{"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":"/sota/image-classification-on-objectnet","task":{"name":"Image Classification","url":"/task/image-classification","note":null},"dataset":{"name":"ObjectNet","url":"/dataset/objectnet"},"category":"Computer Vision","categories":["Adversarial","Computer Vision"],"category_note":null,"description":"**Image Classification** is a fundamental task in vision recognition that aims to understand and categorize an image as a whole under a specific label. Unlike [object detection](/task/object-detection), which involves classification and location of multiple objects within an image, image classification typically pertains to single-object images. When the classification becomes highly detailed or reaches instance-level, it is often referred to as [image retrieval](/task/image-retrieval), which also involves finding similar images in a large database.\r\n\r\n\r\n<span class=\"description-source\">Source: [Metamorphic Testing for Object Detection Systems ](https://arxiv.org/abs/1912.12162)</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Top-1 Accuracy","Top-5 Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction; the tokens 'score' and 'time' are not used on this page); null = not inferred, chart draws points only","by_metric":{"Top-1 Accuracy":"higher","Top-5 Accuracy":"higher"}},"counts":{"rows":106,"rows_with_code":83,"rows_with_paper_page":106,"rows_dated":106,"rows_using_additional_data":104},"rows":[{"rank_in_archive_order":1,"model":"CoCa","metrics":{"Top-1 Accuracy":"82.7"},"uses_additional_data":true,"paper_date":"2022-05-04","paper":"/paper/coca-contrastive-captioners-are-image-text","paper_url":"https://arxiv.org/abs/2205.01917v2","paper_title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","code":"https://github.com/mlfoundations/open_clip","n_code_links":6,"official":null,"syntology":{"n_ran":10,"n_constructed":5,"n_ran_checked":9,"n_instrument":1,"n_unverified":7,"n_samples":17,"n_pointer_only_licence":2,"sample_list":"/paper/coca-contrastive-captioners-are-image-text#ran","syntology_url":"https://syntology.ai/paper/2205.01917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01917"}}}},{"rank_in_archive_order":2,"model":"LiT","metrics":{"Top-1 Accuracy":"82.5"},"uses_additional_data":true,"paper_date":"2021-11-15","paper":"/paper/lit-zero-shot-transfer-with-locked-image-text","paper_url":"https://arxiv.org/abs/2111.07991v3","paper_title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","code":"https://github.com/mlfoundations/open_clip","n_code_links":5,"official":null,"syntology":null},{"rank_in_archive_order":3,"model":"BASIC","metrics":{"Top-1 Accuracy":"82.3"},"uses_additional_data":true,"paper_date":"2021-11-19","paper":"/paper/combined-scaling-for-zero-shot-transfer","paper_url":"https://arxiv.org/abs/2111.10050v3","paper_title":"Combined Scaling for Zero-shot Transfer Learning","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":4,"model":"EVA-02-CLIP-E/14+","metrics":{"Top-1 Accuracy":"79.6"},"uses_additional_data":true,"paper_date":"2023-03-27","paper":"/paper/eva-clip-improved-training-techniques-for","paper_url":"https://arxiv.org/abs/2303.15389v1","paper_title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","code":"https://github.com/baaivision/eva","n_code_links":4,"official":{"repos":["baaivision/eva"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/eva-clip-improved-training-techniques-for#ran","syntology_url":"https://syntology.ai/paper/2303.15389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.15389"}}}},{"rank_in_archive_order":5,"model":"Baseline (ViT-G/14)","metrics":{"Top-1 Accuracy":"79.03"},"uses_additional_data":true,"paper_date":"2022-03-10","paper":"/paper/model-soups-averaging-weights-of-multiple","paper_url":"https://arxiv.org/abs/2203.05482v3","paper_title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","code":"https://github.com/mlfoundations/model-soups","n_code_links":6,"official":{"repos":["mlfoundations/model-soups"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":7,"n_samples":17,"n_pointer_only_licence":0,"sample_list":"/paper/model-soups-averaging-weights-of-multiple#ran","syntology_url":"https://syntology.ai/paper/2203.05482","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.05482"}}}},{"rank_in_archive_order":6,"model":"Model soups (ViT-G/14)","metrics":{"Top-1 Accuracy":"78.52"},"uses_additional_data":true,"paper_date":"2022-03-10","paper":"/paper/model-soups-averaging-weights-of-multiple","paper_url":"https://arxiv.org/abs/2203.05482v3","paper_title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","code":"https://github.com/mlfoundations/model-soups","n_code_links":6,"official":{"repos":["mlfoundations/model-soups"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":7,"n_samples":17,"n_pointer_only_licence":0,"sample_list":"/paper/model-soups-averaging-weights-of-multiple#ran","syntology_url":"https://syntology.ai/paper/2203.05482","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.05482"}}}},{"rank_in_archive_order":7,"model":"MAWS (ViT-6.5B)","metrics":{"Top-1 Accuracy":"77.9"},"uses_additional_data":true,"paper_date":"2023-03-23","paper":"/paper/the-effectiveness-of-mae-pre-pretraining-for","paper_url":"https://arxiv.org/abs/2303.13496v3","paper_title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","code":"https://github.com/facebookresearch/maws","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":8,"model":"MAWS (ViT-2B)","metrics":{"Top-1 Accuracy":"75.8"},"uses_additional_data":true,"paper_date":"2023-03-23","paper":"/paper/the-effectiveness-of-mae-pre-pretraining-for","paper_url":"https://arxiv.org/abs/2303.13496v3","paper_title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","code":"https://github.com/facebookresearch/maws","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":9,"model":"MAWS (ViT-H)","metrics":{"Top-1 Accuracy":"72.6"},"uses_additional_data":true,"paper_date":"2023-03-23","paper":"/paper/the-effectiveness-of-mae-pre-pretraining-for","paper_url":"https://arxiv.org/abs/2303.13496v3","paper_title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","code":"https://github.com/facebookresearch/maws","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":10,"model":"CLIP","metrics":{"Top-1 Accuracy":"72.3"},"uses_additional_data":true,"paper_date":"2021-02-26","paper":"/paper/learning-transferable-visual-models-from","paper_url":"https://arxiv.org/abs/2103.00020v1","paper_title":"Learning Transferable Visual Models From Natural Language Supervision","code":"https://github.com/openai/CLIP","n_code_links":82,"official":{"repos":["openai/CLIP"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":16,"n_constructed":0,"n_ran_checked":2,"n_instrument":14,"n_unverified":4,"n_samples":20,"n_pointer_only_licence":16,"sample_list":"/paper/learning-transferable-visual-models-from#ran","syntology_url":"https://syntology.ai/paper/2103.00020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.00020"}}}},{"rank_in_archive_order":11,"model":"ALIGN","metrics":{"Top-1 Accuracy":"72.2"},"uses_additional_data":true,"paper_date":"2021-11-19","paper":"/paper/combined-scaling-for-zero-shot-transfer","paper_url":"https://arxiv.org/abs/2111.10050v3","paper_title":"Combined Scaling for Zero-shot Transfer Learning","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":12,"model":"WiSE-FT","metrics":{"Top-1 Accuracy":"72.1"},"uses_additional_data":true,"paper_date":"2021-09-04","paper":"/paper/robust-fine-tuning-of-zero-shot-models","paper_url":"https://arxiv.org/abs/2109.01903v3","paper_title":"Robust fine-tuning of zero-shot models","code":"https://github.com/mlfoundations/wise-ft","n_code_links":3,"official":{"repos":["mlfoundations/wise-ft"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":1,"sample_list":"/paper/robust-fine-tuning-of-zero-shot-models#ran","syntology_url":"https://syntology.ai/paper/2109.01903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.01903"}}}},{"rank_in_archive_order":13,"model":"ViT-e","metrics":{"Top-1 Accuracy":"72.0"},"uses_additional_data":false,"paper_date":"2022-09-14","paper":"/paper/pali-a-jointly-scaled-multilingual-language","paper_url":"https://arxiv.org/abs/2209.06794v4","paper_title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","code":"https://github.com/google-research/big_vision","n_code_links":1,"official":{"repos":["google-research/big_vision"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/pali-a-jointly-scaled-multilingual-language#ran","syntology_url":"https://syntology.ai/paper/2209.06794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.06794"}}}},{"rank_in_archive_order":14,"model":"ViT-G/14","metrics":{"Top-1 Accuracy":"70.53"},"uses_additional_data":true,"paper_date":"2021-06-08","paper":"/paper/scaling-vision-transformers","paper_url":"https://arxiv.org/abs/2106.04560v2","paper_title":"Scaling Vision Transformers","code":"https://github.com/google-research/big_vision","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":15,"model":"SWAG (ViT H/14)","metrics":{"Top-1 Accuracy":"69.5"},"uses_additional_data":true,"paper_date":"2022-01-20","paper":"/paper/revisiting-weakly-supervised-pre-training-of","paper_url":"https://arxiv.org/abs/2201.08371v2","paper_title":"Revisiting Weakly Supervised Pre-Training of Visual Perception Models","code":"https://github.com/facebookresearch/SWAG","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":16,"model":"NS (Eff.-L2)","metrics":{"Top-1 Accuracy":"68.5"},"uses_additional_data":true,"paper_date":"2021-06-08","paper":"/paper/scaling-vision-transformers","paper_url":"https://arxiv.org/abs/2106.04560v2","paper_title":"Scaling Vision Transformers","code":"https://github.com/google-research/big_vision","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":17,"model":"RegNetY 128GF (Platt)","metrics":{"Top-1 Accuracy":"64.3"},"uses_additional_data":true,"paper_date":"2022-01-20","paper":"/paper/revisiting-weakly-supervised-pre-training-of","paper_url":"https://arxiv.org/abs/2201.08371v2","paper_title":"Revisiting Weakly Supervised Pre-Training of Visual Perception Models","code":"https://github.com/facebookresearch/SWAG","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":18,"model":"LLE (ViT-H/14, MAE, Edge Aug)","metrics":{"Top-1 Accuracy":"60.78"},"uses_additional_data":false,"paper_date":"2022-12-09","paper":"/paper/a-whac-a-mole-dilemma-shortcuts-come-in","paper_url":"https://arxiv.org/abs/2212.04825v2","paper_title":"A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others","code":"https://github.com/facebookresearch/Whac-A-Mole","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":19,"model":"SEER (RegNet10B)","metrics":{"Top-1 Accuracy":"60.2"},"uses_additional_data":true,"paper_date":"2022-02-16","paper":"/paper/vision-models-are-more-robust-and-fair-when","paper_url":"https://arxiv.org/abs/2202.08360v2","paper_title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","code":"https://github.com/facebookresearch/vissl","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":20,"model":"ViT H/14 (Platt)","metrics":{"Top-1 Accuracy":"60"},"uses_additional_data":true,"paper_date":"2022-01-20","paper":"/paper/revisiting-weakly-supervised-pre-training-of","paper_url":"https://arxiv.org/abs/2201.08371v2","paper_title":"Revisiting Weakly Supervised Pre-Training of Visual Perception Models","code":"https://github.com/facebookresearch/SWAG","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":21,"model":"BiT-L (ResNet-152x4)","metrics":{"Top-1 Accuracy":"58.7","Top-5 Accuracy":"80"},"uses_additional_data":true,"paper_date":"2019-12-24","paper":"/paper/large-scale-learning-of-general-visual","paper_url":"https://arxiv.org/abs/1912.11370v3","paper_title":"Big Transfer (BiT): General Visual Representation Learning","code":"https://github.com/google-research/big_transfer","n_code_links":9,"official":{"repos":["google-research/big_transfer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":0,"sample_list":"/paper/large-scale-learning-of-general-visual#ran","syntology_url":"https://syntology.ai/paper/1912.11370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.11370"}}}},{"rank_in_archive_order":22,"model":"ViT L/16 (Platt)","metrics":{"Top-1 Accuracy":"57.3"},"uses_additional_data":true,"paper_date":"2022-01-20","paper":"/paper/revisiting-weakly-supervised-pre-training-of","paper_url":"https://arxiv.org/abs/2201.08371v2","paper_title":"Revisiting Weakly Supervised Pre-Training of Visual Perception Models","code":"https://github.com/facebookresearch/SWAG","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":23,"model":"Vit B/16 (Bamboo)","metrics":{"Top-1 Accuracy":"53.9"},"uses_additional_data":true,"paper_date":"2022-03-15","paper":"/paper/bamboo-building-mega-scale-vision-dataset","paper_url":"https://arxiv.org/abs/2203.07845v2","paper_title":"Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy","code":"https://github.com/zhangyuanhan-ai/bamboo","n_code_links":2,"official":{"repos":["davidzhangyuanhan/bamboo","zhangyuanhan-ai/bamboo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/bamboo-building-mega-scale-vision-dataset#ran","syntology_url":"https://syntology.ai/paper/2203.07845","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.07845"}}}},{"rank_in_archive_order":24,"model":"AR-L (Opt Relevance)","metrics":{"Top-1 