"name":"SimCLR"},"call":"get_reference_implementation(name='SimCLR')","min_level":{"quoted_from_server_card":["It REFUSES rather than serving below min_level, and the refusal names the highest level that exists","so lowering min_level is a deliberate, informed choice, not a guess."],"default_on_card":2,"server_card":"https://syntology.ai/.well-known/mcp/server-card.json","card_sha256":"479785a84658dd682a11b10237b3620d651d7f87799f5dc7add970aaa83f6d39","this_implementation_level":3}},{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2002.05709"},"call":"get_harvested_code_for_paper(arxiv_id=\"2002.05709\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2002.05709"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2002.05709\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2002.05709"},"call":"get_concepts_for_paper(arxiv_id=\"2002.05709\")"}],"reference_implementation":[{"method_name":"SimCLR","assembly_sha256":"d09eee09a4beef39","source":"generated from the paper text (not the authors' code)","level":3,"level_is_quoted_from_server_card":[{"level":"V2","quoted":["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)"]},{"level":"V3","quoted":["paper-derived property tests pass on both of those same two generations."]}],"server_card":"https://syntology.ai/.well-known/mcp/server-card.json","card_sha256":"479785a84658dd682a11b10237b3620d651d7f87799f5dc7add970aaa83f6d39","v3_tests_passed_both_sides":0,"level_3_note":"level 3 is recorded, but its report lists no property test that passed on both","no_rung":"No rung compares this code against the authors' implementation","no_rung_quoted_from_server_card":"No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.","retrieve_with":"get_reference_implementation(name='SimCLR')","have_check":{"url":"https://syntology.ai/api/graph/have?x=2002.05709","call":"have('2002.05709')","in_build_sample":true,"answer_agreed":true}}],"reference_implementation_is":"Syntology's reference implementation of this paper's method: code Syntology generated from the paper text (not the authors' code), at the level its own end-to-end run recorded (the assembly's own level, never averaged); the level's meaning is quoted from Syntology's server card, and nothing here says the code is correct or reproduces the paper's results","by_repo":[{"repo":"google-research/simclr","kind":"official","samples":2,"ran":2,"instrument":2,"unverified":0},{"repo":"63days/SimCLR","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"AidenDurrant/MoCo-Pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1911.05722"],"harvested_for_calls":[{"arxiv_id":"1911.05722","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1911.05722"},"call":"get_harvested_code_for_paper(arxiv_id=\"1911.05722\")"}]},{"repo":"AndrewAtanov/simclr-pytorch","kind":"listed","samples":13,"ran":11,"instrument":0,"unverified":2},{"repo":"BalajiAI/SimCLR","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Daniel-H-99/SimCLR","kind":"listed","samples":4,"ran":4,"instrument":0,"unverified":0},{"repo":"HobbitLong/SupContrast","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2311.01196"],"harvested_for_calls":[{"arxiv_id":"2311.01196","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2311.01196"},"call":"get_harvested_code_for_paper(arxiv_id=\"2311.01196\")"}]},{"repo":"JoonHyung-Park/SimCLR","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Liut2016/ecg-supcontrast","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"Mind23-2/MindCode-76","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"SaeedShurrab/SimSiam-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Westlake-AI/openmixup","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["1710.09412","1712.09913","1905.04899","2312.11954"],"harvested_for_calls":[{"arxiv_id":"1710.09412","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1710.09412"},"call":"get_harvested_code_for_paper(arxiv_id=\"1710.09412\")"},{"arxiv_id":"1712.09913","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1712.09913"},"call":"get_harvested_code_for_paper(arxiv_id=\"1712.09913\")"},{"arxiv_id":"1905.04899","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1905.04899"},"call":"get_harvested_code_for_paper(arxiv_id=\"1905.04899\")"},{"arxiv_id":"2312.11954","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2312.11954"},"call":"get_harvested_code_for_paper(arxiv_id=\"2312.11954\")"}]},{"repo":"XG293/SupConLoss","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2004.11362"],"harvested_for_calls":[{"arxiv_id":"2004.11362","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2004.11362"},"call":"get_harvested_code_for_paper(arxiv_id=\"2004.11362\")"}]},{"repo":"acholston/SimCLR","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"ae-foster/pytorch-simclr","kind":"listed","samples":6,"ran":6,"instrument":0,"unverified":0},{"repo":"alexk1704/scclv2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2004.11362"],"harvested_for_calls":[{"arxiv_id":"2004.11362","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2004.11362"},"call":"get_harvested_code_for_paper(arxiv_id=\"2004.11362\")"}]},{"repo":"anonymousmlsubmission/datadistributiontransfer","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2302.13602"],"harvested_for_calls":[{"arxiv_id":"2302.13602","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2302.13602"},"call":"get_harvested_code_for_paper(arxiv_id=\"2302.13602\")"}]},{"repo":"applecrumble123/SimCLR_pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"asd08573064/SimCLR","kind":"listed","samples":2,"ran":2,"instrument":0,"unverified":0},{"repo":"beresandras/contrastive-classification-keras","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"bjader/QSSL","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"brainimageanalysis/marmosetgeneatlas_adult","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"caesarea38/doclangid","kind":"listed","samples":3,"ran":3,"instrument":3,"unverified":0},{"repo":"chingyaoc/DCL","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2007.00224"],"harvested_for_calls":[{"arxiv_id":"2007.00224","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2007.00224"},"call":"get_harvested_code_for_paper(arxiv_id=\"2007.00224\")"}]},{"repo":"cjrd/self-supervised-pretraining","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2103.12718"],"harvested_for_calls":[{"arxiv_id":"2103.12718","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2103.12718"},"call":"get_harvested_code_for_paper(arxiv_id=\"2103.12718\")"}]},{"repo":"clabrugere/pytorch-scarf","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"cyrilvallez/image-manipulation-detection","kind":"listed","samples":2,"ran":1,"instrument":0,"unverified":1},{"repo":"danielzgsilva/MOT","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"davidczy/supcon_gamma","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2004.11362"],"harvested_for_calls":[{"arxiv_id":"2004.11362","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2004.11362"},"call":"get_harvested_code_for_paper(arxiv_id=\"2004.11362\")"}]},{"repo":"delyan-boychev/grad-cache-con-learning","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"dewenzeng/clsp","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"edreismd/convirt-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"edureisMD/ConVIRT-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"eminorhan/baby-vision","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2007.16189"],"harvested_for_calls":[{"arxiv_id":"2007.16189","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2007.16189"},"call":"get_harvested_code_for_paper(arxiv_id=\"2007.16189\")"}]},{"repo":"facebookresearch/vissl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["1603.09246","1803.07728","2106.08254","2202.07603"],"harvested_for_calls":[{"arxiv_id":"1603.09246","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1603.09246"},"call":"get_harvested_code_for_paper(arxiv_id=\"1603.09246\")"},{"arxiv_id":"1803.07728","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1803.07728"},"call":"get_harvested_code_for_paper(arxiv_id=\"1803.07728\")"},{"arxiv_id":"2106.08254","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.08254"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.08254\")"},{"arxiv_id":"2202.07603","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2202.07603"},"call":"get_harvested_code_for_paper(arxiv_id=\"2202.07603\")"}]},{"repo":"filipbasara0/matryoshka-representation-learning","kind":"listed","samples":1,"ran":1,"instrument":1,"unverified":0},{"repo":"forcesh/SupContrast","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"guerbet-ai/wsp-contrastive","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"hannaiiyanggit/unicon","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"hemakaraveenhansika/convirt","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"htdt/self-supervised","kind":"listed","samples":2,"ran":1,"instrument":1,"unverified":1},{"repo":"john-mlr/CIFAR-10-SimCLR","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"jramapuram/SimCLR","kind":"listed","samples":3,"ran":3,"instrument":2,"unverified":0},{"repo":"jwcalder/GraphLearningLayer","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"kawshik8/DL-project","kind":"listed","samples":3,"ran":3,"instrument":1,"unverified":0},{"repo":"krafton-ai/mini-batch-cl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1708.03888"],"harvested_for_calls":[{"arxiv_id":"1708.03888","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1708.03888"},"call":"get_harvested_code_for_paper(arxiv_id=\"1708.03888\")"}]},{"repo":"leftthomas/SimCLR","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"lightly-ai/lightly","kind":"listed","samples":2,"ran":2,"instrument":0,"unverified":0},{"repo":"liuch37/image-processing","kind":"listed","samples":1,"ran":1,"instrument":1,"unverified":0},{"repo":"mandiehyewon/goodviews_ecg","kind":"listed","samples":1,"ran":1,"instrument":1,"unverified":0},{"repo":"mariaauslander/capstone_fall20_irrigation","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"mdiephuis/simclr","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"ninatu/mood_challenge","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2006.13265"],"harvested_for_calls":[{"arxiv_id":"2006.13265","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.13265"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.13265\")"}]},{"repo":"open-mmlab/mmselfsup","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2303.02416"],"harvested_for_calls":[{"arxiv_id":"2303.02416","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2303.02416"},"call":"get_harvested_code_for_paper(arxiv_id=\"2303.02416\")"}]},{"repo":"optimization-ai/sogclr","kind":"listed","samples":2,"ran":2,"instrument":0,"unverified":0},{"repo":"p3i0t/simclr-cifar10","kind":"listed","samples":3,"ran":3,"instrument":1,"unverified":0},{"repo":"parkinkon1/simclr","kind":"listed","samples":1,"ran":1,"instrument":1,"unverified":0},{"repo":"phanav/simclr-presentation","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"radiradev/contrastive-neutrino","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"rahimentezari/datadistributiontransferlearning","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"rajatkoner08/oodformer","kind":"listed","samples":3,"ran":3,"instrument":1,"unverified":0,"placed_by_identical_code":1},{"repo":"rdbch/simclr","kind":"listed","samples":4,"ran":2,"instrument":0,"unverified":2},{"repo":"rdbch/tutorial_simclr","kind":"listed","samples":2,"ran":2,"instrument":0,"unverified":0},{"repo":"reppy4620/SimCLR4Paint","kind":"listed","samples":2,"ran":2,"instrument":0,"unverified":0},{"repo":"rmastand/jetclr_ad","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2108.04253"],"harvested_for_calls":[{"arxiv_id":"2108.04253","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2108.04253"},"call":"get_harvested_code_for_paper(arxiv_id=\"2108.04253\")"}]},{"repo":"roydenwa/cell-centroid-former","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"salarim/Semi-Supervised-CL","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sayakpaul/SimCLR-in-TensorFlow-2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"serre-lab/prj_selfsup","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2006.10029"],"harvested_for_calls":[{"arxiv_id":"2006.10029","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.10029"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.10029\")"}]},{"repo":"sidwa/ae_thesis","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"spijkervet/simclr","kind":"listed","samples":4,"ran":4,"instrument":3,"unverified":0},{"repo":"ssumin6/SimCLR","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"sunjesse/SimCLR_pytorch","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"sylviesss/pytorch-simclr","kind":"listed","samples":5,"ran":5,"instrument":0,"unverified":0},{"repo":"ta9ryuWalrus/simclr","kind":"listed","samples":2,"ran":2,"instrument":2,"unverified":0},{"repo":"talipucar/PyFlow_SimCLR","kind":"listed","samples":8,"ran":5,"instrument":1,"unverified":3},{"repo":"thunderInfy/simclr","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"ushmabhatt/Contrastive-Learning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ut-vision/simhand","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2502.15251"],"harvested_for_calls":[{"arxiv_id":"2502.15251","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2502.15251"},"call":"get_harvested_code_for_paper(arxiv_id=\"2502.15251\")"}]},{"repo":"vturrisi/solo-learn","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":3,"harvested_for":["2003.04297","2007.06346","2107.09282"],"harvested_for_calls":[{"arxiv_id":"2003.04297","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2003.04297"},"call":"get_harvested_code_for_paper(arxiv_id=\"2003.04297\")"},{"arxiv_id":"2007.06346","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2007.06346"},"call":"get_harvested_code_for_paper(arxiv_id=\"2007.06346\")"},{"arxiv_id":"2107.09282","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2107.09282"},"call":"get_harvested_code_for_paper(arxiv_id=\"2107.09282\")"}]},{"repo":"wilile26811249/SimCLR","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"wvangansbeke/Unsupervised-Classification","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"yoojungsun0/Psych239","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"zpf0117b/CLMB","kind":"listed","samples":9,"ran":9,"instrument":1,"unverified":0},{"repo":"2023-MindSpore-1/ms-code-216","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"2023-MindSpore-4/Code11","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Mayurji/SimCLR","kind":"listed","samples":2,"ran":0,"instrument":0,"unverified":2},{"repo":"Pangoraw/GeoSSL","kind":"listed","samples":5,"ran":4,"instrument":2,"unverified":1},{"repo":"alibaba/EasyCV","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["2005.12872","2012.12877","2111.06377","2203.01305"],"harvested_for_calls":[{"arxiv_id":"2005.12872","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2005.12872"},"call":"get_harvested_code_for_paper(arxiv_id=\"2005.12872\")"},{"arxiv_id":"2012.12877","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2012.12877"},"call":"get_harvested_code_for_paper(arxiv_id=\"2012.12877\")"},{"arxiv_id":"2111.06377","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2111.06377"},"call":"get_harvested_code_for_paper(arxiv_id=\"2111.06377\")"},{"arxiv_id":"2203.01305","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2203.01305"},"call":"get_harvested_code_for_paper(arxiv_id=\"2203.01305\")"}]},{"repo":"code-implementation1/Code8","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"giakou4/pyfeats","kind":"listed","samples":12,"ran":8,"instrument":0,"unverified":4},{"repo":"giakou4/pyssl","kind":"listed","samples":3,"ran":3,"instrument":1,"unverified":0},{"repo":"mindspore-ai/models","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2208.08084"],"harvested_for_calls":[{"arxiv_id":"2208.08084","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2208.08084"},"call":"get_harvested_code_for_paper(arxiv_id=\"2208.08084\")"}]},{"repo":"nzw0301/simclr","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"sthalles/SimCLR","kind":"listed","samples":1,"ran":1,"instrument":1,"unverified":0},{"repo":"tensorflow/models","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["1502.03167","1512.03385","1605.07146","1704.04861"],"harvested_for_calls":[{"arxiv_id":"1502.03167","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1502.03167"},"call":"get_harvested_code_for_paper(arxiv_id=\"1502.03167\")"},{"arxiv_id":"1512.03385","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1512.03385"},"call":"get_harvested_code_for_paper(arxiv_id=\"1512.03385\")"},{"arxiv_id":"1605.07146","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1605.07146"},"call":"get_harvested_code_for_paper(arxiv_id=\"1605.07146\")"},{"arxiv_id":"1704.04861","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1704.04861"},"call":"get_harvested_code_for_paper(arxiv_id=\"1704.04861\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","assemblies":[{"assembly_sha256":"d09eee09a4beef39","source_kind":"generated","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"Compute the SimCLR contrastive loss given projection vectors z and temperature tau.