Home › Code › train_step

train_step

Syntologyentry name in harvested coderead from the graph 2026-09-24

train_step appears in the code Syntology harvested for 47 papers, as 57 distinct code bodies found in 58 places (a place is one code body under one paper). At least one of them ran in 17 of the papers; 1 of the code bodies carries 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 train_step 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; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 18 of the 57 distinct code bodies named train_step; 39 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

4ran · honoured contract
0ran · violated contract
3ran · our draft was wrong
3ran · fixture could not drive it
8ran
39unverified
1fingerprinted

Licence is a property of each copy, so it is counted per place: 24 of the 58 places are pointer only (Syntology does not serve that copy's text). 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 “fixture could not drive it” 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.

Papers

47 papers shown of 47, newest first; 58 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 6 papers added by Syntology; 4 papers have no page here and are shown by arXiv id only. 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, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
Orthogonal Representation Editing: Decoupling Semantic Entanglement in Batch Knowledge Editing of LLMs added by Syntology 2026-06 (from id) YVVH/ORE/ORE/ORE_main.py 5813326e00feabd0 unverified MIT (permissive)
In-Context Learning in Linear vs. Quadratic Attention Models: An Empirical Study on Regression Tasks added by Syntology 2026-02 (from id) Yushgoel/icl-benchmarking/src/training/trainer.py a9cac69a38c2e2f8 unverified no licence file found · pointer only
Softmax as Linear Attention in the Large-Prompt Regime: a Measure-based Perspective added by Syntology 2025-12 (from id) eboursier/softmax_as_linear/run_experiments.py e770dd61f4f4c86a unverified no licence file found · pointer only
Masked Symbol Modeling for Demodulation of Oversampled Baseband Communication Signals in Impulsive Noise-Dominated Channels added by Syntology 2025-12 (from id) OguzBedir/Masked_Symbol_Modeling/core/engine.py cdc6afbb64a20f40 unverified no licence file found · pointer only
A Probabilistic U-Net Approach to Downscaling Climate Simulations added by Syntology 2025-11 (from id) MaryamAlipourH/prob-unet-climate-downscaling/src/trainmodel.py 7ba04b2294ce3fac unverified no licence file found · pointer only
Customizing the Inductive Biases of Softmax Attention using Structured Matrices added by Syntology 2025-09 (from id) YilunKuang/structured-attention/train_ICL.py 6d19d7bf19c36fb9 unverified Apache-2.0 (permissive)
arXiv:2507.07101 2025-07 (from id) martin-marek/batch-size/finetuning/finetune.py 063239541bbfbe70 unverified MIT (permissive)
Monomial Matrix Group Equivariant Neural Functional Networks 18 Sep 2024 mathematicalai-nus/monomial-nfn/experiments/classify_siren.py baf32f15bff306f8 ran · our draft was wrong MIT (permissive)
arXiv:2409.02606 2024-09 (from id) princetonlips/neural_fdm/src/neural_fdm/training.py c42ff70c20028648 unverified no licence file found · pointer only
Enhancing Size Generalization in Graph Neural Networks through Disentangled Representation Learning 7 Jun 2024 graphminddartmouth/disgen/src/train_util.py 93792408ad287326 ran no licence file found · pointer only
Generative Diffusion-based Downscaling for Climate 27 Apr 2024 robbiewatt1/climatediffuse/src/TrainUnet.py 24c744794804a6b0 ran no licence file found · pointer only
Policy-Guided Diffusion 9 Apr 2024 emptyjackson/policy-guided-diffusion/diffusion/edm.py 9b56bf0de382cda7 unverified MIT (permissive)
Cell Graph Transformer for Nuclei Classification 20 Feb 2024 lhaof/CGT/models/CGT/run_desc.py 2f4c495b7d47dc55 unverified no licence file found · pointer only
A Critical Evaluation of AI Feedback for Aligning Large Language Models 19 Feb 2024 architsharma97/dpo-rlaif/reward_trainer.py 12be818ac399701d ran Apache-2.0 (permissive)
Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks 6 Feb 2024 krafton-ai/mambaformer-icl/src/train_parallel.py 47f61861b53edf4d ran Apache-2.0 (permissive)
Attention Meets Post-hoc Interpretability: A Mathematical Perspective 5 Feb 2024 gianluigilopardo/attention_meets_xai/multi_head_trainer.py 63b9f52bfaf4e99d ran · our draft was wrong no licence file found · pointer only
Rethinking materials simulations: Blending direct numerical simulations with neural operators 8 Dec 2023 vivek-brown/UNet-with-temporal-conditioning/src/code/train_unet.py 196ce81dc470cea6 unverified no licence file found · pointer only
Recurrent Distance Filtering for Graph Representation Learning 3 Dec 2023 skeletondyh/GRED/train_peptides_func.py 9bc42f02f987a9cc unverified no licence file found · pointer only
Recurrent Distance Filtering for Graph Representation Learning 3 Dec 2023 skeletondyh/GRED/train_peptides_struct.py 551c7a7eef38710d unverified no licence file found · pointer only
Recurrent Distance Filtering for Graph Representation Learning 3 Dec 2023 skeletondyh/GRED/train_pixel.py 5ab5f97bf4fe2a26 unverified no licence file found · pointer only
Recurrent Distance Filtering for Graph Representation Learning 3 Dec 2023 skeletondyh/GRED/train_sbm.py 2f7255aaf56805b4 unverified no licence file found · pointer only
A point cloud approach to generative modeling for galaxy surveys at the field level 28 Nov 2023 smsharma/point-cloud-galaxy-diffusion/models/train_utils.py 23d317520a5f2b18 unverified MIT (permissive)
Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression 26 Oct 2023 DeqingFu/transformers-icl-second-order/src/train_linear.py dcdff2706acbf855 ran no licence file found · pointer only
Locally Differentially Private Document Generation Using Zero Shot Prompting 24 Oct 2023 saitejautpala/dp_prompt/attacks/embedding_attacker_architecture.py 480709d96ec54bf8 ran MIT (permissive)
Locally Differentially Private Document Generation Using Zero Shot Prompting 24 Oct 2023 saitejautpala/dp_prompt/mechanisms/sentencelevel/deep_candidate.py 6dd4947c1a74cf75 ran MIT (permissive)
Mirage: Model-Agnostic Graph Distillation for Graph Classification 14 Oct 2023 idea-iitd/mirage/ogbg-molbace/optimization/train_and_test.py 8aba6b7e1a6477c1 ran · honoured contract no licence file found · pointer only
No Privacy Left Outside: On the (In-)Security of TEE-Shielded DNN Partition for On-Device ML 11 Oct 2023 ziqi-zhang/teeslice-artifact/membership-inference/knockoff_train.py 104afcbc0f6f4143 ran no licence file found · pointer only
Mechanism of feature learning in convolutional neural networks 1 Sep 2023 aradha/convrfm/conv_nets/trainer.py 8742a8050792c3dd unverified no licence file found · pointer only
CausalLM is not optimal for in-context learning 14 Aug 2023 google-research/causallm_icl/model_trainer.py db573bba4a35a0c9 unverified Apache-2.0 (permissive)
FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods 15 Jun 2023 ahxt/fair_fairness_benchmark/src/ffb_image_diffdp.py ec995a87fb3aa08f unverified MIT (permissive)
FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods 15 Jun 2023 ahxt/fair_fairness_benchmark/src/ffb_image_diffeodd.py a6a63d55993a1803 unverified MIT (permissive)
FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods 15 Jun 2023 ahxt/fair_fairness_benchmark/src/ffb_image_erm.py fdec6b87d8ff457b unverified MIT (permissive)
FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods 15 Jun 2023 ahxt/fair_fairness_benchmark/src/ffb_tabular_adv_gr.py 4313a3b250fe0838 unverified MIT (permissive)
RETA-LLM: A Retrieval-Augmented Large Language Model Toolkit 8 Jun 2023 ruc-gsai/yulan-ir/WebBrain/generator/run_model_train.py 3b820c3547a5622d unverified MIT (permissive)
Recasting Self-Attention with Holographic Reduced Representations 31 May 2023 FutureComputing4AI/Hrrformer/malware/hrrformer_mgpu.py 73cf404c6a2e8e98 unverified Apache-2.0 (permissive)
