mixup_data
Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.
mixup_data appears in the code Syntology harvested for 51 papers, as 35 distinct code bodies found in 59 places (a place is one code body under one paper). Of the 51 papers, 49 with a sample that ran: 12 with a run with no instrument failure, 37 where every run was a failure of Syntology's instrument. 9 of the code bodies carry a behaviour fingerprint.
What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named mixup_data do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; get_code(code_sha256="…") returns this sample's fingerprint on the shared battery, with the battery's shuffled null and lift; not shown on this site (how to connect). "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.
Samples Syntology
The 35 distinct code bodies named mixup_data: 32 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 21 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. One tile per status, in the site's fixed vocabulary, each code body counted once:
Licence is a property of each copy, so it is counted per place: 32 of the 59 places are pointer only (Syntology does not serve that copy's text); at 3 of those this paper's copy is under a permissive licence, but the stored copy of the same code that Syntology serves is not cleared for its text (hover the licence cell for why). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.
“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “the contract check could not run” (RAISES, DEP_MISSING or TIMEOUT; hover a row's label for which) are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page; “with no instrument failure” is honoured, violated and ran with no contract checked. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Papers
51 papers shown of 51, newest first; 59 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 3 papers added by Syntology; 5 papers have no page here and are shown by their id only (arXiv: for an arXiv id; an id from another venue, such as ACL Anthology or AAAI, is named as that venue's id, never as an arXiv id). Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.
| Paper | Date | File | Status Syntology | Licence |
|---|---|---|---|---|
| Be Fair! Can Machine Learning Engineering Agents Adhere to Fairness Constraints? added by Syntology | 2026-06 (from id) | anna-richter/be-fair/aide/logs/17-addition_2/best_solution.py fc5b29d5049847a0 |
ran | Apache-2.0 (permissive) |
| Rectifying Soft-Label Entangled Bias in Long-Tailed Dataset Distillation added by Syntology | 2025-11 (from id) | j-cyoung/ADSA_DD/SRe2L/cifar10/relabel_cifar_adsa.py 5d6df350b6eefccd |
ran; the contract check could not run (RAISES) | no licence file found · pointer only |
| Scaling Up Temporal Domain Generalization via Temporal Experts Averaging added by Syntology | 2025-09 (from id) | zxcvfd13502/TEA/methods/mixup.py e21ef67063f634df |
ran fingerprinted | no licence file found · pointer only |
| Diversity-Driven Synthesis: Enhancing Dataset Distillation through Directed Weight Adjustment | 26 Sep 2024 | angusdujw/diversity-driven-synthesis/validation/validation_cifar.py 5d6df350b6eefccd |
ran; the contract check could not run (RAISES) | no licence file found · pointer only |
| Comprehensive Attribution: Inherently Explainable Vision Model with Feature Detector | 27 Jul 2024 | zood123/comet/train_module.py 8897714b1e9b6396 |
ran; the contract check could not run (RAISES) · metamorphic tier: deterministic | no licence file found · pointer only |
| Uniformly Stable Algorithms for Adversarial Training and Beyond | 3 May 2024 | jiancongxiao/moreau-envelope-sgd/adversarial_robustness_overfitting/mea_train_cifar.py b20f1357b1d8dbf8 |
ran; the contract check could not run (RAISES) | no licence file found · pointer only |
| Distribution-Aware Data Expansion with Diffusion Models | 11 Mar 2024 | haoweiz23/distdiff/augmentations/mixup.py 345e624f9cc2e32a |
