{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/learning-transferable-visual-models-from","title":"Learning Transferable Visual Models From Natural Language Supervision","arxiv_id":"2103.00020","date":"2021-02-26","proceeding":null,"authors":["Alec Radford","Jong Wook Kim","Chris Hallacy","Aditya Ramesh","Gabriel Goh","Sandhini Agarwal","Girish Sastry","Amanda Askell","Pamela Mishkin","Jack Clark","Gretchen Krueger","Ilya Sutskever"],"abstract":"State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any other visual concept. Learning directly from raw text about images is a promising alternative which leverages a much broader source of supervision. We demonstrate that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet. After pre-training, natural language is used to reference learned visual concepts (or describe new ones) enabling zero-shot transfer of the model to downstream tasks. We study the performance of this approach by benchmarking on over 30 different existing computer vision datasets, spanning tasks such as OCR, action recognition in videos, geo-localization, and many types of fine-grained object classification. The model transfers non-trivially to most tasks and is often competitive with a fully supervised baseline without the need for any dataset specific training. For instance, we match the accuracy of the original ResNet-50 on ImageNet zero-shot without needing to use any of the 1.28 million training examples it was trained on. We release our code and pre-trained model weights at https://github.com/OpenAI/CLIP.","url_abs":"https://arxiv.org/abs/2103.00020v1","url_pdf":"https://arxiv.org/pdf/2103.00020v1.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":"learning-transferable-visual-models-from","repo_url":"https://github.com/openai/CLIP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/AndresPMD/Clip_CMR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/FreddeFrallan/Multilingual-CLIP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/Gahyeonkim09/AAPL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/IMvision12/keras-vision-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/Kaushalya/medclip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/NYU-DICE-Lab/open_clip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/SforAiDl/CountCLIP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/YvanG/VQGAN-CLIP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/ZackPashkin/text2cartoon-pytorch-CLIP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/a736875071/clip-vit-large-patch14","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/ai-forever/ru-clip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/ajayjain/vectorascent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/apple/ml-mobileclip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/armaank/archlectures","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/azshue/TPT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/baskargroup/Arboretum","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/baskargroup/biotrove","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/bespontaneous/proteus-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/borisdayma/clip-jax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/brown-palm/ObjectPrompt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/bruthyu/bpt-vlm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/buyeah1109/KEN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/buyeah1109/finc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/clip-italian/clip-italian","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/dhansmair/flamingo-mini","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/eify/open_clip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/eps696/aphantasia","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/ericyinyzy/vlattack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/facebookresearch/brainmagick","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/facebookresearch/clip-rocket","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/facebookresearch/vissl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/fastscience-ai/medflamingo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/fiabdu/Commonly-Interesting-Images","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/filipbasara0/simple-clip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/giantseaweed/decree","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/iejMac/ScriptWriter","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/jhaprince/multibully","