\n\nInputs:\n- z: numpy array of shape (2N, D) where N is the batch size and D is the projection dimension. Rows are indexed from 0 to 2N-1. For each k in {1, ..., N} (1-indexed), row 2k-2 (0-indexed: 2k-2) and row 2k-1","centrality":"contribution","entry":"simclr_loss","entry_sha256":"bd6ca4b121e2a4fad7498fea2fa28a5556396ac0fd8a2c7be9442d322334b04e","n_bricks":1,"bricks":[{"entry":"simclr_loss","code_sha256":"bd6ca4b121e2a4fad7498fea2fa28a5556396ac0fd8a2c7be9442d322334b04e","role":"entry","order":0,"level":3,"status":"ran_violates"}],"ran_individually":1,"ran_individually_constructed":null,"ran_individually_by_status":{"ran_violates":1},"end_to_end":{"ran":true,"level":3,"against_independent_peer":true,"n_peers":1,"v3_tests_passed_both_sides":0,"means":"this assembly is a single routine, so the entry brick's verification IS the assembly's: it executed and two family-independent implementations agreed"},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"construction","claim_match_judges":["construction:spec_drafted_for_this_method"],"label_verdict":"matches","label_verdict_judged":false,"suggested_method":null,"batch_at":"2026-09-07T20:44:12+00:00","sibling_group":"95abe61e23cd","n_siblings":0,"retention":"keep","provenance":"assembly:generated_reference_impl_v1","attached_at":"2026-09-07T20:44:12+00:00","attached_provenance":"assembly:generated_reference_impl_v1"},{"assembly_sha256":"04aed1f100903a54","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"This code implements the contrastive loss function used in SimCLR, which is central to the paper's proposed self-supervised learning framework.","centrality":"contribution","entry":"NT_Xent","entry_sha256":"f10b64ecf0f39804","n_bricks":1,"bricks":[{"entry":"NT_Xent","code_sha256":"f10b64ecf0f39804","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"0cd7905d79dc0cdf","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"This code implements the SimCLR framework for contrastive learning of visual representations, as proposed in the paper.","centrality":"contribution","entry":"SimCLR","entry_sha256":"e78d903f294bb8e2","n_bricks":1,"bricks":[{"entry":"SimCLR","code_sha256":"e78d903f294bb8e2","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"0eabeef9b9e6247f","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The paper claims this code implements SimCLR, a simple framework for contrastive learning of visual representations without specialized architectures or memory banks.","centrality":"contribution","entry":"SimCLR","entry_sha256":"bf78992ef15b4628","n_bricks":3,"bricks":[{"entry":"SimCLR","code_sha256":"bf78992ef15b4628","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Projector","code_sha256":"626ad09af14b9cab","role":"model","order":1,"level":1,"status":"ran"},{"entry":"nt_xent_loss","code_sha256":"a3786294fb65e90e","role":"loss","order":2,"level":1,"status":"ran_draft_wrong"}],"ran_individually":3,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2,"ran_draft_wrong":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"12e6376d9893bc45","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The paper claims this code implements SimCLR, a simple framework for contrastive learning of visual representations without specialized architectures or memory banks.","centrality":"contribution","entry":"SimCLR","entry_sha256":"ff90bea0467c6b51","n_bricks":1,"bricks":[{"entry":"SimCLR","code_sha256":"ff90bea0467c6b51","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"15d012c928c3242e","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"This code implements the contrastive loss function central to SimCLR, which computes similarity between augmented views of the same image while repelling views from different images.","centrality":"contribution","entry":"ContLoss","entry_sha256":"5ad08dec1ed71937","n_bricks":1,"bricks":[{"entry":"ContLoss","code_sha256":"5ad08dec1ed71937","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"164e68de34508825","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"This function implements the contrastive loss mechanism central to SimCLR, which computes cosine similarity between normalized feature representations of augmented data samples.","centrality":"contribution","entry":"get_contrastive_loss","entry_sha256":"6181cfb7ba78942e","n_bricks":1,"bricks":[{"entry":"get_contrastive_loss","code_sha256":"6181cfb7ba78942e","role":"entry","order":0,"level":1,"status":"ran_draft_wrong"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_draft_wrong":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"23915b44a7f840f5","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The code adapts a ResNet model for contrastive learning by modifying the first convolutional layer and removing the max pooling layer, as specified in the SimCLR paper.","centrality":"component","entry":"_adapt_resnet_model","entry_sha256":"50709c4ec879ecc5","n_bricks":1,"bricks":[{"entry":"_adapt_resnet_model","code_sha256":"50709c4ec879ecc5","role":"entry","order":0,"level":1,"status":"ran_draft_wrong"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_draft_wrong":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"COMPONENT","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"cannot_tell","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"259a0062a8a00072","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The code implements a simple framework for contrastive learning of visual representations without requiring specialized architectures or a memory bank, as proposed in SimCLR.","centrality":"contribution","entry":"ImageSSLModels","entry_sha256":"0a6342453ea2f75f","n_bricks":3,"bricks":[{"entry":"ImageSSLModels","code_sha256":"0a6342453ea2f75f","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"SSLModel","code_sha256":"54df182d9c00588a","role":"model","order":1,"level":1,"status":"ran"},{"entry":"get_base_model","code_sha256":"8c4252f18f2e14a8","role":"helper","order":2,"level":1,"status":"ran_draft_wrong"}],"ran_individually":3,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2,"ran_draft_wrong":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"2a3cea1c471f8bde","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"This function implements the contrastive loss computation central to the SimCLR method, which learns visual representations by maximizing agreement between differently augmented views of the same data example.","centrality":"contribution","entry":"add_contrastive_loss","entry_sha256":"c418940b96d1fe9e","n_bricks":2,"bricks":[{"entry":"add_contrastive_loss","code_sha256":"c418940b96d1fe9e","role":"entry","order":0,"level":1,"status":"ran_draft_wrong"},{"entry":"tpu_cross_replica_concat","code_sha256":"7aac0de5d1568953","role":"helper","order":1,"level":1,"status":"ran_draft_wrong"}],"ran_individually":2,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_draft_wrong":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"2b8c3cfa2149a0d1","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The paper claims this code implements SimCLR, a simple framework for contrastive learning of visual representations without specialized architectures or memory banks.","centrality":"contribution","entry":"SupConLoss","entry_sha256":"19bb24ecb5d473db","n_bricks":1,"bricks":[{"entry":"SupConLoss","code_sha256":"19bb24ecb5d473db","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"2d5a56adfbf4984e","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"This code implements the SimCLR framework's core model architecture, which uses a ResNet-50 backbone with its final fully connected layer replaced by an identity layer to produce visual representations for contrastive learning.","centrality":"contribution","entry":"ResNetSimCLR","entry_sha256":"40a653c6651fc5d4","n_bricks":1,"bricks":[{"entry":"ResNetSimCLR","code_sha256":"40a653c6651fc5d4","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"407f0dcb8b8761f9","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"This code implements the normalized temperature-scaled cross entropy loss, which is the core contrastive loss function proposed in SimCLR for learning visual representations.","centrality":"contribution","entry":"NT_Xent","entry_sha256":"bc1d652d78503f98","n_bricks":1,"bricks":[{"entry":"NT_Xent","code_sha256":"bc1d652d78503f98","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"48a983511b9b9b9c","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The paper claims this code implements the normalized temperature-scaled cross-entropy loss (NT-Xent) used in SimCLR for contrastive learning of visual representations.","centrality":"contribution","entry":"NTXentLoss","entry_sha256":"f3d9092135724cbd","n_bricks":1,"bricks":[{"entry":"NTXentLoss","code_sha256":"f3d9092135724cbd","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"4caf88d9e34c4edc","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"This class implements the SimCLR framework for contrastive learning of visual representations using an encoder and projection head.","centrality":"contribution","entry":"SimCLR","entry_sha256":"99b66383d6cd5bf7","n_bricks":2,"bricks":[{"entry":"SimCLR","code_sha256":"99b66383d6cd5bf7","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Identity","code_sha256":"c6c6288219c9d532","role":"helper","order":1,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"4d2df1c65b119a04","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The paper claims SimCLR implements a contrastive learning framework using a CNN-based encoder and NT-Xent loss to learn visual representations without specialized architectures or memory banks.","centrality":"contribution","entry":"ContrastiveEncoder","entry_sha256":"f5ffc1cae804d1f7","n_bricks":8,"bricks":[{"entry":"ContrastiveEncoder","code_sha256":"f5ffc1cae804d1f7","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"CNNEncoder","code_sha256":"0736b9b372d39725","role":"model","order":1,"level":1,"status":"ran"},{"entry":"NTXentLoss","code_sha256":"93679e35512cbdb7","role":"loss","order":2,"level":1,"status":"ran"},{"entry":"ResNet","code_sha256":"c541394f43fa9adc","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"save_loss_plot","code_sha256":"75b95f2eaa47b97b","role":"helper","order":4,"level":0,"status":"unverified"},{"entry":"set_seed","code_sha256":"20855bdedf943b8f","role":"helper","order":5,"level":0,"status":"unverified"},{"entry":"global_ave_pool","code_sha256":"6940670c59bb0cda","role":"helper","order":6,"level":1,"status":"ran_draft_wrong"},{"entry":"Identity","code_sha256":"b77efc36f9b77b9b","role":"helper","order":7,"level":1,"status":"ran"}],"ran_individually":5,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":4,"ran_draft_wrong":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"5428a3ad40871e82","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The paper claims this code implements SimCLR, a simple framework for contrastive learning of visual representations using a neural encoder and projection head without specialized architectures or memory banks.","centrality":"contribution","entry":"build_simclr_model","entry_sha256":"bb4e645996e12174","n_bricks":1,"bricks":[{"entry":"build_simclr_model","code_sha256":"bb4e645996e12174","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"5f5c075c0a317967","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"This code implements SimCLR, a simple framework for contrastive learning of visual representations using a contrastive loss without specialized architectures or memory banks.","centrality":"contribution","entry":"SimCLR","entry_sha256":"2c196dbc33af1e86","n_bricks":1,"bricks":[{"entry":"SimCLR","code_sha256":"2c196dbc33af1e86","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"656d1538022d3718","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The paper claims this code implements the normalized temperature-scaled cross-entropy loss for contrastive learning of visual representations, as proposed in SimCLR.","centrality":"contribution","entry":"NTXenLoss","entry_sha256":"4fa18a92d2d6193b","n_bricks":1,"bricks":[{"entry":"NTXenLoss","code_sha256":"4fa18a92d2d6193b","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"696d255ac12a77cd","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The paper claims this code implements SimCLR, a simple framework for contrastive learning of visual representations without specialized architectures or memory banks.","centrality":"contribution","entry":"SimCLRMain","entry_sha256":"3ac7ccd797e47c29","n_bricks":5,"bricks":[{"entry":"SimCLRMain","code_sha256":"3ac7ccd797e47c29","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Dropout","code_sha256":"43ca37aec47363d7","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"ResnetEncoder","code_sha256":"15c470cde64303bb","role":"model","order":2,"level":1,"status":"ran"},{"entry":"ResnetEncoderDropout","code_sha256":"5069ef275d4321a2","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"DropoutNd","code_sha256":"3cb087a414dec282","role":"helper","order":4,"level":1,"status":"ran"}],"ran_individually":5,"ran_individually_constructed":5,"ran_individually_by_status":{"ran":5},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"697afa14625c58d0","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The paper claims this code implements the SimCLR contrastive learning framework for visual representations","centrality":"contribution","entry":"SupConLoss","entry_sha256":"0e2efd6b67f01d69","n_bricks":1,"bricks":[{"entry":"SupConLoss","code_sha256":"0e2efd6b67f01d69","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"COMPONENT","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"cannot_tell","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"6d39813a40105290","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The paper claims this code implements SimCLR, a simple framework for contrastive learning of visual representations using an encoder and projector network without specialized architectures or memory banks.","centrality":"contribution","entry":"SimCLR","entry_sha256":"04a16872e7176429","n_bricks":4,"bricks":[{"entry":"SimCLR","code_sha256":"04a16872e7176429","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Configurable","code_sha256":"7fd8c4e94eb9d6f4","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"MLP","code_sha256":"2a061ea2756788d0","role":"helper","order":2,"level":1,"status":"ran"},{"entry":"ResNet","code_sha256":"8ae8bb52d6e02325","role":"model","order":3,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"6e54fd938dd66934","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"This