ran; the contract check could not run (RAISES) · metamorphic tier: deterministic | no licence file found · pointer only |
| MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superposition | 5 Dec 2023 | IBM/multiple-input-multiple-output-nets/MIMOConv/src/mixup.py 112a7683003fa463 |
ran; the contract check could not run (RAISES) | Apache-2.0 (permissive) |
| Label-Only Model Inversion Attacks via Knowledge Transfer | 30 Oct 2023 | val-iisc/hard-label-model-stealing/code/train_student/train_student.py 9917ee672087e236 |
ran; the contract check could not run (RAISES) | no licence file found · pointer only |
| Feature Fusion from Head to Tail for Long-Tailed Visual Recognition | 12 Jun 2023 | keke921/h2t/methods.py 345e624f9cc2e32a |
ran; the contract check could not run (RAISES) · metamorphic tier: deterministic | MIT (permissive) |
| Steering Prototypes with Prompt-tuning for Rehearsal-free Continual Learning | 16 Mar 2023 | lzvv123456/contrastive-prototypical-prompt/utils.py 345e624f9cc2e32a |
ran; the contract check could not run (RAISES) · metamorphic tier: deterministic | Apache-2.0 (permissive) |
| TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization | 9 Mar 2023 | alanjeffares/tangos/src/regularizers.py f8d74fe1d88a952d |
ran; the contract check could not run (RAISES) · metamorphic tier: deterministic fingerprinted | BSD-3-Clause (permissive) |
| TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization | 9 Mar 2023 | vanderschaarlab/tangos/src/tangos/regularizers.py 04a79674a945ae82 |
ran | BSD-3-Clause (permissive) |
| Certified Robust Neural Networks: Generalization and Corruption Resistance | 3 Mar 2023 | ryanlucas3/hr_neural_networks/HR_Neural_Networks/Paper_experiments/Section_6.2/Rice_HR/Rice_HR.py 8d1360df29c61c25 |
ran fingerprinted | MIT (permissive) |
| PCRLv2: A Unified Visual Information Preservation Framework for Self-supervised Pre-training in Medical Image Analysis | 2 Jan 2023 | RL4M/PCRLv2/train_2d.py 27b5c00cc9d84e47 |
ran | MIT (permissive) |
| A2: Efficient Automated Attacker for Boosting Adversarial Training | 7 Oct 2022 | alipay/A2-efficient-automated-attacker-for-boosting-adversarial-training/train_cifar10.py b20f1357b1d8dbf8 |
ran; the contract check could not run (RAISES) | Apache-2.0 (permissive) |
| Long-Tailed Class Incremental Learning | 1 Oct 2022 | xialeiliu/Long-Tailed-CIL/src/approach/LAS_utils.py 345e624f9cc2e32a |
ran; the contract check could not run (RAISES) · metamorphic tier: deterministic | MIT (permissive) |
| SparCL: Sparse Continual Learning on the Edge | 20 Sep 2022 | identical code first harvested elsewhere bd19a75b8bed0114 |
ran; the contract check could not run (RAISES) | licence of this copy not recorded |
| Identifying Hard Noise in Long-Tailed Sample Distribution | 27 Jul 2022 | yxymessi/H2E-Framework/eccv_github/noise_longtail/code/utils.py fd81207449c239dd |
ran; the contract check could not run (RAISES) | MIT (permissive) here; the stored copy is pointer only |
| One-Pixel Shortcut: on the Learning Preference of Deep Neural Networks | 24 May 2022 | cychomatica/one-pixel-shotcut/augmentation/Mixup.py 8897714b1e9b6396 |
ran; the contract check could not run (RAISES) · metamorphic tier: deterministic | Apache-2.0 (permissive) here; the stored copy is pointer only |
| From Modern CNNs to Vision Transformers: Assessing the Performance, Robustness, and Classification Strategies of Deep Learning Models in Histopathology | 11 Apr 2022 | hhi-aml/histobenchmark/code/main_patho_lightning.py c0a4cf940a467481 |
ran; the contract check could not run (RAISES) · metamorphic tier: deterministic fingerprinted | no licence file found · pointer only |
| FedCorr: Multi-Stage Federated Learning for Label Noise Correction | 10 Apr 2022 | identical code first harvested elsewhere 8897714b1e9b6396 |
ran; the contract check could not run (RAISES) · metamorphic tier: deterministic | licence of this copy not recorded |