Accuracy":"52.0","Top-5 Accuracy":"73.5"},"uses_additional_data":true,"paper_date":"2022-06-02","paper":"/paper/optimizing-relevance-maps-of-vision","paper_url":"https://arxiv.org/abs/2206.01161v1","paper_title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","code":"https://github.com/hila-chefer/robustvit","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":25,"model":"ALIGN-MRL","metrics":{"Top-1 Accuracy":"51.6"},"uses_additional_data":true,"paper_date":"2022-05-26","paper":"/paper/matryoshka-representations-for-adaptive","paper_url":"https://arxiv.org/abs/2205.13147v4","paper_title":"Matryoshka Representation Learning","code":"https://github.com/novasearch-team/rag-retrieval","n_code_links":5,"official":{"repos":["raivnlab/mrl"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/matryoshka-representations-for-adaptive#ran","syntology_url":"https://syntology.ai/paper/2205.13147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.13147"}}}},{"rank_in_archive_order":26,"model":"ViT-B/16 (ANN-1.3B)","metrics":{"Top-1 Accuracy":"50.7"},"uses_additional_data":true,"paper_date":"2021-08-12","paper":"/paper/billion-scale-pretraining-with-vision","paper_url":"https://arxiv.org/abs/2108.05887v1","paper_title":"Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":27,"model":"ViT-B/16 (512x512) + Pyramid","metrics":{"Top-1 Accuracy":"49.39"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":28,"model":"ResNet-101 (JFT-300M)","metrics":{"Top-1 Accuracy":"49.1"},"uses_additional_data":true,"paper_date":"2021-08-12","paper":"/paper/billion-scale-pretraining-with-vision","paper_url":"https://arxiv.org/abs/2108.05887v1","paper_title":"Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":29,"model":"ViT B/16","metrics":{"Top-1 Accuracy":"48.9"},"uses_additional_data":true,"paper_date":"2022-01-20","paper":"/paper/revisiting-weakly-supervised-pre-training-of","paper_url":"https://arxiv.org/abs/2201.08371v2","paper_title":"Revisiting Weakly Supervised Pre-Training of Visual Perception Models","code":"https://github.com/facebookresearch/SWAG","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":30,"model":"ViT-B/32","metrics":{"Top-1 Accuracy":"48.4"},"uses_additional_data":true,"paper_date":"2021-08-12","paper":"/paper/billion-scale-pretraining-with-vision","paper_url":"https://arxiv.org/abs/2108.05887v1","paper_title":"Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":31,"model":"ViT-B/16 (512x512) + Pixel","metrics":{"Top-1 Accuracy":"47.53"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":32,"model":"AR-B (Opt Relevance)","metrics":{"Top-1 Accuracy":"47.1","Top-5 Accuracy":"70"},"uses_additional_data":true,"paper_date":"2022-06-02","paper":"/paper/optimizing-relevance-maps-of-vision","paper_url":"https://arxiv.org/abs/2206.01161v1","paper_title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","code":"https://github.com/hila-chefer/robustvit","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":33,"model":"BiT-M (ResNet-152x4)","metrics":{"Top-1 Accuracy":"47.0","Top-5 Accuracy":"69"},"uses_additional_data":true,"paper_date":"2019-12-24","paper":"/paper/large-scale-learning-of-general-visual","paper_url":"https://arxiv.org/abs/1912.11370v3","paper_title":"Big Transfer (BiT): General Visual Representation Learning","code":"https://github.com/google-research/big_transfer","n_code_links":9,"official":{"repos":["google-research/big_transfer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":0,"sample_list":"/paper/large-scale-learning-of-general-visual#ran","syntology_url":"https://syntology.ai/paper/1912.11370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.11370"}}}},{"rank_in_archive_order":34,"model":"ViT-B/16 (512x512)","metrics":{"Top-1 Accuracy":"46.68"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":35,"model":"ViT-B (Discrete 512x512)","metrics":{"Top-1 Accuracy":"46.62"},"uses_additional_data":true,"paper_date":"2021-11-20","paper":"/paper/discrete-representations-strengthen-vision-1","paper_url":"https://arxiv.org/abs/2111.10493v2","paper_title":"Discrete Representations Strengthen Vision Transformer Robustness","code":"https://github.com/alibaba/easyrobust/tree/main/examples/imageclassification/imagenet/drvit","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":36,"model":"AR-L","metrics":{"Top-1 Accuracy":"46.5","Top-5 Accuracy":"68.3"},"uses_additional_data":true,"paper_date":"2022-06-02","paper":"/paper/optimizing-relevance-maps-of-vision","paper_url":"https://arxiv.org/abs/2206.01161v1","paper_title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","code":"https://github.com/hila-chefer/robustvit","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":37,"model":"ViT-L (Opt Relevance)","metrics":{"Top-1 Accuracy":"43.2","Top-5 Accuracy":"65.8"},"uses_additional_data":true,"paper_date":"2022-06-02","paper":"/paper/optimizing-relevance-maps-of-vision","paper_url":"https://arxiv.org/abs/2206.01161v1","paper_title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","code":"https://github.com/hila-chefer/robustvit","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":38,"model":"CLIP L","metrics":{"Top-1 Accuracy":"42.80"},"uses_additional_data":true,"paper_date":"2021-12-31","paper":"/paper/optimal-representations-for-covariate-shift-1","paper_url":"https://arxiv.org/abs/2201.00057v2","paper_title":"Optimal Representations for Covariate Shift","code":"https://github.com/facebookresearch/DomainBed","n_code_links":2,"official":{"repos":["ryoungj/optdom"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":3,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/optimal-representations-for-covariate-shift-1#ran","syntology_url":"https://syntology.ai/paper/2201.00057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.00057"}}}},{"rank_in_archive_order":39,"model":"ResNet-50 (JFT-300M)","metrics":{"Top-1 Accuracy":"42.5"},"uses_additional_data":true,"paper_date":"2021-08-12","paper":"/paper/billion-scale-pretraining-with-vision","paper_url":"https://arxiv.org/abs/2108.05887v1","paper_title":"Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":40,"model":"ViT-B (Opt Relevance)","metrics":{"Top-1 Accuracy":"42.2","Top-5 Accuracy":"65.1"},"uses_additional_data":true,"paper_date":"2022-06-02","paper":"/paper/optimizing-relevance-maps-of-vision","paper_url":"https://arxiv.org/abs/2206.01161v1","paper_title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","code":"https://github.com/hila-chefer/robustvit","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":41,"model":"CLIP L (LAION)","metrics":{"Top-1 Accuracy":"42.10"},"uses_additional_data":true,"paper_date":"2021-12-31","paper":"/paper/optimal-representations-for-covariate-shift-1","paper_url":"https://arxiv.org/abs/2201.00057v2","paper_title":"Optimal