Paper Citation Record · LEDGER

Insights from Gradient Dynamics: Gradient Autoscaled Normalization

As of 7 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 0 inbound Pith citation observations for arXiv:2509.03677.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2509.03677 v2

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T10:51:39.015136Z

measured 32 of 32 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

32 of 32 outbound references displayed

verified exact0
verified fuzzy17
unresolved13
parse uncertain1
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2e8a9f65-878d-44ad-9fdb-c2c37f4b8f47 · outbound

This paper cites Layer Normalization.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Layer Normalization

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T10:51:38.901558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1407376e-2cff-4088-9ec5-946660a7db70 · outbound

This paper cites Large-scale machine learning with stochastic gradient descent.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Large-scale machine learning with stochastic gradient descent

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T10:51:38.906194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cca347b-b28b-4c88-b834-82b04607df9a · outbound

This paper cites The tradeoffs of large scale learning.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization The tradeoffs of large scale learning

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:51:39.384027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5eb220e4-b18d-4c94-87c2-831deb57219a · outbound

This paper cites Curtis, and Jorge Nocedal.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Curtis, and Jorge Nocedal

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T10:51:38.913948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 508674f8-9780-4928-8f92-23f6ddc6c4fd · outbound

This paper cites Entropy-sgd: biasing gradient descent into wide valleys.Journal of Statistical Mechanics: Theory and Experiment, 2019 (12):124018, 2019.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Entropy-sgd: biasing gradient descent into wide valleys.Journal of Statistical Mechanics: Theory and Experiment, 2019 (12):124018, 2019

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T10:51:38.917822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50dd9eb9-c3a2-4dea-bfc4-8127695d03bd · outbound

This paper cites Gradnorm: Gra- dient normalization for adaptive loss balancing in deep multitask networks.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Gradnorm: Gra- dient normalization for adaptive loss balancing in deep multitask networks

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:51:39.372116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation daf8b0b3-9c90-4ece-9d20-2d14d4ef2401 · outbound

This paper cites A Study of Gradient Variance in Deep Learning.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization A Study of Gradient Variance in Deep Learning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T10:51:38.925694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39c137a0-1bb3-4d63-a904-e524da2847fc · outbound

This paper cites Understanding the difficulty of training deep feedfor- ward neural networks.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Understanding the difficulty of training deep feedfor- ward neural networks

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:51:39.358803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2b9b9e64-56f9-45ad-82a7-5bf40561b76f · outbound

This paper cites Take a shortcut back: Mitigating the gradient vanishing for training spiking neural networks.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Take a shortcut back: Mitigating the gradient vanishing for training spiking neural networks

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:51:39.346789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0ded4a05-1d21-438d-876b-2a6eb660e9db · outbound

This paper cites Stable architectures for deep neural networks.Inverse Prob- lems, 34(1):014004, 2018.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Stable architectures for deep neural networks.Inverse Prob- lems, 34(1):014004, 2018

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T10:51:38.936717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b8fee62-d60a-4c24-982a-08ffbde2ad7a · outbound

This paper cites Deep residual learning for im- age recognition.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Deep residual learning for im- age recognition

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T10:51:38.940301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 277ef9dd-4430-4ac2-84ce-f950cd0255d2 · outbound

This paper cites Densely con- nected convolutional networks.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Densely con- nected convolutional networks

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:51:39.326434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8680cf61-593d-422f-a7ab-24d101621042 · outbound

This paper cites Batch normalization: accelerating deep network training by reducing internal covariate shift.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Batch normalization: accelerating deep network training by reducing internal covariate shift

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:51:39.314758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 14022fec-0fee-4ade-b581-4aeadc1fc45d · outbound

This paper cites Adam: A method for stochastic optimization.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Adam: A method for stochastic optimization

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:51:39.302393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 136da08e-f23b-47f1-9cbe-f0acc8558cf5 · outbound

This paper cites Learning multiple layers of features from tiny images.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Learning multiple layers of features from tiny images

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T10:51:38.955468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b18b826-dd66-4c09-9ecc-2c100c3d7a92 · outbound

This paper cites Decoupled weight decay regularization.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Decoupled weight decay regularization

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T10:51:38.958937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30333d8f-2e0f-45f9-a5e4-418c21ce1513 · outbound

This paper cites an unresolved cited work.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-05T10:51:39.273980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d105d30b-bd0c-4d82-b4f0-7a71b96498ea · outbound

This paper cites ViT-CIFAR: PyTorch implementation for Vision Transformer on CIFAR datasets.https://github.com/omihub777/ViT-CIFAR, 2021.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization ViT-CIFAR: PyTorch implementation for Vision Transformer on CIFAR datasets.https://github.com/omihub777/ViT-CIFAR, 2021

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T10:51:38.965544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cab82ace-f151-41f4-8b72-45abeeb5da04 · outbound

This paper cites On the difficulty of training recur- rent neural networks.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization On the difficulty of training recur- rent neural networks

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:51:39.253197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 44fd442c-17b7-4fc6-a684-1050325c3feb · outbound

This paper cites How does batch normalization help optimization? InProceedings of the 32nd International Conference on Neural Information Processing Systems, page 2488–2498, 2018.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization How does batch normalization help optimization? InProceedings of the 32nd International Conference on Neural Information Processing Systems, page 2488–2498, 2018

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:51:39.240820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5e225c31-4624-4cfe-a521-1c1bde9e2861 · outbound

This paper cites Very deep convolutional networks for large-scale image recognition.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Very deep convolutional networks for large-scale image recognition

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T10:51:38.976502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eeccafcb-e5fc-4df6-aa39-dfcdf2de9fec · outbound

This paper cites Lecture 6.5 - RMSProp: Divide the gradient by a running average of its recent magnitude.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Lecture 6.5 - RMSProp: Divide the gradient by a running average of its recent magnitude

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:51:39.220382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 41d7e801-aebb-46f8-bee6-af6aa73c5519 · outbound

This paper cites Aggregated residual transformations for deep neural networks.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Aggregated residual transformations for deep neural networks

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:51:39.199732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 043e8490-a3aa-401d-8c54-cea17189a075 · outbound

This paper cites Gradient centraliza- tion: A new optimization technique for deep neural networks.Proceedings of the Eu- ropean Conference on Computer Vision (ECCV), pages 635–651, 2020.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Gradient centraliza- tion: A new optimization technique for deep neural networks.Proceedings of the Eu- ropean Conference on Computer Vision (ECCV), pages 635–651, 2020

Reference 24

Resolution: malformed identifier; raw_fallback, observed 2026-08-05T10:51:39.187647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6e4fcd63-838c-4864-b798-6e7bacc0f7c0 · outbound

This paper cites Znorm: Z-score gradient normalization accelerating skip-connected network training without architectural modification.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Znorm: Z-score gradient normalization accelerating skip-connected network training without architectural modification

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:51:39.175325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1f6f9682-e8f3-43ab-b0f5-5f048a893f88 · outbound

This paper cites Cutmix: Regularization strategy to train strong classifiers with localizable features.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Cutmix: Regularization strategy to train strong classifiers with localizable features

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:51:39.162901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 03ba7a4c-fef0-45a3-bab9-bfdc4d3a0626 · outbound

This paper cites Wide residual networks.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Wide residual networks

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:51:39.150168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b3896c69-dee6-45ef-87f8-c291c0611120 · outbound

This paper cites When will gradient regularization be harmful? In Forty-first International Conference on Machine Learning.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization When will gradient regularization be harmful? In Forty-first International Conference on Machine Learning

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:51:39.138025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a4417bfb-ccbe-4eef-b9b1-300ea2cf1166 · outbound

This paper cites Penalizing gradient norm for efficiently improving generalization in deep learning.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Penalizing gradient norm for efficiently improving generalization in deep learning

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:51:39.125921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4a462906-6865-4436-bb8f-37482170f4b7 · outbound

This paper cites Recurrent neural networks: vanishing and exploding gradients are not the end of the story.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Recurrent neural networks: vanishing and exploding gradients are not the end of the story

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:51:39.113707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cba70997-9462-43ef-88ca-6d9c72dc12f8 · outbound

This paper cites an unresolved cited work.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-05T10:51:39.100030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation dd4adf9b-d6e3-4efe-8629-5e515d7ffd98 · outbound

This paper cites an unresolved cited work.

Insights from Gradient Dynamics: Gradient Autoscaled Normalization Unresolved cited work

Reference 2012

Resolution: parse uncertain; no resolver link, observed 2026-08-05T10:51:38.983623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.