| Few-shot Learning as Cluster-induced Voronoi Diagrams: A Geometric Approach | 5 Feb 2022 | horsepurve/deepvoro/wrn_mixup_model.py b53e6443d8a7fbf3 |
ran fingerprinted | MIT (permissive) |
| MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge | 26 Oct 2021 | boone891214/MEST/main_sparse_train.py bd19a75b8bed0114 |
ran; the contract check could not run (RAISES) | no licence file found · pointer only |
| Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot? | 1 Jul 2021 | boone891214/sanity-check-LTH/cifar/main_prune_train.py fd81207449c239dd |
ran; the contract check could not run (RAISES) | no licence file found · pointer only |
| SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training | 2 Jun 2021 | somepago/saint/augmentations.py 3f8482bac2c6b9db |
ran | Apache-2.0 recorded; this copy not marked cleared · pointer only |
| Improving Calibration for Long-Tailed Recognition | 1 Apr 2021 | Jia-Research-Lab/MiSLAS/methods.py 345e624f9cc2e32a |
ran; the contract check could not run (RAISES) · metamorphic tier: deterministic | MIT (permissive) |
| MixSearch: Searching for Domain Generalized Medical Image Segmentation Architectures | 26 Feb 2021 | identical code first harvested elsewhere 345e624f9cc2e32a |
ran; the contract check could not run (RAISES) · metamorphic tier: deterministic | licence of this copy not recorded |
| Low Curvature Activations Reduce Overfitting in Adversarial Training | 15 Feb 2021 | identical code first harvested elsewhere b20f1357b1d8dbf8 |
ran; the contract check could not run (RAISES) | licence of this copy not recorded |
| ResLT: Residual Learning for Long-tailed Recognition | 26 Jan 2021 | jiequancui/ResLT/CIFAR/cifarTrain_reslt_cifar10.py 760098c40816bbe8 |
ran; the contract check could not run (RAISES) · metamorphic tier: deterministic | MIT (permissive) |
| Free Lunch for Few-shot Learning: Distribution Calibration | 16 Jan 2021 | sabagh1994/code_dcf/wrn_model.py 56ca7839c3f149ad |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning | 17 Oct 2020 | PaulAlbert31/iMix/utils.py d289cf4cd8e95ada |
unverified | no licence file found · pointer only |
| Data Augmentation for Meta-Learning | 14 Oct 2020 | renkunni/metaaug/train_aug.py ce1ad25b0d64fdd7 |
ran · our draft was wrong | MIT (permissive) |
| Data Augmentation for Meta-Learning | 14 Oct 2020 | RenkunNi/MetaAug/models/R2D2_embedding_mixup.py fcec7c373958ae2d |
ran | MIT (permissive) |
| High-Capacity Expert Binary Networks | 7 Oct 2020 | 1adrianb/expert-binary-networks/utils/mixup.py aafeecd1181e3b50 |
ran fingerprinted | MIT (permissive) |
| Bag of Tricks for Adversarial Training | 1 Oct 2020 | identical code first harvested elsewhere b20f1357b1d8dbf8 |
ran; the contract check could not run (RAISES) | licence of this copy not recorded |
| Comparing to Learn: Surpassing ImageNet Pretraining on Radiographs By Comparing Image Representations | 15 Jul 2020 | funnyzhou/C2L_MICCAI2020/train_C2L_res18.py 572eb5c34ec5ef0c |
ran; the contract check could not run (RAISES) · metamorphic tier: deterministic | MIT (permissive) |
| Adversarial Weight Perturbation Helps Robust Generalization | 13 Apr 2020 | csdongxian/AWP/AT_AWP/train_cifar10.py b20f1357b1d8dbf8 |
ran; the contract check could not run (RAISES) | MIT (permissive) |
| Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks | 3 Mar 2020 | locuslab/robust_overfitting/train_cifar.py b20f1357b1d8dbf8 |
ran; the contract check could not run (RAISES) | no licence file found · pointer only |
| Overfitting in adversarially robust deep learning | 26 Feb 2020 | identical code first harvested elsewhere b20f1357b1d8dbf8 |
ran; the contract check could not run (RAISES) | licence of this copy not recorded |
| Class-Imbalanced Semi-Supervised Learning | 17 Feb 2020 | MinsungHyun/Class-Imbalanced-Semi-Supervised-Learning/CISSL_cls/lib/utils.py b062bea460457feb |
ran; the contract check could not run (RAISES) | MIT (permissive) here; the stored copy is pointer only |
