Home › Code › drop_connect

drop_connect

Syntologyentry name in harvested code

Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

drop_connect appears in the code Syntology harvested for 73 papers, as 17 distinct code bodies found in 79 places (a place is one code body under one paper). Of the 73 papers, 72 with a sample that ran: 6 with a run with no instrument failure, 66 where every run was a failure of Syntology's instrument. 4 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 drop_connect 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 17 distinct code bodies named drop_connect: 16 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 11 where Syntology's instrument failed) · 1 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:

0ran · honoured contract
0ran · violated contract
2ran · our draft was wrong
9ran; the contract check could not run
5ran
1unverified
4fingerprinted

Licence is a property of each copy, so it is counted per place: 49 of the 79 places are pointer only (Syntology does not serve that copy's text); at 32 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

73 papers shown of 73, newest first; 79 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 4 papers added by Syntology; 3 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.

PaperDateFileStatus SyntologyLicence
Breaking the Compression Barrier: Cross-Architecture Compression Boundary Learning via Reverse Regrowth added by Syntology 2026-08 (from id) EnumaCaliber/BRIDGE/models/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted no licence file found · pointer only
When AUC Misleads: Polarization-Aware Evaluation of Deepfake Detectors under Domain Shift added by Syntology 2026-06 (from id) megvii-research/CADDM/backbones/efficientnet_pytorch/utils.py 2dd5dfa94542911e ran; the contract check could not run (RAISES) Apache-2.0 (permissive) here; the stored copy is pointer only
Domain-Skewed Federated Learning with Feature Decoupling and Calibration added by Syntology 2026-03 (from id) mala-lab/F2DC/backbone/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only
Stable Coresets via Posterior Sampling: Aligning Induced and Full Loss Landscapes added by Syntology 2025-11 (from id) decile-team/cords/cords/utils/models/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
arXiv:2507.06262 2025-07 (from id) cats1520cakes/Q-Detection-A-Quantum-Classical-Hybrid-Poisoning-Attack-Detection-Method/models/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted no licence file found · pointer only
Rethinking Continual Learning with Progressive Neural Collapse 30 May 2025 Continue-Edge-AI-Lab/ProNC/backbone/EfficientNet.py f1e3c822763f3ebb ran; the contract check could not run (RAISES) MIT (permissive)
Provably Near-Optimal Federated Ensemble Distillation with Negligible Overhead 10 Feb 2025 kuangliu/pytorch-cifar/models/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices 8 Dec 2024 jyzgh/DapperFL/fedml_api/standalone/domain_generalization/backbone/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only
Continual Learning in the Frequency Domain 9 Oct 2024 EMLS-ICTCAS/CLFD/backbone/EfficientNet.py f1e3c822763f3ebb ran; the contract check could not run (RAISES) MIT (permissive)
CLIP with Generative Latent Replay: a Strong Baseline for Incremental Learning 22 Jul 2024 aimagelab/mammoth/backbone/EfficientNet.py f1e3c822763f3ebb ran; the contract check could not run (RAISES) MIT (permissive)
BWS: Best Window Selection Based on Sample Scores for Data Pruning across Broad Ranges 5 Jun 2024 NohyunKi/BWS/model/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted no licence file found · pointer only
Continual Learning with Weight Interpolation 5 Apr 2024 jedrzejkozal/weight-interpolation-cl/backbone/EfficientNet.py f1e3c822763f3ebb ran; the contract check could not run (RAISES) MIT (permissive)
A Unified and General Framework for Continual Learning 20 Mar 2024 joey-wang123/CL-refresh-learning/backbone/EfficientNet.py f1e3c822763f3ebb ran; the contract check could not run (RAISES) MIT (permissive)
Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection 4 Mar 2024 qingyuliu/exposing-the-deception/models/MI_Net.py d3319e3d34ca90ca ran; the contract check could not run (RAISES) Apache-2.0 (permissive)