code implements the NT-Xent loss function for contrastive learning, which is a key component of the SimCLR method proposed in the paper.","centrality":"contribution","entry":"NTXent","entry_sha256":"249ded5d814fb1fd","n_bricks":1,"bricks":[{"entry":"NTXent","code_sha256":"249ded5d814fb1fd","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"COMPONENT","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"cannot_tell","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"7b60a2ca76165415","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The code implements SimCLR, a simple framework for contrastive learning of visual representations using a projection head and contrastive loss without specialized architectures or memory banks.","centrality":"contribution","entry":"SimCLR","entry_sha256":"dccd7194c3fa9092","n_bricks":3,"bricks":[{"entry":"SimCLR","code_sha256":"dccd7194c3fa9092","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"SimCLRProjectionHead","code_sha256":"2d22ec7eee6353ce","role":"model","order":1,"level":1,"status":"ran"},{"entry":"ProjectionHead","code_sha256":"da76a8285671b345","role":"helper","order":2,"level":1,"status":"ran"}],"ran_individually":3,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"85e48cff362a360a","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"An implementation of a simple framework for contrastive learning of visual representations using a pairwise normalized temperature scaled cross entropy loss (NT-Xent).","centrality":"contribution","entry":"SimCLR","entry_sha256":"965480d2c18b15a7","n_bricks":5,"bricks":[{"entry":"SimCLR","code_sha256":"965480d2c18b15a7","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"BaseMethod","code_sha256":"db566f0014cc2980","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"ResNetBackbone","code_sha256":"7339ae06662b97a5","role":"model","order":2,"level":1,"status":"ran"},{"entry":"nt_xent","code_sha256":"56d873a0ee406a9d","role":"loss","order":3,"level":1,"status":"ran_draft_wrong"},{"entry":"_get_weights_url","code_sha256":"589ff9232fa952cc","role":"helper","order":4,"level":1,"status":"ran_draft_wrong"}],"ran_individually":4,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2,"ran_draft_wrong":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"88ae33c968440e57","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The paper claims this code implements a contrastive learning framework that learns visual representations by maximizing agreement between differently augmented views of the same image.","centrality":"contribution","entry":"SimCLR","entry_sha256":"db46cc53970a4db1","n_bricks":1,"bricks":[{"entry":"SimCLR","code_sha256":"db46cc53970a4db1","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"88da07f5d29302af","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"This code implements the SimCLR contrastive learning loss function, which computes the contrastive loss between augmented views of images to learn visual representations.","centrality":"contribution","entry":"add_contrastive_loss","entry_sha256":"92885c7117af82c9","n_bricks":2,"bricks":[{"entry":"add_contrastive_loss","code_sha256":"92885c7117af82c9","role":"entry","order":0,"level":1,"status":"ran_fixture"},{"entry":"tpu_cross_replica_concat","code_sha256":"5ef56dc923793fb3","role":"helper","order":1,"level":1,"status":"ran_draft_wrong"}],"ran_individually":2,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_draft_wrong":1,"ran_fixture":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"89b433376fa3b4ec","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"This code implements a supervised contrastive learning loss that also supports the unsupervised contrastive loss used in SimCLR.","centrality":"contribution","entry":"SupConLoss","entry_sha256":"a5dbd9a427e2bec3","n_bricks":1,"bricks":[{"entry":"SupConLoss","code_sha256":"a5dbd9a427e2bec3","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"9ec0ec2c075ac5b4","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The paper claims this is the simple framework for contrastive learning of visual representations without requiring specialized architectures or a memory bank.","centrality":"contribution","entry":"SimCLR","entry_sha256":"4c7f0882280707e1","n_bricks":2,"bricks":[{"entry":"SimCLR","code_sha256":"4c7f0882280707e1","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Flatten","code_sha256":"c6673456e63337b4","role":"helper","order":1,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"9f3fee0bf5354ab3","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"This function implements the contrastive loss central to the SimCLR method, computing the loss for visual representation learning by comparing augmented views of images.","centrality":"contribution","entry":"add_contrastive_loss","entry_sha256":"8924ee1d1cde05c4","n_bricks":2,"bricks":[{"entry":"add_contrastive_loss","code_sha256":"8924ee1d1cde05c4","role":"entry","order":0,"level":1,"status":"ran_draft_wrong"},{"entry":"tpu_cross_replica_concat","code_sha256":"7aac0de5d1568953","role":"helper","order":1,"level":1,"status":"ran_draft_wrong"}],"ran_individually":2,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_draft_wrong":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"aed31e8f9eeb48be","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The paper claims this code implements SimCLR, a simple framework for contrastive learning of visual representations using a base encoder and projection MLPs without specialized architectures or memory banks.","centrality":"contribution","entry":"SimCLR","entry_sha256":"b4045ab6673c8148","n_bricks":3,"bricks":[{"entry":"SimCLR","code_sha256":"b4045ab6673c8148","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"all_gather_layer","code_sha256":"8e2cdb7569401c95","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"concat_all_gather","code_sha256":"73cecca9f3575f09","role":"helper","order":2,"level":0,"status":"unverified"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"b2648be997c2fbfa","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The paper claims this code implements SimCLR, a simple framework for contrastive learning of visual representations without specialized architectures or memory banks.","centrality":"contribution","entry":"SimCLR","entry_sha256":"4578ef90ebbe26cd","n_bricks":1,"bricks":[{"entry":"SimCLR","code_sha256":"4578ef90ebbe26cd","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"b3941522b138022e","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The paper claims that SimCLR is a simple framework for contrastive learning of visual representations without requiring specialized architectures or a memory bank.","centrality":"contribution","entry":"SimCLR","entry_sha256":"f81649524890dfe5","n_bricks":2,"bricks":[{"entry":"SimCLR","code_sha256":"f81649524890dfe5","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ContrastiveModel","code_sha256":"acc020a5fafd0a3c","role":"helper","order":1,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"b4dcef0b1c665570","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"This code implements a ResNet-based architecture for contrastive learning of visual representations, specifically SimCLR's backbone network.","centrality":"contribution","entry":"ResNet","entry_sha256":"ea2c3cf94bcdfef3","n_bricks":5,"bricks":[{"entry":"ResNet","code_sha256":"ea2c3cf94bcdfef3","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"BasicBlock","code_sha256":"6994af792574c2ac","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Bottleneck","code_sha256":"e6a9a9260ef0a74a","role":"model","order":2,"level":1,"status":"ran"},{"entry":"conv1x1","code_sha256":"d9def42110729a85","role":"helper","order":3,"level":1,"status":"ran_draft_wrong"},{"entry":"conv3x3","code_sha256":"160bb14bd76201b4","role":"helper","order":4,"level":1,"status":"ran_draft_wrong"}],"ran_individually":4,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2,"ran_draft_wrong":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"COMPONENT","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"cannot_tell","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"be413eda7ac547e7","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"This code implements the contrastive loss function central to SimCLR, which learns visual representations by maximizing agreement between differently augmented views of the same image.","centrality":"contribution","entry":"contrastive_loss","entry_sha256":"eb14839e65ee11cf","n_bricks":1,"bricks":[{"entry":"contrastive_loss","code_sha256":"eb14839e65ee11cf","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"cde16c5182d2bf9a","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The code implements a data augmentation strategy for contrastive learning of visual representations, specifically applying random transformations to generate varied views of images.","centrality":"component","entry":"randaugment","entry_sha256":"5b8da074d51c8e00","n_bricks":3,"bricks":[{"entry":"randaugment","code_sha256":"5b8da074d51c8e00","role":"entry","order":0,"level":1,"status":"ran_draft_wrong"},{"entry":"apply_op","code_sha256":"0809a27fc54eb733","role":"data_transform","order":1,"level":1,"status":"ran_fixture"},{"entry":"generate_op_meta","code_sha256":"b621a5344f937d5e","role":"data_transform","order":2,"level":1,"status":"ran_draft_wrong"}],"ran_individually":3,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_draft_wrong":2,"ran_fixture":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"COMPONENT","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"cannot_tell","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"d0f8533448215672","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The paper claims this code implements SimCLR, a simple framework for contrastive learning of visual representations using a contrastive loss on augmented image pairs.","centrality":"contribution","entry":"ContrastiveHead","entry_sha256":"7d227e358ec14382","n_bricks":1,"bricks":[{"entry":"ContrastiveHead","code_sha256":"7d227e358ec14382","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"d2c26a141843614c","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"This code implements a supervised contrastive loss that also supports the unsupervised contrastive loss used in SimCLR.","centrality":"contribution","entry":"SupConLoss","entry_sha256":"d8d1dd0aafb92f18","n_bricks":1,"bricks":[{"entry":"SupConLoss","code_sha256":"d8d1dd0aafb92f18","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"d67b3821e7f8d3be","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The code implements SimCLR, a simple framework for contrastive learning of visual representations without specialized architectures or memory banks.","centrality":"contribution","entry":"SimCLR","entry_sha256":"708baa8232f99ac8","n_bricks":1,"bricks":[{"entry":"SimCLR","code_sha256":"708baa8232f99ac8","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"dc61815833e07512","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"This code implements a color distortion transformation as part of SimCLR's data augmentation pipeline for contrastive learning of visual representations.","centrality":"component","entry":"get_color_distortion","entry_sha256":"0adaf15a01b00920","n_bricks":1,"bricks":[{"entry":"get_color_distortion","code_sha256":"0adaf15a01b00920","role":"entry","order":0,"level":1,"status":"ran_draft_wrong"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_draft_wrong":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"COMPONENT","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"cannot_tell","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"dd2d576d819a0c8f","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"SimCLR is a simple framework for contrastive learning of visual representations without requiring specialized architectures or a memory bank.","centrality":"component","entry":"SimLoss","entry_sha256":"00e45e65ec60a85c","n_bricks":1,"bricks":[{"entry":"SimLoss","code_sha256":"00e45e65ec60a85c","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"COMPONENT","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"cannot_tell","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"dff330bf79231cb8","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"This code implements a supervised contrastive loss that also supports the unsupervised contrastive loss used in SimCLR.","centrality":"contribution","entry":"SupConLoss","entry_sha256":"1d1a1df3f3426c17","n_bricks":3,"bricks":[{"entry":"SupConLoss","code_sha256":"1d1a1df3f3426c17","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"euclidean_dist","code_sha256":"57bbb1c2ae467a4f","role":"helper","order":1,"level":1,"status":"ran_honours"},{"entry":"mahalanobis","code_sha256":"ae6df0014dbc55c9","role":"helper","order":2,"level":1,"status":"ran_draft_wrong"}],"ran_individually":3,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":1,"ran_draft_wrong":1,"ran_honours":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"e03feaef42f6994d","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"This code implements a ResNet-18 backbone architecture used as the encoder in the SimCLR framework for contrastive learning of visual representations.","centrality":"component","entry":"Res18","entry_sha256":"2f6dc2d5f30f106e","n_bricks":4,"bricks":[{"entry":"Res18","code_sha256":"2f6dc2d5f30f106e","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Res18ConvLayer","code_sha256":"24e7779cb2a243e3","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Res18Block","code_sha256":"8556399cf0e482d3","role":"model","order":2,"level":1,"status":"ran"},{"entry":"ShortCut","code_sha256":"b27ce753d440a134","role":"helper","order":3,"level":1,"status":"ran"}],"ran_individually":4,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":4},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"COMPONENT","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"cannot_tell","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"e79b9aa097970146","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The paper claims this code implements SimCLR, a simple framework for contrastive learning of visual representations without requiring specialized architectures or a memory bank.","centrality":"contribution","entry":"SIMCLR","entry_sha256":"f33e37ad81b7d344","n_bricks":1,"bricks":[{"entry":"SIMCLR","code_sha256":"f33e37ad81b7d344","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"e8606e5170a73918","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The paper claims this code implements a contrastive loss function for learning visual representations without specialized architectures or memory banks, central to the SimCLR framework.","centrality":"contribution","entry":"SimCLRLoss","entry_sha256":"6db2a02555c7f204","n_bricks":1,"bricks":[{"entry":"SimCLRLoss","code_sha256":"6db2a02555c7f204","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"e97fce06bde54ff2","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"This code implements the SimCLR contrastive learning loss (NT-Xent) as proposed in the paper, which is the core method for training visual representations without specialized architectures or memory banks.","centrality":"contribution","entry":"NTXent","entry_sha256":"dec5ae5526431e69","n_bricks":3,"bricks":[{"entry":"NTXent","code_sha256":"dec5ae5526431e69","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"all_gather","code_sha256":"2b5d65dc96c1a03b","role":"helper","order":1,"level":1,"status":"ran_draft_wrong"},{"entry":"l2_normalize","code_sha256":"6325cd34bc332e95","role":"helper","order":2,"level":1,"status":"ran_draft_wrong"}],"ran_individually":3,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":1,"ran_draft_wrong":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"ea3062505390324d","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"This