Representations for Covariate Shift","code":"https://github.com/facebookresearch/DomainBed","n_code_links":2,"official":{"repos":["ryoungj/optdom"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":3,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/optimal-representations-for-covariate-shift-1#ran","syntology_url":"https://syntology.ai/paper/2201.00057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.00057"}}}},{"rank_in_archive_order":42,"model":"AR-B","metrics":{"Top-1 Accuracy":"41.4","Top-5 Accuracy":"63.7"},"uses_additional_data":true,"paper_date":"2022-06-02","paper":"/paper/optimizing-relevance-maps-of-vision","paper_url":"https://arxiv.org/abs/2206.01161v1","paper_title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","code":"https://github.com/hila-chefer/robustvit","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":43,"model":"RegViT on 384x384 + Adv Pyramid","metrics":{"Top-1 Accuracy":"39.79"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":44,"model":"ResNet-152 + GenInt with Transfer","metrics":{"Top-1 Accuracy":"39.38","Top-5 Accuracy":"61.43"},"uses_additional_data":true,"paper_date":"2020-12-22","paper":"/paper/generative-interventions-for-causal-learning","paper_url":"https://arxiv.org/abs/2012.12265v2","paper_title":"Generative Interventions for Causal Learning","code":"https://github.com/cvlab-columbia/GenInt","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":45,"model":"AR-S (Opt Relevance)","metrics":{"Top-1 Accuracy":"39.3","Top-5 Accuracy":"61.7"},"uses_additional_data":true,"paper_date":"2022-06-02","paper":"/paper/optimizing-relevance-maps-of-vision","paper_url":"https://arxiv.org/abs/2206.01161v1","paper_title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","code":"https://github.com/hila-chefer/robustvit","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":46,"model":"ResNet-50 (Bamboo)","metrics":{"Top-1 Accuracy":"38.8"},"uses_additional_data":true,"paper_date":"2022-03-15","paper":"/paper/bamboo-building-mega-scale-vision-dataset","paper_url":"https://arxiv.org/abs/2203.07845v2","paper_title":"Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy","code":"https://github.com/zhangyuanhan-ai/bamboo","n_code_links":2,"official":{"repos":["davidzhangyuanhan/bamboo","zhangyuanhan-ai/bamboo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/bamboo-building-mega-scale-vision-dataset#ran","syntology_url":"https://syntology.ai/paper/2203.07845","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.07845"}}}},{"rank_in_archive_order":47,"model":"RegViT on 384x384 + Adv Pixel","metrics":{"Top-1 Accuracy":"37.41"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":48,"model":"ViT-L","metrics":{"Top-1 Accuracy":"37.4","Top-5 Accuracy":"59.5"},"uses_additional_data":true,"paper_date":"2022-06-02","paper":"/paper/optimizing-relevance-maps-of-vision","paper_url":"https://arxiv.org/abs/2206.01161v1","paper_title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","code":"https://github.com/hila-chefer/robustvit","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":49,"model":"DeiT-L (Opt Relevance)","metrics":{"Top-1 Accuracy":"36.3","Top-5 Accuracy":"56.6"},"uses_additional_data":true,"paper_date":"2022-06-02","paper":"/paper/optimizing-relevance-maps-of-vision","paper_url":"https://arxiv.org/abs/2206.01161v1","paper_title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","code":"https://github.com/hila-chefer/robustvit","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":50,"model":"BiT-S (ResNet-152x4)","metrics":{"Top-1 Accuracy":"36.0","Top-5 Accuracy":"57"},"uses_additional_data":true,"paper_date":"2019-12-24","paper":"/paper/large-scale-learning-of-general-visual","paper_url":"https://arxiv.org/abs/1912.11370v3","paper_title":"Big Transfer (BiT): General Visual Representation Learning","code":"https://github.com/google-research/big_transfer","n_code_links":9,"official":{"repos":["google-research/big_transfer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":0,"sample_list":"/paper/large-scale-learning-of-general-visual#ran","syntology_url":"https://syntology.ai/paper/1912.11370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.11370"}}}},{"rank_in_archive_order":51,"model":"NASNet-A","metrics":{"Top-1 Accuracy":"35.77","Top-5 Accuracy":"56.05"},"uses_additional_data":true,"paper_date":"2019-12-01","paper":"/paper/objectnet-a-large-scale-bias-controlled","paper_url":"http://papers.nips.cc/paper/9142-objectnet-a-large-scale-bias-controlled-dataset-for-pushing-the-limits-of-object-recognition-models","paper_title":"ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":52,"model":"PNASNet-5L","metrics":{"Top-1 Accuracy":"35.63","Top-5 Accuracy":"54.95"},"uses_additional_data":true,"paper_date":"2019-12-01","paper":"/paper/objectnet-a-large-scale-bias-controlled","paper_url":"http://papers.nips.cc/paper/9142-objectnet-a-large-scale-bias-controlled-dataset-for-pushing-the-limits-of-object-recognition-models","paper_title":"ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":53,"model":"RegViT on 384x384","metrics":{"Top-1 Accuracy":"35.59"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":54,"model":"ViT-B","metrics":{"Top-1 Accuracy":"35.1","Top-5 Accuracy":"56.4"},"uses_additional_data":true,"paper_date":"2022-06-02","paper":"/paper/optimizing-relevance-maps-of-vision","paper_url":"https://arxiv.org/abs/2206.01161v1","paper_title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","code":"https://github.com/hila-chefer/robustvit","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":55,"model":"RegViT on 384x384 + Random Pyramid","metrics":{"Top-1 Accuracy":"34.83"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":56,"model":"AR-S","metrics":{"Top-1 Accuracy":"34.3","Top-5 Accuracy":"55.8"},"uses_additional_data":true,"paper_date":"2022-06-02","paper":"/paper/optimizing-relevance-maps-of-vision","paper_url":"https://arxiv.org/abs/2206.01161v1","paper_title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","code":"https://github.com/hila-chefer/robustvit","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":57,"model":"RegViT on 384x384 + Random Pixel","metrics":{"Top-1 Accuracy":"34.12"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":58,"model":"RegViT (RandAug) + Adv Pyramid","metrics":{"Top-1 Accuracy":"32.92"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":59,"model":"Inception-v4","metrics":{"Top-1 Accuracy":"32.24","Top-5 