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/klemens-floege/oneprot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/kynkaat/role-of-imagenet-classes-in-fid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/leolee99/CLIP_ITM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/linjieli222/hero_video_feature_extractor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/lunaproject22/rpa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/madrylab/pretraining-distribution-shift-robustness","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/mainaksingha01/applenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/mainaksingha01/odg-clip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/mertyg/post-hoc-cbm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/michi-3000/eyeclip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/minhanh151/pre","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/minhanh151/respro","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/ml-jku/cloob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/mlbio-epfl/turtle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/mlfoundations/open_clip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/moein-shariatnia/OpenAI-CLIP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/muzairkhattak/multimodal-prompt-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/nahidalam/open_clip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/nopperl/clip_arxiv_pmc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/prabhupad26/100daysofML","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/pseulki/rococo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/ramanakshay/clip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/redcaps-dataset/redcaps-downloader","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/rinnakk/japanese-clip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/s-a-malik/multi-few","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/sajjjadayobi/CLIPfa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/salesforce/pb-ovd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/sberbank-ai/ru-clip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/shivammehta25/clip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/shunk031/simple-aesthetics-predictor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/sincerass/mvlpt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/sithu31296/simple-object-tracking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/taited/clip-score","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/ylqi/count-anything","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/yuuun/clip_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/zhangxu0963/npc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/clip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/clip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/OML-Team/open-metric-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/PaddlePaddle/PASSL/blob/main/docs/Train_CLIP_model.md","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/alibaba/EasyNLP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/pwc-1/Paper-8/tree/main/clip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/shkarupa-alex/tfclip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-transferable-visual-models-from","repo_url":"https://github.com/towhee-io/towhee","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"hateful-meme-classification","task_name":"Hateful Meme Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-to-text-retrieval","task_name":"Image-to-Text Retrieval"},{"task_slug":"long-tail-learning","task_name":"Long-tail Learning"},{"task_slug":"meme-classification","task_name":"Meme Classification"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"object-categorization","task_name":"Object Categorization"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"open-vocabulary-attribute-detection","task_name":"Open Vocabulary Attribute Detection"},{"task_slug":"out-of-distribution-generalization","task_name":"Out-of-Distribution Generalization"},{"task_slug":"preference-mapping","task_name":"Preference Mapping"},{"task_slug":"prompt-engineering","task_name":"Prompt Engineering"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"},{"task_slug":"temporal-relation-extraction","task_name":"Temporal Relation Extraction"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"text-based-person-retrieval-with-noisy","task_name":"Text-based Person Retrieval with Noisy Correspondence"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"},{"task_slug":"zero-shot-cross-modal-retrieval","task_name":"Zero-Shot Cross-Modal Retrieval"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":"zero-shot-transfer-image-classification","task_name":"Zero-Shot Transfer Image Classification"},{"task_slug":"zero-shot-text-to-image-retrieval","task_name":"Zero-shot Text-to-Image Retrieval"},{"task_slug":"geo-localization","task_name":"geo-localization"}],"methods":[{"method_slug":"3d-cnn","method_name":"3D CNN"},{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[{"slug":"clip","name":"CLIP","full_name":"Contrastive Language-Image Pre-training"}],"results":[{"leaderboard":"/sota/action-recognition-on-rareact","task":"Action Recognition","dataset":"RareAct","model":"CLIP","rank_in_archive_order":2,"of":3,"metrics":{"mWAP":"40.7"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-0","task":"Few-Shot Image Classification","dataset":"ImageNet - 0-Shot","model":"CLIP (ViT B/32)","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"63.2%"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-0","task":"Few-Shot Image Classification","dataset":"ImageNet - 0-Shot","model":"CLIP (ResNet50)","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"59.6%"},"uses_additional_data":true},{"leaderboard":"/sota/hateful-meme-classification-on-harm-p","task":"Hateful Meme Classification","dataset":"Harm-P","model":"CLIP","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"80.6","F1":"80.3"},"uses_additional_data":false},{"leaderboard":"/sota/hateful-meme-classification-on-pridemm","task":"Hateful Meme Classification","dataset":"PrideMM","model":"CLIP (fine-tuned)","rank_in_archive_order":7,"of":7,"metrics":{"Accuracy":"72.4","F1":"72.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"CLIP","rank_in_archive_order":10,"of":106,"metrics":{"Top-1 Accuracy":"72.3"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-omnibenchmark","task":"Image Classification","dataset":"OmniBenchmark","model":"CLIP-RN50","rank_in_archive_order":5,"of":22,"metrics":{"Average Top-1 Accuracy":"42.1"},"uses_additional_data":true},{"leaderboard":"/sota/image-to-text-retrieval-on-coco","task":"Image-to-Text Retrieval","dataset":"COCO (Common Objects in Context)","model":"CLIP (zero-shot)","rank_in_archive_order":5,"of":9,"metrics":{"Recall@1":"58.4","Recall@10":"88.1","Recall@5":"81.5"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-coco-mlt","task":"Long-tail Learning","dataset":"COCO-MLT","model":"CLIP(ViT-B/16)","rank_in_archive_order":2,"of":13,"metrics":{"Average mAP":"60.17"},"uses_additional_data":true},{"leaderboard":"/sota/long-tail-learning-on-coco-mlt","task":"Long-tail Learning","dataset":"COCO-MLT","model":"CLIP(ResNet-50)","rank_in_archive_order":5,"of":13,"metrics":{"Average mAP":"56.19"},"uses_additional_data":true},{"leaderboard":"/sota/long-tail-learning-on-voc-mlt","task":"Long-tail Learning","dataset":"VOC-MLT","model":"CLIP(ViT-B/16)","rank_in_archive_order":2,"of":13,"metrics":{"Average mAP":"85.77"},"uses_additional_data":true},{"leaderboard":"/sota/long-tail-learning-on-voc-mlt","task":"Long-tail Learning","dataset":"VOC-MLT","model":"CLIP(ResNet-50)","rank_in_archive_order":4,"of":13,"metrics":{"Average mAP":"84.30"},"uses_additional_data":true},{"leaderboard":"/sota/meme-classification-on-hateful-memes","task":"Meme Classification","dataset":"Hateful Memes","model":"CLIP (zero-shot)","rank_in_archive_order":17,"of":17,"metrics":{"ROC-AUC":"0.661"},"uses_additional_data":false},{"leaderboard":"/sota/meme-classification-on-multioff","task":"Meme Classification","dataset":"MultiOFF","model":"CLIP","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy":"62.4","F1":"48.1"},"uses_additional_data":false},{"leaderboard":"/sota/object-categorization-on-grit","task":"Object Categorization","dataset":"GRIT","model":"CLIP","rank_in_archive_order":3,"of":4,"metrics":{"Categorization (ablation)":"48.1"},"uses_additional_data":false},{"leaderboard":"/sota/object-recognition-on-shape-bias","task":"Object Recognition","dataset":"shape bias","model":"CLIP (ViT-B)","rank_in_archive_order":6,"of":18,"metrics":{"shape bias":"79.9"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-attribute-detection-on-ovad-1","task":"Open Vocabulary Attribute Detection","dataset":"OVAD-Box benchmark","model":"CLIP VIT-B16","rank_in_archive_order":7,"of":7,"metrics":{"mean average precision":"16.6"},"uses_additional_data":true},{"leaderboard":"/sota/prompt-engineering-on-caltech-101","task":"Prompt Engineering","dataset":"Caltech-101","model":"CLIP","rank_in_archive_order":14,"of":14,"metrics":{"Harmonic mean":"95.40"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-dtd","task":"Prompt