| Gated Convolutional Networks with Hybrid Connectivity for Image Classification | 26 Aug 2019 | winycg/HCGNet/main_cifar.py 8897714b1e9b6396 |
ran; the contract check could not run (RAISES) · metamorphic tier: deterministic | no licence file found · pointer only |
| Gated Convolutional Networks with Hybrid Connectivity for Image Classification | 26 Aug 2019 | winycg/HCGNet/main_imagenet.py 3d04404ba40305cc |
ran; the contract check could not run (RAISES) · metamorphic tier: deterministic | no licence file found · pointer only |
| Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning | 8 Aug 2019 | EricArazo/PseudoLabeling/utils_pseudoLab/utils_ssl.py 3547e83bd03591ad |
ran | MIT (permissive) |
| Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy | 16 Jun 2019 | identical code first harvested elsewhere 11b0ec76b88d8553 |
ran · our draft was wrong | licence of this copy not recorded |
| Adversarial Examples Are Not Bugs, They Are Features | 6 May 2019 | ndb796/pytorch-adversarial-training-cifar/interpolated_adversarial_training.py 11b0ec76b88d8553 |
ran · our draft was wrong | no licence file found · pointer only |
| mixup: Beyond Empirical Risk Minimization | 25 Oct 2017 | hongyi-zhang/mixup/cifar/utils.py c8f7fd47a7acbaa3 |
ran; the contract check could not run (RAISES) · metamorphic tier: deterministic | BSD-3-Clause (permissive) |
| mixup: Beyond Empirical Risk Minimization | 25 Oct 2017 | smilelab-fl/fednoisy/fednoisy/utils/mixup.py 1905009bf59716f6 |
ran; the contract check could not run (RAISES) fingerprinted | Apache-2.0 (permissive) |
| mixup: Beyond Empirical Risk Minimization | 25 Oct 2017 | Ryoo72/dimension-wise_mixup/models/utils.py b062bea460457feb |
ran; the contract check could not run (RAISES) | licence not identified · pointer only |
| mixup: Beyond Empirical Risk Minimization | 25 Oct 2017 | andychinka/dcase-challenge/asc/data_aug.py 4ef20d27ae01e4c3 |
ran; the contract check could not run (RAISES) fingerprinted | no licence file found · pointer only |
| mixup: Beyond Empirical Risk Minimization | 25 Oct 2017 | Hazelsuko07/InstaHide/train_cross.py e7229d6a2824b389 |
unverified | MIT (permissive) |
| Towards Deep Learning Models Resistant to Adversarial Attacks | 19 Jun 2017 | identical code first harvested elsewhere b20f1357b1d8dbf8 |
ran; the contract check could not run (RAISES) | licence of this copy not recorded |
| Towards Deep Learning Models Resistant to Adversarial Attacks | 19 Jun 2017 | identical code first harvested elsewhere 11b0ec76b88d8553 |
ran · our draft was wrong | licence of this copy not recorded |
| Adversarial Discriminative Domain Adaptation | 17 Feb 2017 | Backdrop9019/adda_pytorch-pseudo-mixup-/core/adapt.py 084dfb3d87216615 |
ran; the contract check could not run (RAISES) | no licence file found · pointer only |
| OpenReview id openreview_GNrBEnHPPv | Gang-ww/ABFnet/utils.py d9c095b213729e09 |
ran | MIT (permissive) | |
| AAAI id aaai_29262 | Keke921/H2T/methods.py 345e624f9cc2e32a |
ran; the contract check could not run (RAISES) · metamorphic tier: deterministic | MIT (permissive) | |
| AAAI id aaai_16993 | MJ1021/kcm-code/KCM_implementation_01152021/Binary/utils.py de0013b0e10f3103 |
unverified | Apache-2.0 (permissive) | |
| CVF open access id Lazarou_Iterative_Label_Cleaning_for_Transductive_and_Semi-Supervised_Few-Shot_Learning_ICCV_2021_paper | MichalisLazarou/iLPC/wrn_mixup_model.py b53e6443d8a7fbf3 |
ran fingerprinted | MIT (permissive) | |
| id 136850478 (not an arXiv id) | leo-gb/UMA/ccs_training/models/mixup.py 345e624f9cc2e32a |
ran; the contract check could not run (RAISES) · metamorphic tier: deterministic | MIT (permissive) |
This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is under a permissive licence, but the stored copy of the same code that Syntology serves is not cleared for its text. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections