{"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":"/code/cutout","entry":"cutout","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":17,"n_papers_ran":5,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":20,"n_samples_ran":6,"n_samples_fingerprinted":1,"n_places":20,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":2,"ran":1,"unverified":14},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2411.01409","paper":"/paper/classifier-guided-gradient-modulation-for","title":"Classifier-guided Gradient Modulation for Enhanced Multimodal Learning","date":"2024-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zrguo/CGGM","path":"datasets/BratsDataset.py","file_url":"https://github.com/zrguo/CGGM/blob/HEAD/datasets/BratsDataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"653ae4081b06cab6","mcp_get_code":{"code_sha256":"653ae4081b06cab6"}},{"arxiv_id":"2310.13807","paper":"/paper/learning-to-learn-at-test-time","title":"Learning to (Learn at Test Time)","date":"2023-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"test-time-training/mttt","path":"pp/autoaugment.py","file_url":"https://github.com/test-time-training/mttt/blob/HEAD/pp/autoaugment.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a1146beffdc1b587","mcp_get_code":{"code_sha256":"a1146beffdc1b587"}},{"arxiv_id":"2110.09192","paper":"/paper/learning-optimal-conformal-classifiers-1","title":"Learning Optimal Conformal Classifiers","date":"2021-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deepmind/conformal_training","path":"auto_augment.py","file_url":"https://github.com/deepmind/conformal_training/blob/HEAD/auto_augment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4515269703640fc7","mcp_get_code":{"code_sha256":"4515269703640fc7"}},{"arxiv_id":"2106.13195","paper":"/paper/fitvid-overfitting-in-pixel-level-video","title":"FitVid: Overfitting in Pixel-Level Video Prediction","date":"2021-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/fitvid","path":"randaug.py","file_url":"https://github.com/google-research/fitvid/blob/HEAD/randaug.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fddcd1f71282b74e","mcp_get_code":{"code_sha256":"fddcd1f71282b74e"}},{"arxiv_id":"2106.12930","paper":"/paper/vindr-spinexr-a-deep-learning-framework-for","title":"VinDr-SpineXR: A deep learning framework for spinal lesions detection and classification from radiographs","date":"2021-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vinbigdata-medical/vindr-spinexr","path":"spine/augments/autoaugment_utils.py","file_url":"https://github.com/vinbigdata-medical/vindr-spinexr/blob/HEAD/spine/augments/autoaugment_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"24139d2b8e1c934d","mcp_get_code":{"code_sha256":"24139d2b8e1c934d"}},{"arxiv_id":"2103.16201","paper":"/paper/mt3-meta-test-time-training-for-self","title":"MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption","date":"2021-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AlexanderBartler/MT3","path":"model/augementations/auto_augment.py","file_url":"https://github.com/AlexanderBartler/MT3/blob/HEAD/model/augementations/auto_augment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e570f106e7008c26","mcp_get_code":{"code_sha256":"e570f106e7008c26"}},{"arxiv_id":"2010.01412","paper":"/paper/sharpness-aware-minimization-for-efficiently-1","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","date":"2020-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/sam","path":"sam_jax/datasets/augmentation.py","file_url":"https://github.com/google-research/sam/blob/HEAD/sam_jax/datasets/augmentation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"33f3bcef5a763ff8","mcp_get_code":{"code_sha256":"33f3bcef5a763ff8"}},{"arxiv_id":"2006.14536","paper":"/paper/smooth-adversarial-training","title":"Smooth Adversarial Training","date":"2020-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cihangxie/SmoothAdversarialTraining","path":"EfficientNet/autoaugment.py","file_url":"https://github.com/cihangxie/SmoothAdversarialTraining/blob/HEAD/EfficientNet/autoaugment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ea1b2be8595d0bb3","mcp_get_code":{"code_sha256":"ea1b2be8595d0bb3"}},{"arxiv_id":"2001.01265","paper":"/paper/fdftnet-facing-off-fake-images-using-fake","title":"FDFtNet: Facing Off Fake Images using Fake Detection Fine-tuning Network","date":"2020-01-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cutz-j/FDFtNet","path":"utils/aug.py","file_url":"https://github.com/cutz-j/FDFtNet/blob/HEAD/utils/aug.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ab5c0091c67ee617","mcp_get_code":{"code_sha256":"ab5c0091c67ee617"}},{"arxiv_id":"1911.11907","paper":"/paper/ghostnet-more-features-from-cheap-operations","title":"GhostNet: More Features from Cheap Operations","date":"2019-11-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"KopiSoftware/Ghost_ResNet56","path":"train_Ghost_ResNet56.py","file_url":"https://github.com/KopiSoftware/Ghost_ResNet56/blob/HEAD/train_Ghost_ResNet56.