Reconstructive Neuron Pruning for Backdoor Defense 24 May 2023 bboylyg/rnp/train_backdoor.py 1766a1f110a8bd59 unverified no licence file found · pointer only
Video Prediction Models as Rewards for Reinforcement Learning 23 May 2023 nyuolab/VIPER-torch/scripts/train_vqgan.py 1afd8c944e46c401 ran · our draft was wrong MIT (permissive)
Video Prediction Models as Rewards for Reinforcement Learning 23 May 2023 nyuolab/VIPER-torch/scripts/train_videogpt.py ecce8632ff15a248 unverified MIT (permissive)
Identifiability Results for Multimodal Contrastive Learning 16 Mar 2023 imantdaunhawer/multimodal-contrastive-learning/main_imgtxt.py 600f5a2225c1b02c ran · honoured contract licence not identified · pointer only
Identifiability Results for Multimodal Contrastive Learning 16 Mar 2023 imantdaunhawer/multimodal-contrastive-learning/main_mlp.py 5b044fb11a2bde22 unverified licence not identified · pointer only
Shortcut Detection with Variational Autoencoders 8 Feb 2023 fraunhofer-aisec/shortcut-detection-vae/scripts/train_vae.py c9b5a4e0c35dc967 unverified Apache-2.0 (permissive)
Toward Learning Robust and Invariant Representations with Alignment Regularization and Data Augmentation 4 Jun 2022 jyanln/alignreg/src/alignreg/tf_training.py b4c6a8550e4357bf unverified MIT (permissive)
PIE: a Parameter and Inference Efficient Solution for Large Scale Knowledge Graph Embedding Reasoning 29 Apr 2022 alipay/parameter_inference_efficient_pie/entity_typing/src/model.py de25933894de2114 unverified Apache-2.0 (permissive)
Instant Neural Graphics Primitives with a Multiresolution Hash Encoding 16 Jan 2022 blurgyy/jaxngp/app/imagefit.py b2c79c7c992d6668 unverified Apache-2.0 (permissive)
MAGMA -- Multimodal Augmentation of Generative Models through Adapter-based Finetuning 9 Dec 2021 Aleph-Alpha/magma/magma/train_loop.py 5c7e7dc9d5bdc305 unverified MIT (permissive)
Pulling Up by the Causal Bootstraps: Causal Data Augmentation for Pre-training Debiasing 27 Aug 2021 MLforHealth/CausalDA/src/training.py c146534ad54e89c3 unverified MIT (permissive)
AGAIN-VC: A One-shot Voice Conversion using Activation Guidance and Adaptive Instance Normalization 2020-11 (from id) KimythAnly/AGAIN-VC/model/again.py 37bab301d0d6a8f0 unverified MIT (permissive)
Automated Synthetic-to-Real Generalization 14 Jul 2020 NVlabs/ASG/l2o_train.py e0b335b3890feb6d ran · fixture could not drive it licence not identified · pointer only
Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels 18 Apr 2018 yeachan-kr/pytorch-coteaching/runs/train_coteaching.py 5107b016c3d369b0 ran · fixture could not drive it no licence file found · pointer only
Deep Learning using Rectified Linear Units (ReLU) 22 Mar 2018 AFAgarap/relu-classifier/models/neural_net.py b43efda1e2fdb72e unverified Apache-2.0 (permissive)
The Reversible Residual Network: Backpropagation Without Storing Activations 14 Jul 2017 renmengye/revnet-public/run_cifar_train.py afcb9f0b0da3af03 ran · honoured contract MIT (permissive)
The Reversible Residual Network: Backpropagation Without Storing Activations 14 Jul 2017 renmengye/revnet-public/run_imagenet_train.py c5abb3c9365dc91c ran · honoured contract MIT (permissive)
Deep Residual Learning for Image Recognition 10 Dec 2015 ajaystar8/PDRUNet-PyTorch/engine.py 9bd37700bbb48c38 unverified MIT (permissive)
SSD: Single Shot MultiBox Detector 8 Dec 2015 aniketmaurya/ssd-tf2-tfds/train_tfds.py aea7d0ddcbf2b4b3 unverified MIT (permissive)
Unsupervised Domain Adaptation by Backpropagation 26 Sep 2014 chenkang121/DANN/DANN_minit_to_mnist_m.py 810938a759273697 ran · fixture could not drive it fingerprinted no licence file found · pointer only
arXiv:aaai_21180 yuanmu97/MLink/mlink/seq_to_seq.py 505ddfc37d48c30b unverified MIT (permissive)
arXiv:aaai_21180 yuanmu97/MLink/mlink/vec_to_seq.py fed5424f4f1af917 unverified MIT (permissive)
arXiv:2023.findings-emnlp.566 SaitejaUtpala/dp_prompt/attacks/embedding_attacker_architecture.py 480709d96ec54bf8 ran 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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