GenFace: A Large-Scale Fine-Grained Face Forgery Benchmark and Cross Appearance-Edge Learning 3 Feb 2024 jenine-321/genface/model/efficient_net/efficientnet_pytorch/utils.py d3319e3d34ca90ca ran; the contract check could not run (RAISES) no licence file found · pointer only
Optimizing Neural Networks with Gradient Lexicase Selection 19 Dec 2023 ld-ing/gradient-lexicase/models/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models 4 Nov 2023 optml-group/bibaddiff/classifier/models/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted no licence file found · pointer only
ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection 31 Oct 2023 lartpang/zoomnext/methods/backbone/efficientnet_utils.py d3319e3d34ca90ca ran; the contract check could not run (RAISES) no licence file found · pointer only
Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer 11 Oct 2023 ZackZikaiXiao/FedGraB/model/effutil.py f1e3c822763f3ebb ran; the contract check could not run (RAISES) no licence file found · pointer only
CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis 6 Oct 2023 kuangliu/pytorch-CIFAR/models/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Chunking: Continual Learning is not just about Distribution Shift 3 Oct 2023 tlee43/chunking-setting/backbone/EfficientNet.py f1e3c822763f3ebb ran; the contract check could not run (RAISES) no licence file found · pointer only
Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learning 28 Sep 2023 wenkehuang/fccl/fccl+/backbone/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted no licence file found · pointer only
Fine-Grained Cross-View Geo-Localization Using a Correlation-Aware Homography Estimator 31 Aug 2023 xlwangdev/hc-net/models/efficientnet_pytorch/utils.py d3319e3d34ca90ca ran; the contract check could not run (RAISES) no licence file found · pointer only
Fast Adversarial Training with Smooth Convergence 24 Aug 2023 FAT-CS/ConvergeSmooth/models/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted no licence file found · pointer only
SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels 23 Aug 2023 Cralence/SILT/model/backbone/efficientnet_pytorch/utils.py d3319e3d34ca90ca ran; the contract check could not run (RAISES) no licence file found · pointer only
APBench: A Unified Benchmark for Availability Poisoning Attacks and Defenses 7 Aug 2023 lafeat/apbench/nets/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Improving Generalization of Adversarial Training via Robust Critical Fine-Tuning 1 Aug 2023 Immortalise/RiFT/models/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted no licence file found · pointer only
Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability 15 Jul 2023 cgcl-codes/transferattacksurrogates/TransferAttack/models/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Training on Thin Air: Improve Image Classification with Generated Data 24 May 2023 yongchao97/diffusion_inversion/src/models/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Manifold-Aware Self-Training for Unsupervised Domain Adaptation on Regressing 6D Object Pose 18 May 2023 Gorilla-Lab-SCUT/MAST/MAST/models/efficientnet_utils.py 2dd5dfa94542911e ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only
LAVA: Data Valuation without Pre-Specified Learning Algorithms 28 Apr 2023 ruoxi-jia-group/lava/models/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Regularizing Second-Order Influences for Continual Learning 20 Apr 2023 feifeiobama/InfluenceCL/backbone/EfficientNet.py f1e3c822763f3ebb ran; the contract check could not run (RAISES) MIT (permissive)
UNICORN: A Unified Backdoor Trigger Inversion Framework 5 Apr 2023 ru-system-software-and-security/unicorn/models/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms 22 Feb 2023 ruoxi-jia-group/asset/models/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
DIVISION: Memory Efficient Training via Dual Activation Precision 5 Aug 2022 guanchuwang/division/cifar_models/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Dual Representation Learning for Out-of-Distribution Detection 19 Jun 2022 lawliet-zzl/drl/code/models/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification 17 Jun 2022 cambridge-mlg/fit/src/efficientnet_utils.py d3319e3d34ca90ca ran; the contract check could not run (RAISES) MIT (permissive)
Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information 11 Apr 2022 reds-lab/narcissus/models/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability 10 Mar 2022 CVMI-Lab/KDEP/src/efficientnet_utils.py d3319e3d34ca90ca ran; the contract check could not run (RAISES) Apache-2.0 (permissive)
MetaFormer: A Unified Meta Framework for Fine-Grained Recognition 5 Mar 2022 dqshuai/metaformer/models/MBConv.py 2dd5dfa94542911e ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only
AutoBalance: Optimized Loss Functions for Imbalanced Data 4 Jan 2022 ucr-optml/autobalance/models/utils.py 2dd5dfa94542911e ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only
Projected GANs Converge Faster 1 Nov 2021 dome272/ProjectedGAN-pytorch/projected_gan.py ed953cd5fd3a44c8 ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive)
Open-Set Recognition: a Good Closed-Set Classifier is All You Need? 12 Oct 2021 sgvaze/osr_closed_set_all_you_need/models/miscel_utils.py d3319e3d34ca90ca ran; the contract check could not run (RAISES) MIT (permissive)
YOLOP: You Only Look Once for Panoptic Driving Perception 25 Aug 2021 datvuthanh/HybridNets/hybridnets/model.py 2dd5dfa94542911e ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only
Revealing the Distributional Vulnerability of Discriminators by Implicit Generators 23 Aug 2021 lawliet-zzl/fig/code_FIG/models/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Combining EfficientNet and Vision Transformers for Video Deepfake Detection 6 Jul 2021 davide-coccomini/Combining-EfficientNet-and-Vision-Transformers-for-Video-Deepfake-Detection/cross-efficient-vit/efficient_net/efficientnet_pytorch/utils.py d3319e3d34ca90ca ran; the contract check could not run (RAISES) MIT (permissive)
CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation 6 Jul 2021 alsgkals2/CoReD_Released/utils.py f1e3c822763f3ebb ran; the contract check could not run (RAISES) MIT (permissive)
Memory Efficient Meta-Learning with Large Images 2 Jul 2021 cambridge-mlg/LITE/src/efficientnet_utils.py d3319e3d34ca90ca ran; the contract check could not run (RAISES) MIT (permissive)
Adversarial Examples Make Strong Poisons 21 Jun 2021 lhfowl/adversarial_poisons/poison_evaluation/models/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning 7 Jun 2021 thlarsen13/thlarsen_uncertainty_models/uncertainty_baselines/models/efficientnet_utils.py 48ffc519251345a8 ran Apache-2.0 (permissive)
Memory Wrap: a Data-Efficient and Interpretable Extension to Image Classification Models 1 Jun 2021 KRLGroup/memory-wrap/paper/architectures/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Learning from Ambiguous Labels for Lung Nodule Malignancy Prediction 23 Apr 2021 Merrical/DAR/EfficientNet_2d/utils.py 2dd5dfa94542911e ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only
M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection 20 Apr 2021 wangjk666/M2TR-Multi-modal-Multi-scale-Transformers-for-Deepfake-Detection/M2TR/models/efficientnet.py 45eada2b88e70500 ran MIT (permissive)
Multi-attentional Deepfake Detection 3 Mar 2021 yoctta/multiple-attention/models/MAT.py 2dd5dfa94542911e ran; the contract check could not run (RAISES) no licence file found · pointer only
AlphaNet: Improved Training of Supernets with Alpha-Divergence 16 Feb 2021 facebookresearch/AttentiveNAS/models/attentive_nas_dynamic_model.py 6053cb1369b46c73 ran; the contract check could not run (RAISES) licence not identified · pointer only
FSD50K: An Open Dataset of Human-Labeled Sound Events 1 Oct 2020 SarthakYadav/GISE-51-pytorch/src/models/efficientnet_pytorch/utils.py d3319e3d34ca90ca ran; the contract check could not run (RAISES) MIT (permissive)
BOP Challenge 2020 on 6D Object Localization 15 Sep 2020 azad96/cosypose-custom/cosypose/models/efficientnet_utils.py 2dd5dfa94542911e ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only
CosyPose: Consistent multi-view multi-object 6D pose estimation 19 Aug 2020 princeton-vl/coupled-iterative-refinement/pose_models/efficientnet_utils.py 2dd5dfa94542911e ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only