code implements the SimCLR contrastive learning framework, which simplifies contrastive self-supervised learning by using a projection head and contrastive loss without specialized architectures or memory banks.","centrality":"contribution","entry":"Contrastive","entry_sha256":"d1deb5d7410ae0b7","n_bricks":8,"bricks":[{"entry":"Contrastive","code_sha256":"d1deb5d7410ae0b7","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"BaseMethod","code_sha256":"641188dbe3eb2b34","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"contrastive_loss","code_sha256":"ba00312b3d5b70dc","role":"loss","order":2,"level":1,"status":"ran_fixture"},{"entry":"eval_knn","code_sha256":"2ed1c82b5ad2ee9f","role":"helper","order":3,"level":1,"status":"ran_draft_wrong"},{"entry":"eval_sgd","code_sha256":"371021e6723e9c29","role":"helper","order":4,"level":0,"status":"unverified"},{"entry":"get_data","code_sha256":"ceeec13af255b5bc","role":"helper","order":5,"level":1,"status":"ran_fixture"},{"entry":"get_head","code_sha256":"2d19f4f3143c2ccf","role":"model","order":6,"level":1,"status":"ran_draft_wrong"},{"entry":"get_model","code_sha256":"1d4261306685f800","role":"helper","order":7,"level":0,"status":"unverified"}],"ran_individually":4,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_draft_wrong":2,"ran_fixture":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"fc1efec3485b2ac0","source_kind":"harvested","method_name":"SimCLR","realizes_method":"SimCLR","graph_method":"SimCLR","realizes_severed":false,"claim":"The paper claims this code implements SimCLR, a simple framework for contrastive learning of visual representations without specialized architectures or memory banks.","centrality":"contribution","entry":"SimCLR","entry_sha256":"aea60f5692813252","n_bricks":4,"bricks":[{"entry":"SimCLR","code_sha256":"aea60f5692813252","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"accuracy","code_sha256":"b0f936d4d6ae3b8c","role":"helper","order":1,"level":1,"status":"ran_fixture"},{"entry":"save_checkpoint","code_sha256":"7e7b54ff38780a53","role":"helper","order":2,"level":0,"status":"unverified"},{"entry":"save_config_file","code_sha256":"97f82d2378647866","role":"helper","order":3,"level":0,"status":"unverified"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_fixture":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4b2dc4c22f76","n_siblings":46,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"}],"assembly_sibling_groups":[{"group":"4b2dc4c22f76","realizes_method":"SimCLR","source_kind":"harvested","batch_at":"2026-09-09T22:44:46+00:00","members":["04aed1f100903a54","0cd7905d79dc0cdf","0eabeef9b9e6247f","12e6376d9893bc45","15d012c928c3242e","164e68de34508825","23915b44a7f840f5","259a0062a8a00072","2a3cea1c471f8bde","2b8c3cfa2149a0d1","2d5a56adfbf4984e","407f0dcb8b8761f9","48a983511b9b9b9c","4caf88d9e34c4edc","4d2df1c65b119a04","5428a3ad40871e82","5f5c075c0a317967","656d1538022d3718","696d255ac12a77cd","697afa14625c58d0","6d39813a40105290","6e54fd938dd66934","7b60a2ca76165415","85e48cff362a360a","88ae33c968440e57","88da07f5d29302af","89b433376fa3b4ec","9ec0ec2c075ac5b4","9f3fee0bf5354ab3","aed31e8f9eeb48be","b2648be997c2fbfa","b3941522b138022e","b4dcef0b1c665570","be413eda7ac547e7","cde16c5182d2bf9a","d0f8533448215672","d2c26a141843614c","d67b3821e7f8d3be","dc61815833e07512","dd2d576d819a0c8f","dff330bf79231cb8","e03feaef42f6994d","e79b9aa097970146","e8606e5170a73918","e97fce06bde54ff2","ea3062505390324d","fc1efec3485b2ac0"]},{"group":"95abe61e23cd","realizes_method":"SimCLR","source_kind":"generated","batch_at":"2026-09-07T20:44:12+00:00","members":["d09eee09a4beef39"]}],"assemblies_is":{"about":"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.","harvested":"assembled from code harvested from a repository linked to the paper","generated":"generated from the paper text, not the repository's code","end_to_end":"for a harvested assembly, the assembly has not been run end-to-end; for a generated one, end_to_end.level is the assembly's own level and against_independent_peer says whether it ran against a peer: 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","bricks_level":"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_individually":"a COUNT of bricks that ran on their own on a fixture (split by status in ran_individually_by_status), not a level; instrument statuses are failures of Syntology's instrument, not of the code","siblings":"assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another","judged":"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\"","level_lowered":"a generated assembly whose level Syntology's graph lowered, with the level it had, the recorded reason and when","retention":"Syntology's spending triage for further verification, not a verdict","claim_match":"the claim_match vote: IMPLEMENTS, COMPONENT or UNCLEAR. Where claim_match_basis is \"judge:<model>\", it is one model's judgement of the assembly's label against the paper's claim (claim_match_rule single_judge, the model in claim_match_judges): not a verification and not a run. Where it is \"construction\", the value was set when the code was generated for this method and no model judged it, whatever claim_match_rule says. The page prints no claim match for any assembly","label_verdict":"whether the assembly's code is the method it is labelled with: matches, cannot_tell, mislabelled (suggested_method names what it looks like instead) or not_the_method; label_verdict_judged is true only when a model read the code (claim_match_basis \"judge:<model>\")","label_verdict_judged":"where true (claim_match_basis \"judge:<model>\"), label_verdict is a single model's judgement; not calibrated; not printed on the page; where false, it was set by construction, and the page prints it unless the node is shared with another paper (node_properties_written_for)","claim":"the claim text stored on the assembly node: for a harvested assembly, what the paper claims the code implements, as the lifting model wrote it; for a generated one, the specification the code was generated from. Not verified text","centrality":"how central the lifted method is to the paper, as the lifting step recorded it: contribution, component or incidental","v3_tests_passed_both_sides":"end_to_end.v3_tests_passed_both_sides: the number of property tests derived from the paper that passed on both implementations, as the attached report lists them; a level 3 card with 0 says its report lists none","ran_individually_constructed":"ran_individually_constructed: of the bricks counted in ran_individually, how many constructed an object rather than computing a result (Syntology's RAN record's rule, read from the graph-layer sample with the brick's code_sha256); a part of ran_individually, never subtracted from it and never a failure; null where a brick that ran has no sample in the graph layer this build read, so the figure was not counted"},"assemblies_call":{"tool":"assembly","arguments":{"arxiv_id":"2002.05709"},"call":"assembly(arxiv_id=\"2002.05709\")"},"read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2002.05709.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2002.05709.svg"},"claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/google-research/simclr","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/leftthomas/SimCLR","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Westlake-AI/openmixup","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/vissl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HobbitLong/SupContrast","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/clabrugere/pytorch-scarf","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hannaiiyanggit/unicon","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sidwa/ae_thesis","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alexk1704/scclv2","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JoonHyung-Park/SimCLR","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/acholston/SimCLR","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/delyan-boychev/grad-cache-con-learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jramapuram/SimCLR","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Pangoraw/GeoSSL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/giakou4/pyssl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dewenzeng/clsp","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mayurji/SimCLR","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AidenDurrant/MoCo-Pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cjrd/self-supervised-pretraining","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wvangansbeke/Unsupervised-Classification","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sylviesss/pytorch-simclr","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rajatkoner08/oodformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eminorhan/baby-vision","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/phanav/simclr-presentation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/XG293/SupConLoss","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"summary":{"ran_violates":1,"ran":87,"ran_draft_wrong":21,"ran_fixture":5,"ran_honours":1,"unverified":22},"n_samples":137,"n_ran":115,"n_constructed":33,"n_ran_checked":89,"n_instrument":26,"n_unverified":22,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":2,"ran":2,"n_ran_checked":0,"n_instrument":2,"repositories":1},"listed":{"samples":135,"ran":113,"n_ran_checked":89,"n_instrument":24,"repositories":54}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":52,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"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_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing","signature_not_shown":"the graph records a signature for this sample and it is not shown; signature_not_shown_because names why, as the export's field-exclusion reason","signature_not_shown_because":{"signature_is_harness_probe_not_fixture_args":"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"}},"n_ran_with_level_date":109,"n_ran_without_level_date":6,"n_ran_signature_not_shown":18,"levels_written_between":{"first":"2026-09-22","last":"2026-09-25","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","census_is":"Syntology's function-name census ran implementations with this entry name on one shared input per bucket (the positional rank, kind and dtype of each array argument) and counted the distinct output digests (sha256 of the output rounded to 6 decimals). implementations and papers count the compared samples; distinct_outputs counts digests across all buckets; n_buckets is how many shared inputs were used. It is not a statement that any two samples compute one thing, and the name is a string, not an identity.","samples":[{"code_sha256":"190117b425ab9fe1","code_sha256_prefix":"190117b425ab9fe1","entry":"get_lr","repo":"p3i0t/SimCLR-CIFAR10","repo_kind":"listed","path":"simclr.py","file_url":"https://github.com/p3i0t/SimCLR-CIFAR10/blob/HEAD/simclr.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"signature":"step:int/0/int, total_steps:int/0/int, lr_max:float/0/float, lr_min:float/0/float","fixture_out_type":"float64","retrieve_with":{"tool":"get_code","code_sha256":"190117b425ab9fe1"},"code_page":"/code/get-lr","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, p3i0t/SimCLR-CIFAR10 when it was checked","mcp_get_code":{"code_sha256":"190117b425ab9fe1"}},{"code_sha256":"7937263b7909ba06","code_sha256_prefix":"7937263b7909ba06","entry":"BlurOrSharpen","repo":"ae-foster/pytorch-simclr","repo_kind":"listed","path":"augmentation.py","file_url":"https://github.com/ae-foster/pytorch-simclr/blob/HEAD/augmentation.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"radius:float/0/float","fixture_out_type":"RandomApply","level_recorded_at":"2026-09-24T22:55:07.240920+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7937263b7909ba06"}},{"code_sha256":"e6a9a9260ef0a74a","code_sha256_prefix":"e6a9a9260ef0a74a","entry":"Bottleneck","repo":"cyrilvallez/image-manipulation-detection","repo_kind":"listed","path":"hashing/SimCLRv1/resnet_wider.py","file_url":"https://github.com/cyrilvallez/image-manipulation-detection/blob/HEAD/hashing/SimCLRv1/resnet_wider.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Bottleneck","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/bottleneck","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e6a9a9260ef0a74a"}},{"code_sha256":"0736b9b372d39725","code_sha256_prefix":"0736b9b372d39725","entry":"CNNEncoder","repo":"talipucar/PyFlow_SimCLR","repo_kind":"listed","path":"src/model.py","file_url":"https://github.com/talipucar/PyFlow_SimCLR/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"x:Tensor/4/float","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"0736b9b372d39725"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, talipucar/PyFlow_SimCLR when it was checked","mcp_get_code":{"code_sha256":"0736b9b372d39725"}},{"code_sha256":"d05210f656c96fc4","code_sha256_prefix":"d05210f656c96fc4","entry":"ColourDistortion","repo":"ae-foster/pytorch-simclr","repo_kind":"listed","path":"augmentation.py","file_url":"https://github.com/ae-foster/pytorch-simclr/blob/HEAD/augmentation.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"s:float/0/float","fixture_out_type":"Compose","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d05210f656c96fc4"}},{"code_sha256":"5ad08dec1ed71937","code_sha256_prefix":"5ad08dec1ed71937","entry":"ContLoss","repo":"acholston/SimCLR","repo_kind":"listed","path":"loss.py","file_url":"https://github.com/acholston/SimCLR/blob/HEAD/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"ContLoss","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"5ad08dec1ed71937"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, acholston/SimCLR when it was checked","mcp_get_code":{"code_sha256":"5ad08dec1ed71937"}},{"code_sha256":"7d227e358ec14382","code_sha256_prefix":"7d227e358ec14382","entry":"ContrastiveHead","repo":"dewenzeng/clsp","repo_kind":"listed","path":"models/resnet_sk.py","file_url":"https://github.com/dewenzeng/clsp/blob/HEAD/models/resnet_sk.