Accuracy":"51.98"},"uses_additional_data":true,"paper_date":"2019-12-01","paper":"/paper/objectnet-a-large-scale-bias-controlled","paper_url":"http://papers.nips.cc/paper/9142-objectnet-a-large-scale-bias-controlled-dataset-for-pushing-the-limits-of-object-recognition-models","paper_title":"ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":60,"model":"DeiT-S (Opt Relevance)","metrics":{"Top-1 Accuracy":"31.6","Top-5 Accuracy":"53"},"uses_additional_data":true,"paper_date":"2022-06-02","paper":"/paper/optimizing-relevance-maps-of-vision","paper_url":"https://arxiv.org/abs/2206.01161v1","paper_title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","code":"https://github.com/hila-chefer/robustvit","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":61,"model":"ResNet-50 + CGC","metrics":{"Top-1 Accuracy":"31.53","Top-5 Accuracy":"50.16"},"uses_additional_data":true,"paper_date":"2019-10-12","paper":"/paper/context-gated-convolution","paper_url":"https://arxiv.org/abs/1910.05577v4","paper_title":"Context-Gated Convolution","code":"https://github.com/XudongLinthu/context-gated-convolution","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":62,"model":"DeiT-L","metrics":{"Top-1 Accuracy":"31.4","Top-5 Accuracy":"48.5"},"uses_additional_data":true,"paper_date":"2022-06-02","paper":"/paper/optimizing-relevance-maps-of-vision","paper_url":"https://arxiv.org/abs/2206.01161v1","paper_title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","code":"https://github.com/hila-chefer/robustvit","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":63,"model":"Discrete ViT + Pixel","metrics":{"Top-1 Accuracy":"30.98"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":64,"model":"Discrete ViT + Pyramid","metrics":{"Top-1 Accuracy":"30.28"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":65,"model":"RegViT (RandAug) + Adv Pixel","metrics":{"Top-1 Accuracy":"30.11"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":66,"model":"Discrete ViT","metrics":{"Top-1 Accuracy":"29.95"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":67,"model":"ResNet-152","metrics":{"Top-1 Accuracy":"29.59","Top-5 Accuracy":"49.4"},"uses_additional_data":true,"paper_date":"2019-12-01","paper":"/paper/objectnet-a-large-scale-bias-controlled","paper_url":"http://papers.nips.cc/paper/9142-objectnet-a-large-scale-bias-controlled-dataset-for-pushing-the-limits-of-object-recognition-models","paper_title":"ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":68,"model":"RegViT (RandAug) + Random Pyramid","metrics":{"Top-1 Accuracy":"29.41"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":69,"model":"RegViT (RandAug)","metrics":{"Top-1 Accuracy":"29.3"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":70,"model":"ResNet-50 + GroupNorm","metrics":{"Top-1 Accuracy":"29.2","Top-5 Accuracy":"50.2"},"uses_additional_data":true,"paper_date":"2020-06-30","paper":"/paper/improving-robustness-against-common","paper_url":"https://arxiv.org/abs/2006.16971v2","paper_title":"Improving robustness against common corruptions by covariate shift adaptation","code":"https://github.com/bethgelab/robustness","n_code_links":2,"official":{"repos":["bethgelab/robustness"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/improving-robustness-against-common#ran","syntology_url":"https://syntology.ai/paper/2006.16971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.16971"}}}},{"rank_in_archive_order":71,"model":"ResNet-50 + RoHL","metrics":{"Top-1 Accuracy":"29.2"},"uses_additional_data":true,"paper_date":"2020-06-30","paper":"/paper/improving-robustness-against-common","paper_url":"https://arxiv.org/abs/2006.16971v2","paper_title":"Improving robustness against common corruptions by covariate shift adaptation","code":"https://github.com/bethgelab/robustness","n_code_links":2,"official":{"repos":["bethgelab/robustness"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/improving-robustness-against-common#ran","syntology_url":"https://syntology.ai/paper/2006.16971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.16971"}}}},{"rank_in_archive_order":72,"model":"RegViT (RandAug) + Random Pixel","metrics":{"Top-1 Accuracy":"28.72"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":73,"model":"MLP-Mixer + Pyramid","metrics":{"Top-1 Accuracy":"28.6"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":74,"model":"ResNet-50 + FixUp","metrics":{"Top-1 Accuracy":"28.5","Top-5 Accuracy":"48.6"},"uses_additional_data":true,"paper_date":"2020-06-30","paper":"/paper/improving-robustness-against-common","paper_url":"https://arxiv.org/abs/2006.16971v2","paper_title":"Improving robustness against common corruptions by covariate shift adaptation","code":"https://github.com/bethgelab/robustness","n_code_links":2,"official":{"repos":["bethgelab/robustness"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/improving-robustness-against-common#ran","syntology_url":"https://syntology.ai/paper/2006.16971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.16971"}}}},{"rank_in_archive_order":75,"model":"ResNet-50 + MixUp (rescaled)","metrics":{"Top-1 Accuracy":"28.37"},"uses_additional_data":true,"paper_date":"2020-06-10","paper":"/paper/on-mixup-regularization","paper_url":"https://arxiv.org/abs/2006.06049v3","paper_title":"On Mixup Regularization","code":"https://github.com/google/uncertainty-baselines/tree/master/baselines/imagenet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":76,"model":"DeiT-S","metrics":{"Top-1 Accuracy":"28.3","Top-5 Accuracy":"47.3"},"uses_additional_data":true,"paper_date":"2022-06-02","paper":"/paper/optimizing-relevance-maps-of-vision","paper_url":"https://arxiv.org/abs/2206.01161v1","paper_title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","code":"https://github.com/hila-chefer/robustvit","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":77,"model":"ResNet-18 + GenInt with Transfer","metrics":{"Top-1 Accuracy":"27.03","Top-5 Accuracy":"48.02"},"uses_additional_data":true,"paper_date":"2020-12-22","paper":"/paper/generative-interventions-for-causal-learning","paper_url":"https://arxiv.org/abs/2012.12265v2","paper_title":"Generative Interventions for Causal Learning","code":"https://github.com/cvlab-columbia/GenInt","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":78,"model":"MLP-Mixer","metrics":{"Top-1 Accuracy":"25.9"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":79,"model":"RELICv2","metrics":{"Top-1 Accuracy":"25.9"},"uses_additional_data":true,"paper_date":"2022-01-13","paper":"/paper/pushing-the-limits-of-self-supervised-resnets","paper_url":"https://arxiv.org/abs/2201.05119v2","paper_title":"Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?","code":"https://github.com/google-deepmind/relicv2","n_code_links":1,"official":{"repos":["google-deepmind/relicv2"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":1,"n_samples":14,"n_pointer_only_licence":0,"sample_list":"/paper/pushing-the-limits-of-self-supervised-resnets#ran","syntology_url":"https://syntology.ai/paper/2201.05119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.05119"}}}},{"rank_in_archive_order":80,"model":"ViT + MixUp","metrics":{"Top-1 Accuracy":"25.65"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":81,"model":"C-BYOL","metrics":{"Top-1 Accuracy":"25.5"},"uses_additional_data":true,"paper_date":"2021-09-27","paper":"/paper/compressive-visual-representations","paper_url":"https://arxiv.org/abs/2109.12909v3","paper_title":"Compressive Visual Representations","code":"https://github.com/google-research/compressive-visual-representations","n_code_links":1,"official":{"repos":["google-research/compressive-visual-representations"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":5,"n_samples":12,"n_pointer_only_licence":0,"sample_list":"/paper/compressive-visual-representations#ran","syntology_url":"https://syntology.ai/paper/2109.12909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.12909"}}}},{"rank_in_archive_order":82,"model":"MLP-Mixer + Pixel","metrics":{"Top-1 Accuracy":"24.75"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":83,"model":"BYOL (BG_RM)","metrics":{"Top-1 Accuracy":"23.9"},"uses_additional_data":true,"paper_date":"2021-03-23","paper":"/paper/leveraging-background-augmentations-to","paper_url":"https://arxiv.org/abs/2103.12719v2","paper_title":"Characterizing and Improving the Robustness of Self-Supervised Learning through Background Augmentations","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":84,"model":"RELIC","metrics":{"Top-1 Accuracy":"23.8"},"uses_additional_data":true,"paper_date":"2022-01-13","paper":"/paper/pushing-the-limits-of-self-supervised-resnets","paper_url":"https://arxiv.org/abs/2201.05119v2","paper_title":"Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?","code":"https://github.com/google-deepmind/relicv2","n_code_links":1,"official":{"repos":["google-deepmind/relicv2"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":1,"n_samples":14,"n_pointer_only_licence":0,"sample_list":"/paper/pushing-the-limits-of-self-supervised-resnets#ran","syntology_url":"https://syntology.ai/paper/2201.05119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.05119"}}}},{"rank_in_archive_order":85,"model":"BYOL","metrics":{"Top-1 Accuracy":"23"},"uses_additional_data":true,"paper_date":"2022-01-13","paper":"/paper/pushing-the-limits-of-self-supervised-resnets","paper_url":"https://arxiv.org/abs/2201.05119v2","paper_title":"Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?","code":"https://github.com/google-deepmind/relicv2","n_code_links":1,"official":{"repos":["google-deepmind/relicv2"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":1,"n_samples":14,"n_pointer_only_licence":0,"sample_list":"/paper/pushing-the-limits-of-self-supervised-resnets#ran","syntology_url":"https://syntology.ai/paper/2201.05119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.05119"}}}},{"rank_in_archive_order":86,"model":"SwAV (BG_RM)","metrics":{"Top-1 Accuracy":"21.9"},"uses_additional_data":true,"paper_date":"2021-03-23","paper":"/paper/leveraging-background-augmentations-to","paper_url":"https://arxiv.org/abs/2103.12719v2","paper_title":"Characterizing and Improving the Robustness of Self-Supervised Learning through Background Augmentations","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":87,"model":"ViT + CutMix","metrics":{"Top-1 Accuracy":"21.61"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":88,"model":"MoCo-v2 (BG_Swaps)","metrics":{"Top-1 Accuracy":"20.8"},"uses_additional_data":true,"paper_date":"2021-03-23","paper":"/paper/leveraging-background-augmentations-to","paper_url":"https://arxiv.org/abs/2103.12719v2","paper_title":"Characterizing and Improving the Robustness of Self-Supervised Learning through Background Augmentations","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":89,"model":"C-SimCLR","metrics":{"Top-1 Accuracy":"20.8"},"uses_additional_data":true,"paper_date":"2021-09-27","paper":"/paper/compressive-visual-representations","paper_url":"https://arxiv.org/abs/2109.12909v3","paper_title":"Compressive Visual Representations","code":"https://github.com/google-research/compressive-visual-representations","n_code_links":1,"official":{"repos":["google-research/compressive-visual-representations"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":5,"n_samples":12,"n_pointer_only_licence":0,"sample_list":"/paper/compressive-visual-representations#ran","syntology_url":"https://syntology.ai/paper/2109.12909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.12909"}}}},{"rank_in_archive_order":90,"model":"SeLa(v2) (reverse linear probing)","metrics":{"Top-1 Accuracy":"20.61","Top-5 Accuracy":"48.83"},"uses_additional_data":true,"paper_date":"2021-09-29","paper":"/paper/measuring-the-interpretability-of","paper_url":"https://openreview.net/forum?id=HFPTzdwN39","paper_title":"Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":91,"model":"DILEMMA","metrics":{"Top-1 Accuracy":"20.51"},"uses_additional_data":true,"paper_date":"2022-04-10","paper":"/paper/dilemma-self-supervised-shape-and-texture","paper_url":"https://arxiv.org/abs/2204.04788v2","paper_title":"Representation Learning by Detecting Incorrect Location Embeddings","code":"https://github.com/separius/dilemma","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":92,"model":"DeepCluster(v2) (reverse linear probing)","metrics":{"Top-1 Accuracy":"19.73","Top-5 Accuracy":"46.81"},"uses_additional_data":true,"paper_date":"2021-09-29","paper":"/paper/measuring-the-interpretability-of","paper_url":"https://openreview.net/forum?id=HFPTzdwN39","paper_title":"Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":93,"model":"VGG-14","metrics":{"Top-1 Accuracy":"19.13","Top-5 Accuracy":"37.15"},"uses_additional_data":true,"paper_date":"2019-12-01","paper":"/paper/objectnet-a-large-scale-bias-controlled","paper_url":"http://papers.nips.cc/paper/9142-objectnet-a-large-scale-bias-controlled-dataset-for-pushing-the-limits-of-object-recognition-models","paper_title":"ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":94,"model":"ResNet-50 (ImageNet-Captions)","metrics":{"Top-1 Accuracy":"18.70"},"uses_additional_data":true,"paper_date":"2022-05-03","paper":"/paper/data-determines-distributional-robustness-in","paper_url":"https://arxiv.org/abs/2205.01397v2","paper_title":"Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)","code":"https://github.com/mlfoundations/imagenet-captions","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":95,"model":"SwAV (reverse linear probing)","metrics":{"Top-1 Accuracy":"17.71","Top-5 Accuracy":"43.64"},"uses_additional_data":true,"paper_date":"2021-09-29","paper":"/paper/measuring-the-interpretability-of","paper_url":"https://openreview.net/forum?id=HFPTzdwN39","paper_title":"Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":96,"model":"ViT","metrics":{"Top-1 Accuracy":"17.36"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":97,"model":"ResNet34-RPG","metrics":{"Top-1 Accuracy":"16.5"},"uses_additional_data":true,"paper_date":"2021-07-15","paper":"/paper/recurrent-parameter-generators","paper_url":"https://arxiv.org/abs/2107.07110v3","paper_title":"Compact and Optimal Deep Learning with Recurrent Parameter Generators","code":"https://github.com/samaonline/Recurrent-Parameter-Generators","n_code_links":1,"official":{"repos":["samaonline/Recurrent-Parameter-Generators"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1,"sample_list":"/paper/recurrent-parameter-generators#ran","syntology_url":"https://syntology.ai/paper/2107.07110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07110"}}}},{"rank_in_archive_order":98,"model":"CLIP (CC12M pretrain)","metrics":{"Top-1 Accuracy":"15.24"},"uses_additional_data":true,"paper_date":"2022-04-10","paper":"/paper/robust-cross-modal-representation-learning","paper_url":"https://arxiv.org/abs/2204.04588v1","paper_title":"Robust Cross-Modal Representation Learning with Progressive Self-Distillation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":99,"model":"SimCLR","metrics":{"Top-1 Accuracy":"14.6"},"uses_additional_data":true,"paper_date":"2022-01-13","paper":"/paper/pushing-the-limits-of-self-supervised-resnets","paper_url":"https://arxiv.org/abs/2201.05119v2","paper_title":"Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?","code":"https://github.com/google-deepmind/relicv2","n_code_links":1,"official":{"repos":["google-deepmind/relicv2"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":1,"n_samples":14,"n_pointer_only_licence":0,"sample_list":"/paper/pushing-the-limits-of-self-supervised-resnets#ran","syntology_url":"https://syntology.ai/paper/2201.05119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.05119"}}}},{"rank_in_archive_order":100,"model":"ResNet-152 (FRCNN-ag-ad, VOC)","metrics":{"Top-1 Accuracy":"13.2","Top-5 Accuracy":"29.7"},"uses_additional_data":true,"paper_date":"2020-11-28","paper":"/paper/class-agnostic-object-detection","paper_url":"https://arxiv.org/abs/2011.14204v1","paper_title":"Class-agnostic Object Detection","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":101,"model":"MoCo(v2) (reverse linear probing)","metrics":{"Top-1 Accuracy":"12.67","Top-5 Accuracy":"31.45"},"uses_additional_data":true,"paper_date":"2021-09-29","paper":"/paper/measuring-the-interpretability-of","paper_url":"https://openreview.net/forum?id=HFPTzdwN39","paper_title":"Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":102,"model":"MoCHi  (reverse linear probing)","metrics":{"Top-1 Accuracy":"12.64","Top-5 Accuracy":"31.71"},"uses_additional_data":true,"paper_date":"2021-09-29","paper":"/paper/measuring-the-interpretability-of","paper_url":"https://openreview.net/forum?id=HFPTzdwN39","paper_title":"Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":103,"model":"OBoW (reverse linear probing)","metrics":{"Top-1 Accuracy":"12.23","Top-5 Accuracy":"31.72"},"uses_additional_data":true,"paper_date":"2021-09-29","paper":"/paper/measuring-the-interpretability-of","paper_url":"https://openreview.net/forum?id=HFPTzdwN39","paper_title":"Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":104,"model":"AlexNet","metrics":{"Top-1 Accuracy":"6.78","Top-5 Accuracy":"17.6"},"uses_additional_data":true,"paper_date":"2019-12-01","paper":"/paper/objectnet-a-large-scale-bias-controlled","paper_url":"http://papers.nips.cc/paper/9142-objectnet-a-large-scale-bias-controlled-dataset-for-pushing-the-limits-of-object-recognition-models","paper_title":"ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":105,"model":"BigBiGAN (RevNet-50 4×)","metrics":{"Top-1 Accuracy":"4.92"},"uses_additional_data":true,"paper_date":"2020-08-24","paper":"/paper/self-supervised-learning-for-large-scale","paper_url":"https://arxiv.org/abs/2008.10312v2","paper_title":"Self-Supervised Learning for Large-Scale Unsupervised Image Clustering","code":"https://github.com/Randl/kmeans_selfsuper","n_code_links":1,"official":{"repos":["Randl/kmeans_selfsuper"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":0,"sample_list":"/paper/self-supervised-learning-for-large-scale#ran","syntology_url":"https://syntology.ai/paper/2008.10312","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.10312"}}}},{"rank_in_archive_order":106,"model":"ViT-H/14","metrics":{"Top-5 Accuracy":"82.1"},"uses_additional_data":true,"paper_date":"2020-10-22","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","paper_url":"https://arxiv.org/abs/2010.11929v2","paper_title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","code":"https://github.com/huggingface/transformers","n_code_links":158,"official":{"repos":["google-research/vision_transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":["community","listed","unlocated"]},"syntology":{"n_ran":307,"n_constructed":165,"n_ran_checked":286,"n_instrument":21,"n_unverified":112,"n_samples":419,"n_pointer_only_licence":154,"sample_list":"/paper/an-image-is-worth-16x16-words-transformers-1#ran","syntology_url":"https://syntology.ai/paper/2010.11929","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.11929"}}}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"adjudicator":"Claude Opus 5.5","adjudicator_from":"groundwork/59_code_with_papers/LB_EXTRACTOR_PREREG.md (not recorded in lb_measurement.json; the file's frozen_commit, measured_on and counts equal the run the pre-registration records)","adjudicator_sensitivity":[69,70],"adjudicator_specificity":[101,103],"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication by a model (adjudicator) of accepted entries on a held-out split of archive papers, rules frozen before the test; adjudicator_sensitivity and adjudicator_specificity are its own controls as [judged right, of]; it was not measured on the newer papers placed here","measurement_sentence":"Measured before publishing, on held-out archive papers: the extractor was given 883 of them and produced output for 881 (the other 2 had no title and were excluded before any model call, so they are not part of this measurement). A model adjudicator (Claude Opus 5.5), blind to which entries were real, judged 108 of 110 accepted entries correct on those held-out archive papers; its own controls: 69 