T-GD: Transferable GAN-generated Images Detection Framework 10 Aug 2020 cutz-j/T-GD/models/utils.py 2dd5dfa94542911e ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only
Smooth Adversarial Training 25 Jun 2020 cihangxie/SmoothAdversarialTraining/EfficientNet/utils.py d63756c8fcf336f4 ran MIT (permissive)
Neural Architecture Transfer 12 May 2020 human-analysis/neural-architecture-transfer/codebase/networks/natnet.py 7028564474e3fefd unverified no licence file found · pointer only
Designing Network Design Spaces 30 Mar 2020 ZHANGHeng19931123/MutualGuide/models/backbone/efficientnet_backbone.py 45eada2b88e70500 ran MIT (permissive)
Can we have it all? On the Trade-off between Spatial and Adversarial Robustness of Neural Networks 26 Feb 2020 ksandeshk/spatial-vs-robustness/stdcnn/models/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Towards Robust and Reproducible Active Learning Using Neural Networks 21 Feb 2020 acl21/deep-active-learning-pytorch/pycls/utils/net.py 79583b4154444ddf ran · our draft was wrong fingerprinted MIT (permissive)
YOLACT++: Better Real-time Instance Segmentation 3 Dec 2019 SpaceView/Yolact_EfficientNet/efficientnet/utils.py 2dd5dfa94542911e ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only
YOLACT++: Better Real-time Instance Segmentation 3 Dec 2019 kaylode/Clothes-Segmentation/efficient_utils.py 1667bcdf49534735 ran; the contract check could not run (RAISES) MIT (permissive)
Leveraging Procedural Generation to Benchmark Reinforcement Learning 3 Dec 2019 rgilman33/carlita/efficientnet_utils.py d3319e3d34ca90ca ran; the contract check could not run (RAISES) MIT recorded; this copy not marked cleared · pointer only
EfficientDet: Scalable and Efficient Object Detection 20 Nov 2019 sevakon/efficientdet/model/efficientnet/utils.py 2dd5dfa94542911e ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only
EfficientDet: Scalable and Efficient Object Detection 20 Nov 2019 Jintao-Huang/EfficientDet_PyTorch/models/efficientnet.py 53d13d88994382df ran; the contract check could not run (RAISES) Apache-2.0 (permissive)
Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency 12 Aug 2019 vaapopescu/gradient-pruning/models/efficientnet.py b1ba3f72f7fe5886 ran fingerprinted MIT (permissive)
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks 28 May 2019 facebookresearch/ClassyVision/classy_vision/models/efficientnet.py 01ef2c316f547d5d ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive)
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks 28 May 2019 shijianjian/efficientnet-pytorch-3d/efficientnet_pytorch_3d/model.py 4e82aac968b327d5 ran; the contract check could not run (RAISES) Apache-2.0 (permissive)
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks 28 May 2019 AmirmohammadRostami/KeywordsSpotting-EfficientNet-A0/utils/efficientnet_pytorch/model.py 1667bcdf49534735 ran; the contract check could not run (RAISES) MIT (permissive)
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks 28 May 2019 Jintao-Huang/EfficientNet_PyTorch/models/efficientnet.py 53d13d88994382df ran; the contract check could not run (RAISES) Apache-2.0 (permissive)
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks 28 May 2019 facebookresearch/pycls/pycls/models/effnet.py 79583b4154444ddf ran · our draft was wrong fingerprinted MIT (permissive)
Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks 23 Aug 2018 qubvel/segmentation_models.pytorch/segmentation_models_pytorch/encoders/_efficientnet.py 7366397639253b99 ran MIT (permissive)
Deep Residual Learning for Image Recognition 10 Dec 2015 vineeths96/Gradient-Compression/models/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
AAAI id aaai_32254 HongsinLee/FLAIR/backbone/EfficientNet.py f1e3c822763f3ebb ran; the contract check could not run (RAISES) MIT (permissive)
CVF open access id Huang_Boosting_Accuracy_and_Robustness_of_Student_Models_via_Adaptive_Adversarial_CVPR_2023_paper boyellow/AdaAD/networks/efficientnet.py 4304a326c593f8db ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only

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