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"x:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"7d227e358ec14382"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dewenzeng/clsp when it was checked","mcp_get_code":{"code_sha256":"7d227e358ec14382"}},{"code_sha256":"43ca37aec47363d7","code_sha256_prefix":"43ca37aec47363d7","entry":"Dropout","repo":"sylviesss/pytorch-simclr","repo_kind":"listed","path":"models/simclr.py","file_url":"https://github.com/sylviesss/pytorch-simclr/blob/HEAD/models/simclr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Dropout","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"43ca37aec47363d7"},"code_page":"/code/dropout-2","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, sylviesss/pytorch-simclr when it was checked","mcp_get_code":{"code_sha256":"43ca37aec47363d7"}},{"code_sha256":"3cb087a414dec282","code_sha256_prefix":"3cb087a414dec282","entry":"DropoutNd","repo":"sylviesss/pytorch-simclr","repo_kind":"listed","path":"models/simclr.py","file_url":"https://github.com/sylviesss/pytorch-simclr/blob/HEAD/models/simclr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"DropoutNd","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/dropoutnd","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, sylviesss/pytorch-simclr when it was checked","mcp_get_code":{"code_sha256":"3cb087a414dec282"}},{"code_sha256":"c6673456e63337b4","code_sha256_prefix":"c6673456e63337b4","entry":"Flatten","repo":"reppy4620/SimCLR4Paint","repo_kind":"listed","path":"modules/simclr.py","file_url":"https://github.com/reppy4620/SimCLR4Paint/blob/HEAD/modules/simclr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"x:Tensor/4/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"c6673456e63337b4"},"code_page":"/code/flatten-2","census":{"url":"/census/flatten","implementations":9,"papers":9,"distinct_outputs":2,"n_buckets":2,"bucket_key":[[4,"float","float32"]],"bucket_index":1,"bucket_label":"arg 1: rank 4, kind float, dtype float32"},"census_bucket_fragment":"bucket-1","licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, reppy4620/SimCLR4Paint when it was checked","mcp_get_code":{"code_sha256":"c6673456e63337b4"}},{"code_sha256":"b77efc36f9b77b9b","code_sha256_prefix":"b77efc36f9b77b9b","entry":"Identity","repo":"talipucar/PyFlow_SimCLR","repo_kind":"listed","path":"src/model.py","file_url":"https://github.com/talipucar/PyFlow_SimCLR/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Identity","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"b77efc36f9b77b9b"},"code_page":"/code/identity-2","census":{"url":"/census/identity-2","implementations":10,"papers":13,"distinct_outputs":4,"n_buckets":4,"bucket_key":null,"bucket_index":null,"bucket_label":null},"census_bucket_fragment":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, talipucar/PyFlow_SimCLR when it was checked","mcp_get_code":{"code_sha256":"b77efc36f9b77b9b"}},{"code_sha256":"0a6342453ea2f75f","code_sha256_prefix":"0a6342453ea2f75f","entry":"ImageSSLModels","repo":"kawshik8/DL-project","repo_kind":"listed","path":"src/SSLmodels.py","file_url":"https://github.com/kawshik8/DL-project/blob/HEAD/src/SSLmodels.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"ImageSSLModels","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, kawshik8/DL-project when it was checked","mcp_get_code":{"code_sha256":"0a6342453ea2f75f"}},{"code_sha256":"2a061ea2756788d0","code_sha256_prefix":"2a061ea2756788d0","entry":"MLP","repo":"rdbch/simclr","repo_kind":"listed","path":"core/networks/simclr.py","file_url":"https://github.com/rdbch/simclr/blob/HEAD/core/networks/simclr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"MLP","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/mlp","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2a061ea2756788d0"}},{"code_sha256":"4fa18a92d2d6193b","code_sha256_prefix":"4fa18a92d2d6193b","entry":"NTXenLoss","repo":"guerbet-ai/wsp-contrastive","repo_kind":"listed","path":"losses.py","file_url":"https://github.com/guerbet-ai/wsp-contrastive/blob/HEAD/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"NTXenLoss","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"4fa18a92d2d6193b"},"code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, guerbet-ai/wsp-contrastive (NOASSERTION)","mcp_get_code":{"code_sha256":"4fa18a92d2d6193b"}},{"code_sha256":"249ded5d814fb1fd","code_sha256_prefix":"249ded5d814fb1fd","entry":"NTXent","repo":"clabrugere/pytorch-scarf","repo_kind":"listed","path":"scarf/loss.py","file_url":"https://github.com/clabrugere/pytorch-scarf/blob/HEAD/scarf/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"NTXent","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"249ded5d814fb1fd"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"249ded5d814fb1fd"}},{"code_sha256":"dec5ae5526431e69","code_sha256_prefix":"dec5ae5526431e69","entry":"NTXent","repo":"jramapuram/SimCLR","repo_kind":"listed","path":"objective.py","file_url":"https://github.com/jramapuram/SimCLR/blob/HEAD/objective.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"embedding1:Tensor/2/float, embedding2:Tensor/2/float, temperature:float/0/float, num_replicas:int/0/int","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"dec5ae5526431e69"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"dec5ae5526431e69"}},{"code_sha256":"f3d9092135724cbd","code_sha256_prefix":"f3d9092135724cbd","entry":"NTXentLoss","repo":"hemakaraveenhansika/convirt","repo_kind":"listed","path":"loss/nt_xent.py","file_url":"https://github.com/hemakaraveenhansika/convirt/blob/HEAD/loss/nt_xent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"NTXentLoss","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"f3d9092135724cbd"},"code_page":"/code/ntxentloss","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f3d9092135724cbd"}},{"code_sha256":"93679e35512cbdb7","code_sha256_prefix":"93679e35512cbdb7","entry":"NTXentLoss","repo":"talipucar/PyFlow_SimCLR","repo_kind":"listed","path":"src/model.py","file_url":"https://github.com/talipucar/PyFlow_SimCLR/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"NTXentLoss","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/ntxentloss","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, talipucar/PyFlow_SimCLR when it was checked","mcp_get_code":{"code_sha256":"93679e35512cbdb7"}},{"code_sha256":"f10b64ecf0f39804","code_sha256_prefix":"f10b64ecf0f39804","entry":"NT_Xent","repo":"john-mlr/CIFAR-10-SimCLR","repo_kind":"listed","path":"simclr/modules/nt_xent.py","file_url":"https://github.com/john-mlr/CIFAR-10-SimCLR/blob/HEAD/simclr/modules/nt_xent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"z_i:Tensor/2/float, z_j:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/nt-xent-2","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, john-mlr/CIFAR-10-SimCLR when it was checked","mcp_get_code":{"code_sha256":"f10b64ecf0f39804"}},{"code_sha256":"bc1d652d78503f98","code_sha256_prefix":"bc1d652d78503f98","entry":"NT_Xent","repo":"nzw0301/simclr","repo_kind":"listed","path":"loss.py","file_url":"https://github.com/nzw0301/simclr/blob/HEAD/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"NT_Xent","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"bc1d652d78503f98"},"code_page":"/code/nt-xent-2","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, nzw0301/simclr when it was checked","mcp_get_code":{"code_sha256":"bc1d652d78503f98"}},{"code_sha256":"626ad09af14b9cab","code_sha256_prefix":"626ad09af14b9cab","entry":"Projector","repo":"giakou4/pyssl","repo_kind":"listed","path":"builders/simclr.py","file_url":"https://github.com/giakou4/pyssl/blob/HEAD/builders/simclr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Projector","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/projector","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"626ad09af14b9cab"}},{"code_sha256":"2f6dc2d5f30f106e","code_sha256_prefix":"2f6dc2d5f30f106e","entry":"Res18","repo":"Daniel-H-99/SimCLR","repo_kind":"listed","path":"model.py","file_url":"https://github.com/Daniel-H-99/SimCLR/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"input:Tensor/4/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Daniel-H-99/SimCLR when it was checked","mcp_get_code":{"code_sha256":"2f6dc2d5f30f106e"}},{"code_sha256":"8556399cf0e482d3","code_sha256_prefix":"8556399cf0e482d3","entry":"Res18Block","repo":"Daniel-H-99/SimCLR","repo_kind":"listed","path":"model.py","file_url":"https://github.com/Daniel-H-99/SimCLR/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"input:Tensor/4/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"8556399cf0e482d3"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Daniel-H-99/SimCLR when it was checked","mcp_get_code":{"code_sha256":"8556399cf0e482d3"}},{"code_sha256":"24e7779cb2a243e3","code_sha256_prefix":"24e7779cb2a243e3","entry":"Res18ConvLayer","repo":"Daniel-H-99/SimCLR","repo_kind":"listed","path":"model.py","file_url":"https://github.com/Daniel-H-99/SimCLR/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"input:Tensor/4/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Daniel-H-99/SimCLR when it was checked","mcp_get_code":{"code_sha256":"24e7779cb2a243e3"}},{"code_sha256":"c541394f43fa9adc","code_sha256_prefix":"c541394f43fa9adc","entry":"ResNet","repo":"talipucar/PyFlow_SimCLR","repo_kind":"listed","path":"src/model.py","file_url":"https://github.com/talipucar/PyFlow_SimCLR/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"ResNet","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"c541394f43fa9adc"},"code_page":"/code/resnet","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, talipucar/PyFlow_SimCLR when it was checked","mcp_get_code":{"code_sha256":"c541394f43fa9adc"}},{"code_sha256":"8ae8bb52d6e02325","code_sha256_prefix":"8ae8bb52d6e02325","entry":"ResNet","repo":"rdbch/simclr","repo_kind":"listed","path":"core/networks/simclr.py","file_url":"https://github.com/rdbch/simclr/blob/HEAD/core/networks/simclr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ResNet","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/resnet","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8ae8bb52d6e02325"}},{"code_sha256":"7339ae06662b97a5","code_sha256_prefix":"7339ae06662b97a5","entry":"ResNetBackbone","repo":"Pangoraw/GeoSSL","repo_kind":"listed","path":"geossl/simclr.py","file_url":"https://github.com/Pangoraw/GeoSSL/blob/HEAD/geossl/simclr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"ResNetBackbone","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"7339ae06662b97a5"},"code_page":"/code/resnetbackbone","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7339ae06662b97a5"}},{"code_sha256":"40a653c6651fc5d4","code_sha256_prefix":"40a653c6651fc5d4","entry":"ResNetSimCLR","repo":"wilile26811249/SimCLR","repo_kind":"listed","path":"model.py","file_url":"https://github.com/wilile26811249/SimCLR/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"ResNetSimCLR","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"40a653c6651fc5d4"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"40a653c6651fc5d4"}},{"code_sha256":"15c470cde64303bb","code_sha256_prefix":"15c470cde64303bb","entry":"ResnetEncoder","repo":"sylviesss/pytorch-simclr","repo_kind":"listed","path":"models/simclr.py","file_url":"https://github.com/sylviesss/pytorch-simclr/blob/HEAD/models/simclr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"ResnetEncoder","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"15c470cde64303bb"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, sylviesss/pytorch-simclr when it was checked","mcp_get_code":{"code_sha256":"15c470cde64303bb"}},{"code_sha256":"5069ef275d4321a2","code_sha256_prefix":"5069ef275d4321a2","entry":"ResnetEncoderDropout","repo":"sylviesss/pytorch-simclr","repo_kind":"listed","path":"models/simclr.py","file_url":"https://github.com/sylviesss/pytorch-simclr/blob/HEAD/models/simclr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"ResnetEncoderDropout","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"5069ef275d4321a2"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, sylviesss/pytorch-simclr when it was checked","mcp_get_code":{"code_sha256":"5069ef275d4321a2"}},{"code_sha256":"f33e37ad81b7d344","code_sha256_prefix":"f33e37ad81b7d344","entry":"SIMCLR","repo":"rahimentezari/datadistributiontransferlearning","repo_kind":"listed","path":"src/models/simclr/models.py","file_url":"https://github.com/rahimentezari/datadistributiontransferlearning/blob/HEAD/src/models/simclr/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"aug1:Tensor/2/float, aug2:Tensor/2/float","fixture_out_type":"dict","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, rahimentezari/datadistributiontransferlearning (NOASSERTION)","mcp_get_code":{"code_sha256":"f33e37ad81b7d344"}},{"code_sha256":"54df182d9c00588a","code_sha256_prefix":"54df182d9c00588a","entry":"SSLModel","repo":"kawshik8/DL-project","repo_kind":"listed","path":"src/SSLmodels.py","file_url":"https://github.com/kawshik8/DL-project/blob/HEAD/src/SSLmodels.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"SSLModel","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, kawshik8/DL-project when it was checked","mcp_get_code":{"code_sha256":"54df182d9c00588a"}},{"code_sha256":"b27ce753d440a134","code_sha256_prefix":"b27ce753d440a134","entry":"ShortCut","repo":"Daniel-H-99/SimCLR","repo_kind":"listed","path":"model.py","file_url":"https://github.com/Daniel-H-99/SimCLR/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"input:Tensor/4/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Daniel-H-99/SimCLR when it was checked","mcp_get_code":{"code_sha256":"b27ce753d440a134"}},{"code_sha256":"e78d903f294bb8e2","code_sha256_prefix":"e78d903f294bb8e2","entry":"SimCLR","repo":"bjader/QSSL","repo_kind":"listed","path":"moco/builder.py","file_url":"https://github.com/bjader/QSSL/blob/HEAD/moco/builder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"SimCLR","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e78d903f294bb8e2"}},{"code_sha256":"bf78992ef15b4628","code_sha256_prefix":"bf78992ef15b4628","entry":"SimCLR","repo":"giakou4/pyssl","repo_kind":"listed","path":"builders/simclr.py","file_url":"https://github.com/giakou4/pyssl/blob/HEAD/builders/simclr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"SimCLR","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"bf78992ef15b4628"}},{"code_sha256":"99b66383d6cd5bf7","code_sha256_prefix":"99b66383d6cd5bf7","entry":"SimCLR","repo":"spijkervet/simclr","repo_kind":"listed","path":"simclr/simclr.py","file_url":"https://github.com/spijkervet/simclr/blob/HEAD/simclr/simclr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"SimCLR","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"99b66383d6cd5bf7"}},{"code_sha256":"2c196dbc33af1e86","code_sha256_prefix":"2c196dbc33af1e86","entry":"SimCLR","repo":"thunderInfy/simclr","repo_kind":"listed","path":"simclr.py","file_url":"https://github.com/thunderInfy/simclr/blob/HEAD/simclr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"SimCLR","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, thunderInfy/simclr when it was checked","mcp_get_code":{"code_sha256":"2c196dbc33af1e86"}},{"code_sha256":"dccd7194c3fa9092","code_sha256_prefix":"dccd7194c3fa9092","entry":"SimCLR","repo":"lightly-ai/lightly","repo_kind":"listed","path":"lightly/models/simclr.py","file_url":"https://github.com/lightly-ai/lightly/blob/HEAD/lightly/models/simclr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"SimCLR","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"dccd7194c3fa9092"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"dccd7194c3fa9092"}},{"code_sha256":"965480d2c18b15a7","code_sha256_prefix":"965480d2c18b15a7","entry":"SimCLR","repo":"Pangoraw/GeoSSL","repo_kind":"listed","path":"geossl/simclr.py","file_url":"https://github.com/Pangoraw/GeoSSL/blob/HEAD/geossl/simclr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"SimCLR","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"965480d2c18b15a7"}},{"code_sha256":"db46cc53970a4db1","code_sha256_prefix":"db46cc53970a4db1","entry":"SimCLR","repo":"p3i0t/simclr-cifar10","repo_kind":"listed","path":"models.py","file_url":"https://github.com/p3i0t/simclr-cifar10/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"SimCLR","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"db46cc53970a4db1"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, p3i0t/simclr-cifar10 when it was checked","mcp_get_code":{"code_sha256":"db46cc53970a4db1"}},{"code_sha256":"4c7f0882280707e1","code_sha256_prefix":"4c7f0882280707e1","entry":"SimCLR","repo":"reppy4620/SimCLR4Paint","repo_kind":"listed","path":"modules/simclr.py","file_url":"https://github.com/reppy4620/SimCLR4Paint/blob/HEAD/modules/simclr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"SimCLR","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, reppy4620/SimCLR4Paint when it was checked","mcp_get_code":{"code_sha256":"4c7f0882280707e1"}},{"code_sha256":"b4045ab6673c8148","code_sha256_prefix":"b4045ab6673c8148","entry":"SimCLR","repo":"optimization-ai/sogclr","repo_kind":"listed","path":"sogclr/builder.py","file_url":"https://github.com/optimization-ai/sogclr/blob/HEAD/sogclr/builder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"SimCLR","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, optimization-ai/sogclr