of 70 archive-confirmed entries judged true, 101 of 103 corrupted copies judged false. It was not measured on the newer papers whose results are placed on this site.","coverage":{"sentence":"Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.","complete":false,"papers_newer_than_archive":18637,"papers_checked":8886,"papers_checked_no_leaderboard_matched":3717,"papers_read_nothing_to_place":733,"papers_could_not_be_read":41,"papers_could_not_be_read_by_status":{"unparseable":41},"papers_extracted_not_yet_verified":0,"boards_without_verdict":3,"papers_not_yet_extracted":8975},"board_status":{"sentence":"Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 2 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,595 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 2 proposed a result; of those 2, 2 gave no cell that passed the extractor's own checks, 0 were rejected by the independent check, 0 await a verdict and 0 were placed.","note":"papers, from the extractor's own records, over the newer papers whose tables were read; proposed = no_cell_passed_checks + rejected_by_independent_check + accepted_not_placed + awaiting_verdict + placed; counts, never a rate","eligible":true,"eligible_note":"false when the extractor never considers this board: it loads only boards with archive rows and at least one metric column (lb_extract.py Boards), so no newer paper can be proposed here; archive_rows and metric_columns say which","archive_rows":106,"metric_columns":2,"papers_read":8888,"papers_read_checked":8886,"papers_read_awaiting_verdict":2,"papers_read_verified":8888,"papers_read_not_yet_verified":0,"papers_read_at_candidate_cap":1596,"papers_read_list_full_without_this_board":1595,"candidates":2,"candidates_capped_note":"candidates = papers that had this board among the leaderboards the extractor considered for their tables; the extractor keeps at most 10 per paper and 4 per dataset, so a board crowded out of a paper's list is not counted and candidates is a floor; papers_read_list_full_without_this_board counts the read papers whose list did not hold this board and had reached 10, or held 4 boards of this board's dataset (the only papers that could have crowded it out); papers_read_at_candidate_cap counts, over every board, the papers whose list reached 10","proposed":2,"no_cell_passed_checks":2,"rejected_by_independent_check":0,"accepted_not_placed":0,"awaiting_verdict":0,"placed":0,"placed_entries_listed":0,"file_lines_unreadable_as_read":0,"since_line":"Since the archive (Syntology): none placed; 2 newer papers judged to report on this board so far"},"judged_to_report":{"heading":"Newer papers whose tables Claude Sonnet 4.5 judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)","judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"a_record_without_a_model":false,"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here","order":"newest first by arXiv id (the identifier's order, not a rank)","outcomes":{"placed":"placed","no_cell_passed_checks":"no cell passed the extractor's checks","refused_by_rule":"refused by a rule","rejected":"rejected by the independent check","accepted_not_placed":"accepted by the independent check but not placed by this site","awaiting":"awaiting a verdict"},"reason_note":"for refused_by_rule, the rules' plain words for the reason codes the record gives (never the quoted or the actual cell text); null for every other outcome","total":2,"shown_on_page":2,"no_cell_split":{"no_cell_passed_checks_in_ledger":2,"rows_refused_by_rule":2,"rows_no_cell_passed_checks":0},"rows":[{"arxiv_id":"2605.29380","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2603.08309","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric; one configuration gave two values for one column"}]},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per row: of M harvested code samples from that row's paper, n_ran executed on a synthesized fixture (n_ran = n_ran_checked + n_instrument; n_instrument counts failures of Syntology's instrument, not of the code); the other M - n_ran are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","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)"},"rows_with_graph_line":27,"rows_with_any_sample_ran":27,"rows_with_a_run_with_no_instrument_failure":22,"official":{"state_rule":"the archive's official repositories have samples for this paper that ran: 'official (archive's flag): N ran' (N counts them, instrument failures included); they have samples, none ran: 'official: harvested, nothing ran'; they have no sample for this paper and another sample ran: 'community repositories only' when every sample that ran came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, else 'official: no sample here; runs from other or unrecorded repositories' (a repository named in the paper or found in its text by Syntology, or no repository recorded); otherwise 'official: harvested for another paper' or 'official: not harvested'. Absent when the archive marks no repository official. Official is the archive's is_official flag, not an authorship verdict","flag":"the archive's is_official flag for the paper's code link; not a verdict on who wrote the code","rows_with_an_archive_official_repository":26,"rows_whose_official_repository_has_a_sample_that_ran":17,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":13,"rows_community_repositories_only":6,"rows_runs_from_other_or_unrecorded_repositories":1,"note":"rows[].official, per row with a graph line: repos (marked official in the archive), state, n_ran and n_unverified (samples from those repositories), and ran_from_kinds (the kinds of repository the paper's samples that ran came from; 'unlocated' is no repository recorded)"},"filters":{"ran_modes":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"the page's filters hide rows and never renumber them; they read the Ran cell's counts, the same figures rows[].syntology and rows[].official carry"},"row_route":"rows[].syntology carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","distinct_papers_with_graph_line":16,"distinct_papers_with_any_sample_ran":16,"distinct_papers_with_a_run_with_no_instrument_failure":13,"samples_over_distinct_papers":{"n_ran":399,"n_constructed":174,"n_ran_checked":345,"n_instrument":54,"n_unverified":150,"n_samples":549,"n_pointer_only_licence":177,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":486,"n_constructed":177,"n_ran_checked":416,"n_instrument":70,"n_unverified":169,"n_samples":655,"n_pointer_only_licence":180,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}},"record_sha256":"aea4efe48c84eda4d875d68381d57963e6e4b4bac8903a41c876bef68773481d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}