Engineering","dataset":"DTD","model":"CLIP","rank_in_archive_order":14,"of":14,"metrics":{"Harmonic mean":"56.37"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-eurosat","task":"Prompt Engineering","dataset":"EuroSAT","model":"CLIP","rank_in_archive_order":14,"of":14,"metrics":{"Harmonic mean":"60.03"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-fgvc-aircraft","task":"Prompt Engineering","dataset":"FGVC-Aircraft","model":"CLIP","rank_in_archive_order":13,"of":14,"metrics":{"Harmonic mean":"31.09"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-imagenet","task":"Prompt Engineering","dataset":"ImageNet","model":"CLIP","rank_in_archive_order":15,"of":15,"metrics":{"Harmonic mean":"70.22"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-imagenet-v2","task":"Prompt Engineering","dataset":"ImageNet V2","model":"CLIP","rank_in_archive_order":8,"of":8,"metrics":{"Top-1 accuracy %":"60.83"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-imagenet-a","task":"Prompt Engineering","dataset":"ImageNet-A","model":"CLIP","rank_in_archive_order":9,"of":9,"metrics":{"Top-1 accuracy %":"47.77"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-imagenet-r","task":"Prompt Engineering","dataset":"ImageNet-R","model":"CLIP","rank_in_archive_order":9,"of":9,"metrics":{"Top-1 accuracy %":"73.96"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-imagenet-s","task":"Prompt Engineering","dataset":"ImageNet-S","model":"CLIP","rank_in_archive_order":9,"of":9,"metrics":{"Top-1 accuracy %":"46.15"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-oxford-102-flower","task":"Prompt Engineering","dataset":"Oxford 102 Flower","model":"CLIP","rank_in_archive_order":14,"of":14,"metrics":{"Harmonic mean":"74.83"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-oxford-iiit-pet-dataset","task":"Prompt Engineering","dataset":"Oxford-IIIT Pet Dataset","model":"CLIP","rank_in_archive_order":14,"of":14,"metrics":{"Harmonic mean":"94.12"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-sun397","task":"Prompt Engineering","dataset":"SUN397","model":"CLIP","rank_in_archive_order":14,"of":14,"metrics":{"Harmonic mean":"72.23"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-stanford-cars-1","task":"Prompt Engineering","dataset":"Stanford Cars","model":"CLIP","rank_in_archive_order":14,"of":14,"metrics":{"Harmonic mean":"68.65"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-ucf101","task":"Prompt Engineering","dataset":"UCF101","model":"CLIP","rank_in_archive_order":14,"of":14,"metrics":{"Harmonic mean":"73.85"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-16","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 0.2% labeled data","model":"CLIP (ResNet-50)","rank_in_archive_order":3,"of":3,"metrics":{"ImageNet Top-1 Accuracy":"40%"},"uses_additional_data":true},{"leaderboard":"/sota/text-based-person-retrieval-with-noisy","task":"Text-based Person Retrieval with Noisy Correspondence","dataset":"CUHK-PEDES","model":"CLIP-C","rank_in_archive_order":4,"of":6,"metrics":{"Rank 10":"90.89","Rank-1":"66.41","Rank-5":"85.15","mAP":"59.36","mINP":"43.02"},"uses_additional_data":true},{"leaderboard":"/sota/text-based-person-retrieval-with-noisy-1","task":"Text-based Person Retrieval with Noisy Correspondence","dataset":"ICFG-PEDES","model":"CLIP-C","rank_in_archive_order":4,"of":6,"metrics":{"Rank 1":"55.25","Rank-10":"81.32","Rank-5":"74.76","mAP":"31.09","mINP":"4.94"},"uses_additional_data":true},{"leaderboard":"/sota/text-based-person-retrieval-with-noisy-2","task":"Text-based Person Retrieval with Noisy Correspondence","dataset":"RSTPReid","model":"CLIP-C","rank_in_archive_order":4,"of":6,"metrics":{"Rank 1":"54.45","Rank 10":"86.70","Rank 5":"77.80","mAP":"42.58","mINP":"21.38"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-cross-modal-retrieval-on-coco-2014","task":"Zero-Shot Cross-Modal Retrieval","dataset":"COCO 2014","model":"CLIP","rank_in_archive_order":15,"of":18,"metrics":{"Image-to-text R@1":"58.4","Image-to-text R@10":"88.1","Image-to-text R@5":"81.5","Text-to-image R@1":"37.8","Text-to-image R@10":"72.2","Text-to-image R@5":"62.4"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-cross-modal-retrieval-on-flickr30k","task":"Zero-Shot Cross-Modal Retrieval","dataset":"Flickr30k","model":"CLIP","rank_in_archive_order":15,"of":22,"metrics":{"Image-to-text R@1":"88.0","Image-to-text R@10":"99.4","Image-to-text R@5":"98.7","Text-to-image R@1":"68.7","Text-to-image R@10":"95.2","Text-to-image R@5":"90.6"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-learning-on-coco-mlt","task":"Zero-Shot