when it was checked","mcp_get_code":{"code_sha256":"b4045ab6673c8148"}},{"code_sha256":"4578ef90ebbe26cd","code_sha256_prefix":"4578ef90ebbe26cd","entry":"SimCLR","repo":"ssumin6/SimCLR","repo_kind":"listed","path":"model.py","file_url":"https://github.com/ssumin6/SimCLR/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"SimCLR","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ssumin6/SimCLR when it was checked","mcp_get_code":{"code_sha256":"4578ef90ebbe26cd"}},{"code_sha256":"6db2a02555c7f204","code_sha256_prefix":"6db2a02555c7f204","entry":"SimCLRLoss","repo":"wvangansbeke/Unsupervised-Classification","repo_kind":"listed","path":"losses/losses.py","file_url":"https://github.com/wvangansbeke/Unsupervised-Classification/blob/HEAD/losses/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"features:Tensor/3/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, wvangansbeke/Unsupervised-Classification (NOASSERTION)","mcp_get_code":{"code_sha256":"6db2a02555c7f204"}},{"code_sha256":"3ac7ccd797e47c29","code_sha256_prefix":"3ac7ccd797e47c29","entry":"SimCLRMain","repo":"sylviesss/pytorch-simclr","repo_kind":"listed","path":"models/simclr.py","file_url":"https://github.com/sylviesss/pytorch-simclr/blob/HEAD/models/simclr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"SimCLRMain","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"3ac7ccd797e47c29"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, sylviesss/pytorch-simclr when it was checked","mcp_get_code":{"code_sha256":"3ac7ccd797e47c29"}},{"code_sha256":"2d22ec7eee6353ce","code_sha256_prefix":"2d22ec7eee6353ce","entry":"SimCLRProjectionHead","repo":"lightly-ai/lightly","repo_kind":"listed","path":"lightly/models/simclr.py","file_url":"https://github.com/lightly-ai/lightly/blob/HEAD/lightly/models/simclr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"SimCLRProjectionHead","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2d22ec7eee6353ce"}},{"code_sha256":"00e45e65ec60a85c","code_sha256_prefix":"00e45e65ec60a85c","entry":"SimLoss","repo":"sunjesse/SimCLR_pytorch","repo_kind":"listed","path":"loss.py","file_url":"https://github.com/sunjesse/SimCLR_pytorch/blob/HEAD/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"batch:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"00e45e65ec60a85c"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, sunjesse/SimCLR_pytorch when it was checked","mcp_get_code":{"code_sha256":"00e45e65ec60a85c"}},{"code_sha256":"19bb24ecb5d473db","code_sha256_prefix":"19bb24ecb5d473db","entry":"SupConLoss","repo":"delyan-boychev/grad-cache-con-learning","repo_kind":"listed","path":"src/grad_cache_con_learning/losses.py","file_url":"https://github.com/delyan-boychev/grad-cache-con-learning/blob/HEAD/src/grad_cache_con_learning/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"features:Tensor/3/float, labels:Tensor/1/int, mask:NoneType/0/?","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/supconloss","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"19bb24ecb5d473db"}},{"code_sha256":"a5dbd9a427e2bec3","code_sha256_prefix":"a5dbd9a427e2bec3","entry":"SupConLoss","repo":"hannaiiyanggit/unicon","repo_kind":"listed","path":"losses.py","file_url":"https://github.com/hannaiiyanggit/unicon/blob/HEAD/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"features:Tensor/3/float, labels:Tensor/1/int, mask:NoneType/0/?","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/supconloss","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a5dbd9a427e2bec3"}},{"code_sha256":"d8d1dd0aafb92f18","code_sha256_prefix":"d8d1dd0aafb92f18","entry":"SupConLoss","repo":"Liut2016/ecg-supcontrast","repo_kind":"listed","path":"losses.py","file_url":"https://github.com/Liut2016/ecg-supcontrast/blob/HEAD/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"features:Tensor/3/float, labels:Tensor/1/int, mask:NoneType/0/?","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/supconloss","census":null,"licence":"BSD-2-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d8d1dd0aafb92f18"}},{"code_sha256":"1d1a1df3f3426c17","code_sha256_prefix":"1d1a1df3f3426c17","entry":"SupConLoss","repo":"rajatkoner08/oodformer","repo_kind":"listed","path":"losses.py","file_url":"https://github.com/rajatkoner08/oodformer/blob/HEAD/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"features:Tensor/3/float, labels:Tensor/1/int, mask:NoneType/0/?","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/supconloss","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, rajatkoner08/oodformer when it was checked","mcp_get_code":{"code_sha256":"1d1a1df3f3426c17"}},{"code_sha256":"50709c4ec879ecc5","code_sha256_prefix":"50709c4ec879ecc5","entry":"_adapt_resnet_model","repo":"filipbasara0/matryoshka-representation-learning","repo_kind":"listed","path":"mrl/encoders/models.py","file_url":"https://github.com/filipbasara0/matryoshka-representation-learning/blob/HEAD/mrl/encoders/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"model:callable/0/?","fixture_out_type":"MinimalResNet","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"50709c4ec879ecc5"}},{"code_sha256":"589ff9232fa952cc","code_sha256_prefix":"589ff9232fa952cc","entry":"_get_weights_url","repo":"Pangoraw/GeoSSL","repo_kind":"listed","path":"geossl/simclr.py","file_url":"https://github.com/Pangoraw/GeoSSL/blob/HEAD/geossl/simclr.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"rn_model:str/0/str, dataset:str/0/str, method:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"589ff9232fa952cc"}},{"code_sha256":"b0f936d4d6ae3b8c","code_sha256_prefix":"b0f936d4d6ae3b8c","entry":"accuracy","repo":"sthalles/SimCLR","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/sthalles/SimCLR/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int","fixture_out_type":"list","code_page":"/code/accuracy","census":{"url":"/census/accuracy","implementations":8,"papers":7,"distinct_outputs":7,"n_buckets":6,"bucket_key":null,"bucket_index":null,"bucket_label":null},"census_bucket_fragment":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b0f936d4d6ae3b8c"}},{"code_sha256":"11bc56dd2ecb7644","code_sha256_prefix":"11bc56dd2ecb7644","entry":"accuracy","repo":"AndrewAtanov/simclr-pytorch","repo_kind":"listed","path":"models/losses.py","file_url":"https://github.com/AndrewAtanov/simclr-pytorch/blob/HEAD/models/losses.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"logits:Tensor/2/float, labels:Tensor/2/int, k:int/0/int","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/accuracy","census":{"url":"/census/accuracy","implementations":8,"papers":7,"distinct_outputs":7,"n_buckets":6,"bucket_key":null,"bucket_index":null,"bucket_label":null},"census_bucket_fragment":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"11bc56dd2ecb7644"}},{"code_sha256":"c418940b96d1fe9e","code_sha256_prefix":"c418940b96d1fe9e","entry":"add_contrastive_loss","repo":"google-research/simclr","repo_kind":"official","path":"objective.py","file_url":"https://github.com/google-research/simclr/blob/HEAD/objective.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"hidden:SymbolicTensor/2/float, hidden_norm:bool/0/bool, temperature:float/0/float, tpu_context:NoneType/0/?, weights:float/0/float","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c418940b96d1fe9e"}},{"code_sha256":"92885c7117af82c9","code_sha256_prefix":"92885c7117af82c9","entry":"add_contrastive_loss","repo":"ta9ryuWalrus/simclr","repo_kind":"listed","path":"tf2/objective.py","file_url":"https://github.com/ta9ryuWalrus/simclr/blob/HEAD/tf2/objective.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"hidden:EagerTensor/2/float, hidden_norm:bool/0/bool, temperature:float/0/float, strategy:NoneType/0/?","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"92885c7117af82c9"},"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"92885c7117af82c9"}},{"code_sha256":"8924ee1d1cde05c4","code_sha256_prefix":"8924ee1d1cde05c4","entry":"add_contrastive_loss","repo":"parkinkon1/simclr","repo_kind":"listed","path":"objective.py","file_url":"https://github.com/parkinkon1/simclr/blob/HEAD/objective.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"hidden:SymbolicTensor/2/float, hidden_norm:bool/0/bool, temperature:float/0/float, tpu_context:NoneType/0/?, weights:float/0/float","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8924ee1d1cde05c4"}},{"code_sha256":"4cc4c53bf5875d64","code_sha256_prefix":"4cc4c53bf5875d64","entry":"add_indices","repo":"ae-foster/pytorch-simclr","repo_kind":"listed","path":"dataset.py","file_url":"https://github.com/ae-foster/pytorch-simclr/blob/HEAD/dataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"dataset_cls:callable/0/?","fixture_out_type":"type","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"4cc4c53bf5875d64"}},{"code_sha256":"2c4b4b78675c35ee","code_sha256_prefix":"2c4b4b78675c35ee","entry":"agg_all_metrics","repo":"AndrewAtanov/simclr-pytorch","repo_kind":"listed","path":"utils/utils.py","file_url":"https://github.com/AndrewAtanov/simclr-pytorch/blob/HEAD/utils/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"outputs:list/1/dict","fixture_out_type":"dict","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2c4b4b78675c35ee"}},{"code_sha256":"2b5d65dc96c1a03b","code_sha256_prefix":"2b5d65dc96c1a03b","entry":"all_gather","repo":"jramapuram/SimCLR","repo_kind":"listed","path":"objective.py","file_url":"https://github.com/jramapuram/SimCLR/blob/HEAD/objective.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"tensor:Tensor/2/float, expand_dim:int/0/int, num_replicas:int/0/int","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/all-gather","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2b5d65dc96c1a03b"}},{"code_sha256":"8e2cdb7569401c95","code_sha256_prefix":"8e2cdb7569401c95","entry":"all_gather_layer","repo":"optimization-ai/sogclr","repo_kind":"listed","path":"sogclr/builder.py","file_url":"https://github.com/optimization-ai/sogclr/blob/HEAD/sogclr/builder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"all_gather_layer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, optimization-ai/sogclr when it was checked","mcp_get_code":{"code_sha256":"8e2cdb7569401c95"}},{"code_sha256":"3a7dd916ad6f6389","code_sha256_prefix":"3a7dd916ad6f6389","entry":"amfm_features","repo":"giakou4/pyfeats","repo_kind":"listed","path":"pyfeats/multiscale/amfm.py","file_url":"https://github.com/giakou4/pyfeats/blob/HEAD/pyfeats/multiscale/amfm.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"f:ndarray/2/float, bins:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","retrieve_with":{"tool":"get_code","code_sha256":"3a7dd916ad6f6389"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3a7dd916ad6f6389"}},{"code_sha256":"0809a27fc54eb733","code_sha256_prefix":"0809a27fc54eb733","entry":"apply_op","repo":"caesarea38/doclangid","repo_kind":"listed","path":"src/core/augmentations.py","file_url":"https://github.com/caesarea38/doclangid/blob/HEAD/src/core/augmentations.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"image:Image/0/?, op_name:str/0/str, magnitude:float/0/float, interpolation:int/0/int, fill:int/0/int","fixture_out_type":"Image","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/apply-op","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, caesarea38/doclangid when it was checked","mcp_get_code":{"code_sha256":"0809a27fc54eb733"}},{"code_sha256":"583552044648d2f0","code_sha256_prefix":"583552044648d2f0","entry":"clique_merge","repo":"zpf0117b/CLMB","repo_kind":"listed","path":"src/mergeclusters.py","file_url":"https://github.com/zpf0117b/CLMB/blob/HEAD/src/mergeclusters.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"contigsof:dict/0/?, threshold:float/0/float","fixture_out_type":"dict","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"583552044648d2f0"}},{"code_sha256":"eb14839e65ee11cf","code_sha256_prefix":"eb14839e65ee11cf","entry":"contrastive_loss","repo":"mdiephuis/simclr","repo_kind":"listed","path":"loss.py","file_url":"https://github.com/mdiephuis/simclr/blob/HEAD/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"xi:Tensor/2/float, xj:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"eb14839e65ee11cf"},"code_page":"/code/contrastive-loss","census":{"url":"/census/contrastive-loss","implementations":11,"papers":18,"distinct_outputs":7,"n_buckets":3,"bucket_key":null,"bucket_index":null,"bucket_label":null},"census_bucket_fragment":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"eb14839e65ee11cf"}},{"code_sha256":"ba00312b3d5b70dc","code_sha256_prefix":"ba00312b3d5b70dc","entry":"contrastive_loss","repo":"htdt/self-supervised","repo_kind":"listed","path":"methods/contrastive.py","file_url":"https://github.com/htdt/self-supervised/blob/HEAD/methods/contrastive.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/contrastive-loss","census":{"url":"/census/contrastive-loss","implementations":11,"papers":18,"distinct_outputs":7,"n_buckets":3,"bucket_key":[[2,"float","float32"],[2,"float","float32"]],"bucket_index":2,"bucket_label":"arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32"},"census_bucket_fragment":"bucket-2","licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, htdt/self-supervised when it was checked","mcp_get_code":{"code_sha256":"ba00312b3d5b70dc"}},{"code_sha256":"eac22c52c3120485","code_sha256_prefix":"eac22c52c3120485","entry":"contrastive_loss","repo":"asd08573064/SimCLR","repo_kind":"listed","path":"train_SSL.py","file_url":"https://github.com/asd08573064/SimCLR/blob/HEAD/train_SSL.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"projections_1:EagerTensor/2/float, projections_2:EagerTensor/2/float, temperature:float/0/float","fixture_out_type":"EagerTensor","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":"/code/contrastive-loss","census":{"url":"/census/contrastive-loss","implementations":11,"papers":18,"distinct_outputs":7,"n_buckets":3,"bucket_key":null,"bucket_index":null,"bucket_label":null},"census_bucket_fragment":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"eac22c52c3120485"}},{"code_sha256":"6842d0dec7d692ae","code_sha256_prefix":"6842d0dec7d692ae","entry":"create_data_loaders_from_arrays","repo":"Spijkervet/SimCLR","repo_kind":"listed","path":"linear_evaluation.py","file_url":"https://github.com/Spijkervet/SimCLR/blob/HEAD/linear_evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"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","fixture_out_type":"tuple","retrieve_with":{"tool":"get_code","code_sha256":"6842d0dec7d692ae"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6842d0dec7d692ae"}},{"code_sha256":"5d283bdd3a74687f","code_sha256_prefix":"5d283bdd3a74687f","entry":"create_projection_kernel","repo":"zpf0117b/CLMB","repo_kind":"listed","path":"src/create_kernel.py","file_url":"https://github.com/zpf0117b/CLMB/blob/HEAD/src/create_kernel.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"k:int/0/int","fixture_out_type":"ndarray","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5d283bdd3a74687f"}},{"code_sha256":"c412bcc0dbd87516","code_sha256_prefix":"c412bcc0dbd87516","entry":"create_rc_kernel","repo":"zpf0117b/CLMB","repo_kind":"listed","path":"src/create_kernel.py","file_url":"https://github.com/zpf0117b/CLMB/blob/HEAD/src/create_kernel.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"k:int/0/int","fixture_out_type":"ndarray","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c412bcc0dbd87516"}},{"code_sha256":"3615fd781c0e7e45","code_sha256_prefix":"3615fd781c0e7e45","entry":"encode_train_set","repo":"ae-foster/pytorch-simclr","repo_kind":"listed","path":"evaluate/lbfgs.py","file_url":"https://github.com/ae-foster/pytorch-simclr/blob/HEAD/evaluate/lbfgs.