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"ce3aa75b714c404e","mcp_get_code":{"code_sha256":"ce3aa75b714c404e"}},{"arxiv_id":"1911.04252","paper":"/paper/self-training-with-noisy-student-improves","title":"Self-training with Noisy Student improves ImageNet classification","date":"2019-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/noisystudent","path":"randaugment.py","file_url":"https://github.com/google-research/noisystudent/blob/HEAD/randaugment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d42d54a4353367b5","mcp_get_code":{"code_sha256":"d42d54a4353367b5"}},{"arxiv_id":"1909.13719","paper":"/paper/randaugment-practical-data-augmentation-with","title":"RandAugment: Practical automated data augmentation with a reduced search space","date":"2019-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nachiket273/pytorch_resnet_rs","path":"model/randaugment.py","file_url":"https://github.com/nachiket273/pytorch_resnet_rs/blob/HEAD/model/randaugment.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a07328daac80e5d4","mcp_get_code":{"code_sha256":"a07328daac80e5d4"}},{"arxiv_id":"1909.13719","paper":"/paper/randaugment-practical-data-augmentation-with","title":"RandAugment: Practical automated data augmentation with a reduced search space","date":"2019-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lyxxn0414/test-data-generation","path":"auto_augment.py","file_url":"https://github.com/lyxxn0414/test-data-generation/blob/HEAD/auto_augment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"93e2ff77da69661e","mcp_get_code":{"code_sha256":"93e2ff77da69661e"}},{"arxiv_id":"1906.11172","paper":"/paper/learning-data-augmentation-strategies-for","title":"Learning Data Augmentation Strategies for Object Detection","date":"2019-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cy0616/data_augment","path":"autoaugment_utils.py.py","file_url":"https://github.com/cy0616/data_augment/blob/HEAD/autoaugment_utils.py.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"d845de56fb50b753","mcp_get_code":{"code_sha256":"d845de56fb50b753"}},{"arxiv_id":"1905.11468","paper":"/paper/scaleable-input-gradient-regularization-for","title":"Scaleable input gradient regularization for adversarial robustness","date":"2019-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cfinlay/tulip","path":"cifar10/dataloader.py","file_url":"https://github.com/cfinlay/tulip/blob/HEAD/cifar10/dataloader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"27af56f88823ce93","mcp_get_code":{"code_sha256":"27af56f88823ce93"}},{"arxiv_id":"1812.01187","paper":"/paper/bag-of-tricks-for-image-classification-with","title":"Bag of Tricks for Image Classification with Convolutional Neural Networks","date":"2018-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PistonY/ResidualAttentionNetwork","path":"lib/piston_util.py","file_url":"https://github.com/PistonY/ResidualAttentionNetwork/blob/HEAD/lib/piston_util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"de47a57778dd152f","mcp_get_code":{"code_sha256":"de47a57778dd152f"}},{"arxiv_id":"1802.08530","paper":"/paper/training-wide-residual-networks-for","title":"Training wide residual networks for deployment using a single bit for each weight","date":"2018-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"McDonnell-Lab/1-bit-per-weight","path":"Utils.py","file_url":"https://github.com/McDonnell-Lab/1-bit-per-weight/blob/HEAD/Utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f9677443f26ffc60","mcp_get_code":{"code_sha256":"f9677443f26ffc60"}},{"arxiv_id":"1708.04552","paper":"/paper/improved-regularization-of-convolutional","title":"Improved Regularization of Convolutional Neural Networks with Cutout","date":"2017-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PsorTheDoctor/microarray-data","path":"utils/augmentation.py","file_url":"https://github.com/PsorTheDoctor/microarray-data/blob/HEAD/utils/augmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4a5f5e6272b139bf","mcp_get_code":{"code_sha256":"4a5f5e6272b139bf"}},{"arxiv_id":"1708.04552","paper":"/paper/improved-regularization-of-convolutional","title":"Improved Regularization of Convolutional Neural Networks with Cutout","date":"2017-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"albumentations-team/albumentations","path":"albumentations/augmentations/dropout/functional.py","file_url":"https://github.com/albumentations-team/albumentations/blob/HEAD/albumentations/augmentations/dropout/functional.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d912ce51776a4d78","mcp_get_code":{"code_sha256":"d912ce51776a4d78"}},{"arxiv_id":"1708.04552","paper":"/paper/improved-regularization-of-convolutional","title":"Improved Regularization of Convolutional Neural Networks with Cutout","date":"2017-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mingsun-tse/good-da-in-kd","path":"helper/loops.py","file_url":"https://github.com/mingsun-tse/good-da-in-kd/blob/HEAD/helper/loops.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0972fd225cc9b653","mcp_get_code":{"code_sha256":"0972fd225cc9b653"}}]}