Learning","dataset":"COCO-MLT","model":"ResNet-50","rank_in_archive_order":1,"of":2,"metrics":{"Average mAP":"56.19"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-learning-on-coco-mlt","task":"Zero-Shot Learning","dataset":"COCO-MLT","model":"ViT-B/16","rank_in_archive_order":2,"of":2,"metrics":{"Average mAP":"60.17"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-learning-on-voc-mlt","task":"Zero-Shot Learning","dataset":"VOC-MLT","model":"CLIP(ResNet-50)","rank_in_archive_order":1,"of":2,"metrics":{"Average mAP":"84.30"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-learning-on-voc-mlt","task":"Zero-Shot Learning","dataset":"VOC-MLT","model":"CLIP(ViT-B/16)","rank_in_archive_order":2,"of":2,"metrics":{"Average mAP":"85.77"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-1","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet","model":"CLIP（ViT-L/14-336px）","rank_in_archive_order":17,"of":23,"metrics":{"Accuracy (Private)":"76.2"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-1","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet","model":"CLIP (ResNet50)","rank_in_archive_order":21,"of":23,"metrics":{"Accuracy (Private)":"59.6"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-1","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet","model":"CLIP","rank_in_archive_order":23,"of":23,"metrics":{"Accuracy (Public)":" 31.3"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-3","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet V2","model":"CLIP","rank_in_archive_order":11,"of":13,"metrics":{"Accuracy (Private)":"70.1","Accuracy (Public)":"-"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-5","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet-A","model":"CLIP","rank_in_archive_order":10,"of":13,"metrics":{"Accuracy (Private)":"77.2","Accuracy (Public)":"-"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-4","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet-R","model":"CLIP","rank_in_archive_order":10,"of":12,"metrics":{"Accuracy":"88.9"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-6","task":"Zero-Shot Transfer Image Classification","dataset":"ObjectNet","model":"CLIP","rank_in_archive_order":8,"of":9,"metrics":{"Accuracy (Private)":"72.3","Accuracy (Public)":"-"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-2","task":"Zero-Shot Transfer Image Classification","dataset":"SUN","model":"CLIP","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy":"58.5"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on","task":"Zero-Shot Transfer Image Classification","dataset":"aYahoo","model":"CLIP","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"98.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.00020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.00020"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/openai/CLIP","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kynkaat/role-of-imagenet-classes-in-fid","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mertyg/post-hoc-cbm","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/mlfoundations/open_clip","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sberbank-ai/ru-clip","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/OML-Team/open-metric-learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sincerass/mvlpt","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nopperl/clip_arxiv_pmc","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mainaksingha01/applenet","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/FreddeFrallan/Multilingual-CLIP","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AndresPMD/Clip_CMR","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/brainmagick","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/baskargroup/biotrove","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jhaprince/multibully","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/a736875071/clip-vit-large-patch14","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/iejMac/ScriptWriter","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/salesforce/pb-ovd","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/klemens-floege/oneprot","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sajjjadayobi/CLIPfa","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/clip","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/michi-3000/eyeclip","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ZackPashkin/text2cartoon-pytorch-CLIP","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/prabhupad26/100daysofML","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YvanG/VQGAN-CLIP","reach":null}],"summary":{"ran_fixture":4,"ran_draft_wrong":10,"ran_violates":1,"ran_honours":1,"unverified":4},"by_repo_kind":{"listed":{"samples":10,"ran":9,"repositories":6}},"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":16,"samples":[{"code_sha256_prefix":"2e59707d16d21473","entry":"accuracy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"2e59707d16d21473"}},{"code_sha256_prefix":"441ae80dd4f616f3","entry":"avg_entropy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"441ae80dd4f616f3"}},{"code_sha256_prefix":"4ea4d130ce4030a1","entry":"contrastive_loss","repo":"filipbasara0/simple-clip","repo_kind":"listed","path":"simple_clip/clip.py","file_url":"https://github.com/filipbasara0/simple-clip/blob/HEAD/simple_clip/clip.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4ea4d130ce4030a1"}},{"code_sha256_prefix":"f19962ebb134b3d7","entry":"convert_to_custom_text_state_dict","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"f19962ebb134b3d7"}},{"code_sha256_prefix":"63e6e57b587c3aa8","entry":"cross_entropy","repo":"moein-shariatnia/OpenAI-CLIP","repo_kind":"listed","path":"CLIP.py","file_url":"https://github.com/moein-shariatnia/OpenAI-CLIP/blob/HEAD/CLIP.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"63e6e57b587c3aa8"}},{"code_sha256_prefix":"7f39fa83f26c97c7","entry":"domain_text_loss","repo":"mainaksingha01/odg-clip","repo_kind":"listed","path":"pacs.py","file_url":"https://github.com/mainaksingha01/odg-clip/blob/HEAD/pacs.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7f39fa83f26c97c7"}},{"code_sha256_prefix":"dcd422d66b0581d8","entry":"get_cast_dtype","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"code_sha256_prefix":"b476c8cfbf0f1f47","entry":"get_input_dtype","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"b476c8cfbf0f1f47"}},{"code_sha256_prefix":"1c4b58a58ab65b12","entry":"lanczos","repo":"YvanG/VQGAN-CLIP","repo_kind":"listed","path":"CLIP_VQGAN.py","file_url":"https://github.com/YvanG/VQGAN-CLIP/blob/HEAD/CLIP_VQGAN.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1c4b58a58ab65b12"}},{"code_sha256_prefix":"f0eb8193f86d363b","entry":"mean_per_class","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"f0eb8193f86d363b"}},{"code_sha256_prefix":"1b17b45e4d751423","entry":"misc_measures","repo":"michi-3000/eyeclip","repo_kind":"listed","path":"zero_shot.py","file_url":"https://github.com/michi-3000/eyeclip/blob/HEAD/zero_shot.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1b17b45e4d751423"}},{"code_sha256_prefix":"8c580a6820115461","entry":"ramp","repo":"YvanG/VQGAN-CLIP","repo_kind":"listed","path":"CLIP_VQGAN.py","file_url":"https://github.com/YvanG/VQGAN-CLIP/blob/HEAD/CLIP_VQGAN.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8c580a6820115461"}},{"code_sha256_prefix":"3ce4d11e58de02ad","entry":"select_confident_samples","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"3ce4d11e58de02ad"}},{"code_sha256_prefix":"67c4ef5004396e02","entry":"siglip_loss","repo":"filipbasara0/simple-clip","repo_kind":"listed","path":"simple_clip/clip.py","file_url":"https://github.com/filipbasara0/simple-clip/blob/HEAD/simple_clip/clip.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"67c4ef5004396e02"}},{"code_sha256_prefix":"86a64cd8e1771cc5","entry":"sinc","repo":"YvanG/VQGAN-CLIP","repo_kind":"listed","path":"CLIP_VQGAN.py","file_url":"https://github.com/YvanG/VQGAN-CLIP/blob/HEAD/CLIP_VQGAN.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"86a64cd8e1771cc5"}},{"code_sha256_prefix":"8e95157106d1df8c","entry":"trace_model","repo":"NYU-DICE-Lab/open_clip","repo_kind":"listed","path":"src/open_clip/model.py","file_url":"https://github.com/NYU-DICE-Lab/open_clip/blob/HEAD/src/open_clip/model.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,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8e95157106d1df8c"}},{"code_sha256_prefix":"903b104e9c495329","entry":"build_model_from_openai_state_dict","repo":"NYU-DICE-Lab/open_clip","repo_kind":"listed","path":"src/open_clip/model.py","file_url":"https://github.com/NYU-DICE-Lab/open_clip/blob/HEAD/src/open_clip/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"903b104e9c495329"}},{"code_sha256_prefix":"1cd2728a84872357","entry":"has_ddp_wrapper","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"1cd2728a84872357"}},{"code_sha256_prefix":"f565e9c6316d8c64","entry":"remove_ddp_wrapper","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"f565e9c6316d8c64"}},{"code_sha256_prefix":"631c70c26c0fcedf","entry":"test_time_tuning","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"631c70c26c0fcedf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}