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"clftrainloader:list/1/tuple, device:str/0/str, net:callable/0/?","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T09:36:09.529386+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3615fd781c0e7e45"}},{"code_sha256":"57bbb1c2ae467a4f","code_sha256_prefix":"57bbb1c2ae467a4f","entry":"euclidean_dist","repo":null,"repo_kind":"listed","path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"x:Tensor/2/float, support_mean:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"57bbb1c2ae467a4f"},"code_page":"/code/euclidean-dist","census":{"url":"/census/euclidean-dist","implementations":12,"papers":14,"distinct_outputs":3,"n_buckets":1,"bucket_key":[[2,"float","float32"],[2,"float","float32"]],"bucket_index":1,"bucket_label":"arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32"},"census_bucket_fragment":"bucket-1","placed_by_identical_code":{"repo":"rajatkoner08/oodformer","path":"OOD_Distance.py","file_url":"https://github.com/rajatkoner08/oodformer/blob/HEAD/OOD_Distance.py","papers":["2107.08976"],"is":"identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own"},"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"57bbb1c2ae467a4f"}},{"code_sha256":"07fd42842d206009","code_sha256_prefix":"07fd42842d206009","entry":"fdta","repo":"giakou4/pyfeats","repo_kind":"listed","path":"pyfeats/multiscale/fdta.py","file_url":"https://github.com/giakou4/pyfeats/blob/HEAD/pyfeats/multiscale/fdta.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"f:ndarray/2/float, mask:ndarray/2/float, s:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T22:55:07.240920+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"07fd42842d206009"}},{"code_sha256":"1f3daef400d7d53c","code_sha256_prefix":"1f3daef400d7d53c","entry":"filter_clusters","repo":"zpf0117b/CLMB","repo_kind":"listed","path":"vamb/benchmark.py","file_url":"https://github.com/zpf0117b/CLMB/blob/HEAD/vamb/benchmark.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"clusters:dict/0/?, reference:MockReference/0/?, minsize:int/0/int, mincontigs:int/0/int, checkpresence:bool/0/bool","fixture_out_type":"dict","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1f3daef400d7d53c"}},{"code_sha256":"b621a5344f937d5e","code_sha256_prefix":"b621a5344f937d5e","entry":"generate_op_meta","repo":"caesarea38/doclangid","repo_kind":"listed","path":"src/core/augmentations.py","file_url":"https://github.com/caesarea38/doclangid/blob/HEAD/src/core/augmentations.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"numb_magnitudes:int/0/int, image_size:int/0/int","fixture_out_type":"dict","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, caesarea38/doclangid when it was checked","mcp_get_code":{"code_sha256":"b621a5344f937d5e"}},{"code_sha256":"86b892b3b407785f","code_sha256_prefix":"86b892b3b407785f","entry":"get_adjusted_rand_score","repo":"zpf0117b/CLMB","repo_kind":"listed","path":"src/benchmark_old.py","file_url":"https://github.com/zpf0117b/CLMB/blob/HEAD/src/benchmark_old.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"clusters1:dict/0/?, clusters2:dict/0/?","fixture_out_type":"float","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"86b892b3b407785f"}},{"code_sha256":"8c4252f18f2e14a8","code_sha256_prefix":"8c4252f18f2e14a8","entry":"get_base_model","repo":"kawshik8/DL-project","repo_kind":"listed","path":"src/SSLmodels.py","file_url":"https://github.com/kawshik8/DL-project/blob/HEAD/src/SSLmodels.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"name:str/0/str","fixture_out_type":"ResNet","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/get-base-model","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, kawshik8/DL-project when it was checked","mcp_get_code":{"code_sha256":"8c4252f18f2e14a8"}},{"code_sha256":"0adaf15a01b00920","code_sha256_prefix":"0adaf15a01b00920","entry":"get_color_distortion","repo":"liuch37/image-processing","repo_kind":"listed","path":"augmentation/color_distortion_pytorch.py","file_url":"https://github.com/liuch37/image-processing/blob/HEAD/augmentation/color_distortion_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"s:float/0/float","fixture_out_type":"Compose","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/get-color-distortion","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0adaf15a01b00920"}},{"code_sha256":"94226f82998bee03","code_sha256_prefix":"94226f82998bee03","entry":"get_color_distortion","repo":"AndrewAtanov/simclr-pytorch","repo_kind":"listed","path":"utils/datautils.py","file_url":"https://github.com/AndrewAtanov/simclr-pytorch/blob/HEAD/utils/datautils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"s:float/0/float","fixture_out_type":"Compose","level_recorded_at":"2026-09-25T08:04:19.804293+00:00","code_page":"/code/get-color-distortion","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"94226f82998bee03"}},{"code_sha256":"6181cfb7ba78942e","code_sha256_prefix":"6181cfb7ba78942e","entry":"get_contrastive_loss","repo":"mandiehyewon/goodviews_ecg","repo_kind":"listed","path":"utils/loss.py","file_url":"https://github.com/mandiehyewon/goodviews_ecg/blob/HEAD/utils/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"args:Args/0/?, features:Tensor/2/float, group_labels:Tensor/1/int, device:device/0/?","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, mandiehyewon/goodviews_ecg when it was checked","mcp_get_code":{"code_sha256":"6181cfb7ba78942e"}},{"code_sha256":"cb291d2ffc7590c7","code_sha256_prefix":"cb291d2ffc7590c7","entry":"get_features","repo":"Spijkervet/SimCLR","repo_kind":"listed","path":"linear_evaluation.py","file_url":"https://github.com/Spijkervet/SimCLR/blob/HEAD/linear_evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"simclr_model:callable/0/?, train_loader:list/1/tuple, test_loader:list/1/tuple, device:str/0/str","fixture_out_type":"tuple","code_page":"/code/get-features","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"cb291d2ffc7590c7"}},{"code_sha256":"6940670c59bb0cda","code_sha256_prefix":"6940670c59bb0cda","entry":"global_ave_pool","repo":"talipucar/PyFlow_SimCLR","repo_kind":"listed","path":"src/model.py","file_url":"https://github.com/talipucar/PyFlow_SimCLR/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"x:Tensor/4/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"6940670c59bb0cda"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, talipucar/PyFlow_SimCLR when it was checked","mcp_get_code":{"code_sha256":"6940670c59bb0cda"}},{"code_sha256":"bcbf650b774f3bab","code_sha256_prefix":"bcbf650b774f3bab","entry":"grayscale_morphology_features","repo":"giakou4/pyfeats","repo_kind":"listed","path":"pyfeats/morphological/grayscale_morphological_analysis.py","file_url":"https://github.com/giakou4/pyfeats/blob/HEAD/pyfeats/morphological/grayscale_morphological_analysis.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"f:ndarray/2/int, N:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T22:55:07.240920+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"bcbf650b774f3bab"}},{"code_sha256":"df7842ad80bc568e","code_sha256_prefix":"df7842ad80bc568e","entry":"hierarchical_merge","repo":"zpf0117b/CLMB","repo_kind":"listed","path":"src/mergeclusters.py","file_url":"https://github.com/zpf0117b/CLMB/blob/HEAD/src/mergeclusters.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"contigsof:dict/0/?, threshold:float/0/float","fixture_out_type":"dict","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"df7842ad80bc568e"}},{"code_sha256":"a89e539d4a1fa3b2","code_sha256_prefix":"a89e539d4a1fa3b2","entry":"histogram","repo":"giakou4/pyfeats","repo_kind":"listed","path":"pyfeats/histogram/histogram.py","file_url":"https://github.com/giakou4/pyfeats/blob/HEAD/pyfeats/histogram/histogram.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"f:ndarray/2/int, mask:ndarray/2/int, bins:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","retrieve_with":{"tool":"get_code","code_sha256":"a89e539d4a1fa3b2"},"code_page":"/code/histogram","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a89e539d4a1fa3b2"}},{"code_sha256":"e0f6be0e6d3d8c17","code_sha256_prefix":"e0f6be0e6d3d8c17","entry":"inference","repo":"Spijkervet/SimCLR","repo_kind":"listed","path":"linear_evaluation.py","file_url":"https://github.com/Spijkervet/SimCLR/blob/HEAD/linear_evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"loader:list/1/tuple, simclr_model:callable/0/?, device:device/0/?","fixture_out_type":"tuple","code_page":"/code/inference","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e0f6be0e6d3d8c17"}},{"code_sha256":"6325cd34bc332e95","code_sha256_prefix":"6325cd34bc332e95","entry":"l2_normalize","repo":"jramapuram/SimCLR","repo_kind":"listed","path":"objective.py","file_url":"https://github.com/jramapuram/SimCLR/blob/HEAD/objective.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"x:Tensor/2/float, dim:int/0/int, eps:float/0/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"6325cd34bc332e95"},"code_page":"/code/l2-normalize","census":{"url":"/census/l2-normalize","implementations":15,"papers":13,"distinct_outputs":5,"n_buckets":3,"bucket_key":[[2,"float","float32"]],"bucket_index":1,"bucket_label":"arg 1: rank 2, kind float, dtype float32"},"census_bucket_fragment":"bucket-1","licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6325cd34bc332e95"}},{"code_sha256":"ae6df0014dbc55c9","code_sha256_prefix":"ae6df0014dbc55c9","entry":"mahalanobis","repo":"rajatkoner08/oodformer","repo_kind":"listed","path":"losses.py","file_url":"https://github.com/rajatkoner08/oodformer/blob/HEAD/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"x:Tensor/2/float, support_mean:list/1/Tensor, inv_covmat:list/1/ndarray","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, rajatkoner08/oodformer when it was checked","mcp_get_code":{"code_sha256":"ae6df0014dbc55c9"}},{"code_sha256":"439f4fcb999995b5","code_sha256_prefix":"439f4fcb999995b5","entry":"mean_cumulative_gain","repo":"AndrewAtanov/simclr-pytorch","repo_kind":"listed","path":"models/losses.py","file_url":"https://github.com/AndrewAtanov/simclr-pytorch/blob/HEAD/models/losses.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"logits:Tensor/2/float, labels:Tensor/2/int, k:int/0/int","fixture_out_type":"Tensor","level_recorded_at":"2026-09-25T10:06:43.451432+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"439f4fcb999995b5"}},{"code_sha256":"d3385cd7eed6a6f2","code_sha256_prefix":"d3385cd7eed6a6f2","entry":"multilevel_binary_morphology_features","repo":"giakou4/pyfeats","repo_kind":"listed","path":"pyfeats/morphological/multilevel_binary_morphological_analysis.py","file_url":"https://github.com/giakou4/pyfeats/blob/HEAD/pyfeats/morphological/multilevel_binary_morphological_analysis.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"img:ndarray/2/int, mask:ndarray/2/int, N:int/0/int, thresholds:list/1/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d3385cd7eed6a6f2"}},{"code_sha256":"191b9a33cbd317cc","code_sha256_prefix":"191b9a33cbd317cc","entry":"multiregion_histogram","repo":"giakou4/pyfeats","repo_kind":"listed","path":"pyfeats/histogram/multiregion_histogram.py","file_url":"https://github.com/giakou4/pyfeats/blob/HEAD/pyfeats/histogram/multiregion_histogram.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"f:ndarray/2/int, mask:ndarray/2/int, bins:int/0/int, num_eros:int/0/int, square_size:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"191b9a33cbd317cc"}},{"code_sha256":"0931a280f76e561f","code_sha256_prefix":"0931a280f76e561f","entry":"nt_xent","repo":"p3i0t/SimCLR-CIFAR10","repo_kind":"listed","path":"simclr.py","file_url":"https://github.com/p3i0t/SimCLR-CIFAR10/blob/HEAD/simclr.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"x:Tensor/2/float, t:float/0/float","fixture_out_type":"Tensor","retrieve_with":{"tool":"get_code","code_sha256":"0931a280f76e561f"},"code_page":"/code/nt-xent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, p3i0t/SimCLR-CIFAR10 when it was checked","mcp_get_code":{"code_sha256":"0931a280f76e561f"}},{"code_sha256":"56d873a0ee406a9d","code_sha256_prefix":"56d873a0ee406a9d","entry":"nt_xent","repo":"Pangoraw/GeoSSL","repo_kind":"listed","path":"geossl/simclr.py","file_url":"https://github.com/Pangoraw/GeoSSL/blob/HEAD/geossl/simclr.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"z:Tensor/2/float, perm:Tensor/1/int, tau:float/0/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/nt-xent","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"56d873a0ee406a9d"}},{"code_sha256":"a3786294fb65e90e","code_sha256_prefix":"a3786294fb65e90e","entry":"nt_xent_loss","repo":"giakou4/pyssl","repo_kind":"listed","path":"builders/simclr.py","file_url":"https://github.com/giakou4/pyssl/blob/HEAD/builders/simclr.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"z1:Tensor/2/float, z2:Tensor/2/float, temperature:float/0/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"a3786294fb65e90e"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a3786294fb65e90e"}},{"code_sha256":"c404ad6b3c3cae86","code_sha256_prefix":"c404ad6b3c3cae86","entry":"only_value_error","repo":"AndrewAtanov/simclr-pytorch","repo_kind":"listed","path":"myexman/index.py","file_url":"https://github.com/AndrewAtanov/simclr-pytorch/blob/HEAD/myexman/index.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"conv:callable/0/?","fixture_out_type":"function","level_recorded_at":"2026-09-24T21:54:21.362907+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c404ad6b3c3cae86"}},{"code_sha256":"eab99ab911f1645a","code_sha256_prefix":"eab99ab911f1645a","entry":"pad","repo":"AndrewAtanov/simclr-pytorch","repo_kind":"listed","path":"utils/datautils.py","file_url":"https://github.com/AndrewAtanov/simclr-pytorch/blob/HEAD/utils/datautils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"img:Image/0/?, size:int/0/int, mode:str/0/str","fixture_out_type":"ndarray","level_recorded_at":"2026-09-25T10:37:12.143382+00:00","code_page":"/code/pad","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"eab99ab911f1645a"}},{"code_sha256":"98c1de629745feab","code_sha256_prefix":"98c1de629745feab","entry":"pad_image","repo":"giakou4/pyfeats","repo_kind":"listed","path":"pyfeats/utilities.py","file_url":"https://github.com/giakou4/pyfeats/blob/HEAD/pyfeats/utilities.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"f:ndarray/2/int, pad:int/0/int, fill_val:int/0/int","fixture_out_type":"ndarray","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":"/code/pad-image","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"98c1de629745feab"}},{"code_sha256":"9a021af106b97cf3","code_sha256_prefix":"9a021af106b97cf3","entry":"pairs","repo":"zpf0117b/CLMB","repo_kind":"listed","path":"vamb/cluster.py","file_url":"https://github.com/zpf0117b/CLMB/blob/HEAD/vamb/cluster.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"clustergenerator:ClusterGenerator/0/?, labels:ndarray/1/int","fixture_out_type":"generator","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9a021af106b97cf3"}},{"code_sha256":"034143e2f3288a7c","code_sha256_prefix":"034143e2f3288a7c","entry":"parse_images","repo":"asd08573064/SimCLR","repo_kind":"listed","path":"dataset.py","file_url":"https://github.com/asd08573064/SimCLR/blob/HEAD/dataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"image_path:str/0/str","fixture_out_type":"EagerTensor","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"034143e2f3288a7c"}},{"code_sha256":"5b8da074d51c8e00","code_sha256_prefix":"5b8da074d51c8e00","entry":"randaugment","repo":"caesarea38/doclangid","repo_kind":"listed","path":"src/core/augmentations.py","file_url":"https://github.com/caesarea38/doclangid/blob/HEAD/src/core/augmentations.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"image:Image/0/?, ops:tuple/1/int, mag:tuple/1/int, numb_magnitudes:int/0/int, interpolation:InterpolationMode/0/?, fill:list/1/int","fixture_out_type":"Image","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, caesarea38/doclangid when it was checked","mcp_get_code":{"code_sha256":"5b8da074d51c8e00"}},{"code_sha256":"0834c0be7a6b72e8","code_sha256_prefix":"0834c0be7a6b72e8","entry":"represent_as_str","repo":"AndrewAtanov/simclr-pytorch","repo_kind":"listed","path":"myexman/parser.py","file_url":"https://github.com/AndrewAtanov/simclr-pytorch/blob/HEAD/myexman/parser.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"self:Representer/0/?, data:CustomObject/0/?, tostr:callable/0/?","fixture_out_type":"ScalarNode","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0834c0be7a6b72e8"}},{"code_sha256":"cfd9492c2dbc3c97","code_sha256_prefix":"cfd9492c2dbc3c97","entry":"reverse_complement","repo":"zpf0117b/CLMB","repo_kind":"listed","path":"src/create_kernel.py","file_url":"https://github.com/zpf0117b/CLMB/blob/HEAD/src/create_kernel.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"nuc:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"cfd9492c2dbc3c97"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"cfd9492c2dbc3c97"}},{"code_sha256":"122255f68540f240","code_sha256_prefix":"122255f68540f240","entry":"same_padding","repo":"rdbch/tutorial_simclr","repo_kind":"listed","path":"core/nn/blocks/utils.py","file_url":"https://github.com/rdbch/tutorial_simclr/blob/HEAD/core/nn/blocks/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"kSize:int/0/int, dilSize:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T22:55:07.240920+00:00","retrieve_with":{"tool":"get_code","code_sha256":"122255f68540f240"},"code_page":"/code/same-padding","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"122255f68540f240"}},{"code_sha256":"c91376d1f880ecf3","code_sha256_prefix":"c91376d1f880ecf3","entry":"simple_import","repo":"rdbch/tutorial_simclr","repo_kind":"listed","path":"core/nn/blocks/utils.py","file_url":"https://github.com/rdbch/tutorial_simclr/blob/HEAD/core/nn/blocks/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"name:str/0/str, pack:str/0/str","fixture_out_type":"module","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c91376d1f880ecf3"}},{"code_sha256":"e098d0fbdbf83114","code_sha256_prefix":"e098d0fbdbf83114","entry":"simpleroot","repo":"AndrewAtanov/simclr-pytorch","repo_kind":"listed","path":"myexman/parser.py","file_url":"https://github.com/AndrewAtanov/simclr-pytorch/blob/HEAD/myexman/parser.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"__file__:str/0/str","fixture_out_type":"PosixPath","level_recorded_at":"2026-09-24T22:55:07.240920+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e098d0fbdbf83114"}},{"code_sha256":"c48a4ea6fafc859f","code_sha256_prefix":"c48a4ea6fafc859f","entry":"subgraph_merge","repo":"zpf0117b/CLMB","repo_kind":"listed","path":"src/mergeclusters.py","file_url":"https://github.com/zpf0117b/CLMB/blob/HEAD/src/mergeclusters.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"contigsof:dict/0/?, threshold:float/0/float","fixture_out_type":"dict","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c48a4ea6fafc859f"}},{"code_sha256":"3f1dd5d8d7b83513","code_sha256_prefix":"3f1dd5d8d7b83513","entry":"test","repo":"ae-foster/pytorch-simclr","repo_kind":"listed","path":"evaluate/lbfgs.py","file_url":"https://github.com/ae-foster/pytorch-simclr/blob/HEAD/evaluate/lbfgs.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"testloader:list/1/tuple, device:str/0/str, net:callable/0/?, clf:callable/0/?","fixture_out_type":"float","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":"/code/test","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3f1dd5d8d7b83513"}},{"code_sha256":"7d95614711e96832","code_sha256_prefix":"7d95614711e96832","entry":"timing","repo":"AndrewAtanov/simclr-pytorch","repo_kind":"listed","path":"utils/utils.py","file_url":"https://github.com/AndrewAtanov/simclr-pytorch/blob/HEAD/utils/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"f:callable/0/?","fixture_out_type":"function","level_recorded_at":"2026-09-24T22:55:07.240920+00:00","code_page":"/code/timing","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7d95614711e96832"}},{"code_sha256":"7aac0de5d1568953","code_sha256_prefix":"7aac0de5d1568953","entry":"tpu_cross_replica_concat","repo":"google-research/simclr","repo_kind":"official","path":"objective.py","file_url":"https://github.com/google-research/simclr/blob/HEAD/objective.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"tensor:SymbolicTensor/2/float, tpu_context:TPUContext/0/?","fixture_out_type":"SymbolicTensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7aac0de5d1568953"}},{"code_sha256":"5ef56dc923793fb3","code_sha256_prefix":"5ef56dc923793fb3","entry":"tpu_cross_replica_concat","repo":"ta9ryuWalrus/simclr","repo_kind":"listed","path":"tf2/objective.py","file_url":"https://github.com/ta9ryuWalrus/simclr/blob/HEAD/tf2/objective.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"tensor:EagerTensor/2/float, strategy:MockStrategy/0/?","fixture_out_type":"EagerTensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5ef56dc923793fb3"}},{"code_sha256":"4ec61811bee71758","code_sha256_prefix":"4ec61811bee71758","entry":"train_clf","repo":"ae-foster/pytorch-simclr","repo_kind":"listed","path":"evaluate/lbfgs.py","file_url":"https://github.com/ae-foster/pytorch-simclr/blob/HEAD/evaluate/lbfgs.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"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","fixture_out_type":"Linear","level_recorded_at":"2026-09-24T22:55:07.240920+00:00","code_page":"/code/train-clf","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"4ec61811bee71758"}},{"code_sha256":"d77f6aa7bb727375","code_sha256_prefix":"d77f6aa7bb727375","entry":"viz_array_grid","repo":"AndrewAtanov/simclr-pytorch","repo_kind":"listed","path":"utils/utils.py","file_url":"https://github.com/AndrewAtanov/simclr-pytorch/blob/HEAD/utils/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"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","fixture_out_type":"ndarray","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d77f6aa7bb727375"}},{"code_sha256":"b00d9ebb0254cfd3","code_sha256_prefix":"b00d9ebb0254cfd3","entry":"wp_features","repo":"giakou4/pyfeats","repo_kind":"listed","path":"pyfeats/multiscale/wp.py","file_url":"https://github.com/giakou4/pyfeats/blob/HEAD/pyfeats/multiscale/wp.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"f:ndarray/2/float, mask:ndarray/2/float, wavelet:str/0/str, maxlevel:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b00d9ebb0254cfd3"}},{"code_sha256":"f823e0add18d7eec","code_sha256_prefix":"f823e0add18d7eec","entry":"yaml_file","repo":"AndrewAtanov/simclr-pytorch","repo_kind":"listed","path":"myexman/parser.py","file_url":"https://github.com/AndrewAtanov/simclr-pytorch/blob/HEAD/myexman/parser.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"name:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-24T22:55:07.240920+00:00","retrieve_with":{"tool":"get_code","code_sha256":"f823e0add18d7eec"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f823e0add18d7eec"}},{"code_sha256":"db566f0014cc2980","code_sha256_prefix":"db566f0014cc2980","entry":"BaseMethod","repo":"Pangoraw/GeoSSL","repo_kind":"listed","path":"geossl/simclr.py","file_url":"https://github.com/Pangoraw/GeoSSL/blob/HEAD/geossl/simclr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/basemethod","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"db566f0014cc2980"}},{"code_sha256":"7fd8c4e94eb9d6f4","code_sha256_prefix":"7fd8c4e94eb9d6f4","entry":"Configurable","repo":"rdbch/simclr","repo_kind":"listed","path":"core/networks/simclr.py","file_url":"https://github.com/rdbch/simclr/blob/HEAD/core/networks/simclr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7fd8c4e94eb9d6f4"}},{"code_sha256":"d1deb5d7410ae0b7","code_sha256_prefix":"d1deb5d7410ae0b7","entry":"Contrastive","repo":"htdt/self-supervised","repo_kind":"listed","path":"methods/contrastive.py","file_url":"https://github.com/htdt/self-supervised/blob/HEAD/methods/contrastive.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, htdt/self-supervised when it was checked","mcp_get_code":{"code_sha256":"d1deb5d7410ae0b7"}},{"code_sha256":"f5ffc1cae804d1f7","code_sha256_prefix":"f5ffc1cae804d1f7","entry":"ContrastiveEncoder","repo":"talipucar/PyFlow_SimCLR","repo_kind":"listed","path":"src/model.py","file_url":"https://github.com/talipucar/PyFlow_SimCLR/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, talipucar/PyFlow_SimCLR when it was checked","mcp_get_code":{"code_sha256":"f5ffc1cae804d1f7"}},{"code_sha256":"ea2c3cf94bcdfef3","code_sha256_prefix":"ea2c3cf94bcdfef3","entry":"ResNet","repo":"cyrilvallez/image-manipulation-detection","repo_kind":"listed","path":"hashing/SimCLRv1/resnet_wider.py","file_url":"https://github.com/cyrilvallez/image-manipulation-detection/blob/HEAD/hashing/SimCLRv1/resnet_wider.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/resnet","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ea2c3cf94bcdfef3"}},{"code_sha256":"ff90bea0467c6b51","code_sha256_prefix":"ff90bea0467c6b51","entry":"SimCLR","repo":"63days/SimCLR","repo_kind":"listed","path":"model.py","file_url":"https://github.com/63days/SimCLR/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, 63days/SimCLR when it was checked","mcp_get_code":{"code_sha256":"ff90bea0467c6b51"}},{"code_sha256":"04a16872e7176429","code_sha256_prefix":"04a16872e7176429","entry":"SimCLR","repo":"rdbch/simclr","repo_kind":"listed","path":"core/networks/simclr.py","file_url":"https://github.com/rdbch/simclr/blob/HEAD/core/networks/simclr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"04a16872e7176429"}},{"code_sha256":"f81649524890dfe5","code_sha256_prefix":"f81649524890dfe5","entry":"SimCLR","repo":"beresandras/contrastive-classification-keras","repo_kind":"listed","path":"algorithms.py","file_url":"https://github.com/beresandras/contrastive-classification-keras/blob/HEAD/algorithms.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f81649524890dfe5"}},{"code_sha256":"708baa8232f99ac8","code_sha256_prefix":"708baa8232f99ac8","entry":"SimCLR","repo":"roydenwa/cell-centroid-former","repo_kind":"listed","path":"src/cellcentroidformer/self_supervised.py","file_url":"https://github.com/roydenwa/cell-centroid-former/blob/HEAD/src/cellcentroidformer/self_supervised.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, roydenwa/cell-centroid-former when it was checked","mcp_get_code":{"code_sha256":"708baa8232f99ac8"}},{"code_sha256":"aea60f5692813252","code_sha256_prefix":"aea60f5692813252","entry":"SimCLR","repo":"Mayurji/SimCLR","repo_kind":"listed","path":"SimCLR.py","file_url":"https://github.com/Mayurji/SimCLR/blob/HEAD/SimCLR.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"GPL-3.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GPL-3.0, as GitHub detects it on this paper's repository, Mayurji/SimCLR, is not in the permissive set Syntology serves inline","mcp_get_code":{"code_sha256":"aea60f5692813252"}},{"code_sha256":"0e2efd6b67f01d69","code_sha256_prefix":"0e2efd6b67f01d69","entry":"SupConLoss","repo":"jwcalder/GraphLearningLayer","repo_kind":"listed","path":"losses.py","file_url":"https://github.com/jwcalder/GraphLearningLayer/blob/HEAD/losses.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/supconloss","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0e2efd6b67f01d69"}},{"code_sha256":"bb4e645996e12174","code_sha256_prefix":"bb4e645996e12174","entry":"build_simclr_model","repo":"mariaauslander/capstone_fall20_irrigation","repo_kind":"listed","path":"simclr.py","file_url":"https://github.com/mariaauslander/capstone_fall20_irrigation/blob/HEAD/simclr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, mariaauslander/capstone_fall20_irrigation when it was checked","mcp_get_code":{"code_sha256":"bb4e645996e12174"}},{"code_sha256":"ddf47684b8425901","code_sha256_prefix":"ddf47684b8425901","entry":"correlogram","repo":"giakou4/pyfeats","repo_kind":"listed","path":"pyfeats/histogram/correlogram.py","file_url":"https://github.com/giakou4/pyfeats/blob/HEAD/pyfeats/histogram/correlogram.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ddf47684b8425901"}},{"code_sha256":"634317f9c741abd3","code_sha256_prefix":"634317f9c741abd3","entry":"dwt_features","repo":"giakou4/pyfeats","repo_kind":"listed","path":"pyfeats/multiscale/dwt.py","file_url":"https://github.com/giakou4/pyfeats/blob/HEAD/pyfeats/multiscale/dwt.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"634317f9c741abd3"}},{"code_sha256":"5bd550cf0a598b22","code_sha256_prefix":"5bd550cf0a598b22","entry":"get_args","repo":"AndrewAtanov/simclr-pytorch","repo_kind":"listed","path":"myexman/index.py","file_url":"https://github.com/AndrewAtanov/simclr-pytorch/blob/HEAD/myexman/index.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/get-args","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5bd550cf0a598b22"}},{"code_sha256":"9e33b14b41b316ca","code_sha256_prefix":"9e33b14b41b316ca","entry":"gt_features","repo":"giakou4/pyfeats","repo_kind":"listed","path":"pyfeats/multiscale/gt.py","file_url":"https://github.com/giakou4/pyfeats/blob/HEAD/pyfeats/multiscale/gt.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9e33b14b41b316ca"}},{"code_sha256":"459939c749c8fd3f","code_sha256_prefix":"459939c749c8fd3f","entry":"none2none","repo":"AndrewAtanov/simclr-pytorch","repo_kind":"listed","path":"myexman/index.py","file_url":"https://github.com/AndrewAtanov/simclr-pytorch/blob/HEAD/myexman/index.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"459939c749c8fd3f"}},{"code_sha256":"7e7b54ff38780a53","code_sha256_prefix":"7e7b54ff38780a53","entry":"save_checkpoint","repo":"Mayurji/SimCLR","repo_kind":"listed","path":"SimCLR.py","file_url":"https://github.com/Mayurji/SimCLR/blob/HEAD/SimCLR.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/save-checkpoint","census":null,"licence":"GPL-3.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GPL-3.0, as GitHub detects it on this paper's repository, Mayurji/SimCLR, is not in the permissive set Syntology serves inline","mcp_get_code":{"code_sha256":"7e7b54ff38780a53"}},{"code_sha256":"75b95f2eaa47b97b","code_sha256_prefix":"75b95f2eaa47b97b","entry":"save_loss_plot","repo":"talipucar/PyFlow_SimCLR","repo_kind":"listed","path":"src/model.py","file_url":"https://github.com/talipucar/PyFlow_SimCLR/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, talipucar/PyFlow_SimCLR when it was checked","mcp_get_code":{"code_sha256":"75b95f2eaa47b97b"}},{"code_sha256":"20855bdedf943b8f","code_sha256_prefix":"20855bdedf943b8f","entry":"set_seed","repo":"talipucar/PyFlow_SimCLR","repo_kind":"listed","path":"src/model.py","file_url":"https://github.com/talipucar/PyFlow_SimCLR/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/set-seed","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, talipucar/PyFlow_SimCLR when it was checked","mcp_get_code":{"code_sha256":"20855bdedf943b8f"}},{"code_sha256":"b81f9f44d8624e5f","code_sha256_prefix":"b81f9f44d8624e5f","entry":"swt_features","repo":"giakou4/pyfeats","repo_kind":"listed","path":"pyfeats/multiscale/swt.py","file_url":"https://github.com/giakou4/pyfeats/blob/HEAD/pyfeats/multiscale/swt.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b81f9f44d8624e5f"}},{"code_sha256":"667eaf3785a1c4a9","code_sha256_prefix":"667eaf3785a1c4a9","entry":"train_val","repo":"leftthomas/SimCLR","repo_kind":"listed","path":"linear.py","file_url":"https://github.com/leftthomas/SimCLR/blob/HEAD/linear.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/train-val","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, leftthomas/SimCLR when it was checked","mcp_get_code":{"code_sha256":"667eaf3785a1c4a9"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"8af447b634fcabfb14a140c93d4997800441673dc99ab27d9f00971a3aa85a8c","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}