Paper Citation Record · LEDGER

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis

As of 15 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:2412.10146.

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

pith.paper-citation-record.v1
2412.10146 v2

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T16:19:56.086727Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+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

36 of 36 outbound references displayed

verified exact1
verified fuzzy15
unresolved20
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 83742e7f-2d4d-4196-86f5-136e31b8c3e7 · outbound

This paper cites Exploring Generalization in Deep Learning.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Exploring Generalization in Deep Learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T16:19:55.937950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51ebb433-3fe5-4b46-90cf-4a3039eedc70 · outbound

This paper cites Sensitivity and Generalization in Neural Networks: an Empirical Study.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Sensitivity and Generalization in Neural Networks: an Empirical Study

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T16:19:55.942889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bbc02d7-4740-42a5-a2de-69553380fd9d · outbound

This paper cites Visualizing the Loss Landscape of Neural Nets.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Visualizing the Loss Landscape of Neural Nets

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T16:19:55.948001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bbca19e-9110-41d0-a0f0-becfe12dc74e · outbound

This paper cites An empirical analysis of the optimization of deep network loss surfaces.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis An empirical analysis of the optimization of deep network loss surfaces

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T16:19:55.952649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9eb349a8-8f7b-485b-afe8-e56212763229 · outbound

This paper cites Pytorch,.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Pytorch,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:19:56.599612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5146d550-2b20-4bb0-800a-6ee4d78c8846 · outbound

This paper cites Loss landscape analysis,.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Loss landscape analysis,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:19:56.588232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e9188f9d-3118-4637-a803-7e5b388829a2 · outbound

This paper cites loss-landscapes,.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis loss-landscapes,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:19:56.576379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 110033e6-6576-4fe6-a58f-39e869403994 · outbound

This paper cites The Hessian perspective into the Nature of Convolutional Neural Networks.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis The Hessian perspective into the Nature of Convolutional Neural Networks

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T16:19:55.969697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9ad4249-cee4-461c-8963-bc1a82d41261 · outbound

This paper cites Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-08-11T16:19:56.352472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation fc3a77a4-eb34-4071-9953-9979cb017f0b · outbound

This paper cites A review of supervised machine learning al- gorithms,.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis A review of supervised machine learning al- gorithms,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:19:56.564471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a15d0791-ff51-4d48-aa7f-a59bf2f3e545 · outbound

This paper cites Deep residual learning for image recognition,.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Deep residual learning for image recognition,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:19:56.551335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation aea02c2a-6744-4d47-927a-c1779d80c6ba · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T16:19:55.992351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c15e311-cf84-4a2f-be8f-258db6a263b4 · outbound

This paper cites Emergent properties of the local geometry of neural loss landscapes.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Emergent properties of the local geometry of neural loss landscapes

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T16:19:55.997409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d776d5e-8d82-4b67-b94b-824068bee6c5 · outbound

This paper cites Visualizing high-dimensional loss landscapes with hessian directions,.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Visualizing high-dimensional loss landscapes with hessian directions,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T16:19:56.001310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 122026f6-26e0-4161-b0e2-6fdc993eb7b3 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Adam: A Method for Stochastic Optimization

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T16:19:56.005857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1598f21b-804d-4ca0-a537-c95cd5365021 · outbound

This paper cites Visualizing the loss landscape of neural nets,.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Visualizing the loss landscape of neural nets,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:19:56.538033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e2f33b71-b3d9-4ddb-af66-bcef5f9a450d · outbound

This paper cites Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T16:19:56.013765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93431833-6aa2-4528-8d9c-8c7fd6bbd89f · outbound

This paper cites Batchnorm2d in pytorch,.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Batchnorm2d in pytorch,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:19:56.525023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c51356d9-b221-4c0a-8d72-44aae1527635 · outbound

This paper cites Models and pre-trained weights in pytorch,.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Models and pre-trained weights in pytorch,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:19:56.511517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9bb1ba24-f67f-4114-98fd-0dc5675d27dc · outbound

This paper cites Imagenet classification with deep con- volutional neural networks,.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Imagenet classification with deep con- volutional neural networks,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:19:56.498446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 46bb2bc8-aa5e-4c88-bb6b-91162a97e039 · outbound

This paper cites SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T16:19:56.028849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1917853-9c12-41cf-8d3d-c51104aa0289 · outbound

This paper cites Gradient-based learning applied to document recognition,.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Gradient-based learning applied to document recognition,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:19:56.486684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d03e78de-1899-4aef-811b-4383b50b6c7b · outbound

This paper cites Randomized algorithms for estimating the trace of an implicit symmetric positive semi-definite matrix,.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Randomized algorithms for estimating the trace of an implicit symmetric positive semi-definite matrix,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T16:19:56.036555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b37a9508-5f56-4504-9eb3-580817ba3168 · outbound

This paper cites Randomized algorithms for matrices and data,.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Randomized algorithms for matrices and data,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T16:19:56.041119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 639f5719-b212-4897-bb96-7e4dd9a14d87 · outbound

This paper cites Fast estimation of tr(f(a)) via stochastic lanczos quadrature,.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Fast estimation of tr(f(a)) via stochastic lanczos quadrature,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T16:19:56.044946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32e694da-60f2-456a-9fd2-d68dd1572d45 · outbound

This paper cites PyHessian: Neural Networks Through the Lens of the Hessian.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis PyHessian: Neural Networks Through the Lens of the Hessian

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T16:19:56.048868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d1cf250-ca9b-466d-b95c-caf0c7eee019 · outbound

This paper cites Pyhessian,.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Pyhessian,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:19:56.474420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7f40479d-a072-4286-9a4f-8b5311673f1d · outbound

This paper cites Why Transformers Need Adam: A Hessian Perspective.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Why Transformers Need Adam: A Hessian Perspective

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T16:19:56.056413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8900c900-4872-41c1-8146-ff8e2f347fe9 · outbound

This paper cites Pytorch image models,.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Pytorch image models,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:19:56.462537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c7df48ae-e248-437c-a28e-1419025b653d · outbound

This paper cites How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T16:19:56.065350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f70da2f-60ab-4b74-802a-9e2cb1d36f93 · outbound

This paper cites Imagenet: A large-scale hierarchical image database,.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Imagenet: A large-scale hierarchical image database,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T16:19:56.069783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15e84ba3-f77f-47a0-a858-9369f6f96ce8 · outbound

This paper cites Mnist handwritten digit database,.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Mnist handwritten digit database,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:19:56.442379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5e34e04b-8459-43d8-9f81-e4e0640e697b · outbound

This paper cites The street view house numbers (svhn) dataset,.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis The street view house numbers (svhn) dataset,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:19:56.430160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5ed3c535-4f9d-4666-9f32-b80c0b876ce1 · outbound

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

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Learning multiple layers of features from tiny images,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:19:56.416566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6212b29a-9af7-4f0d-8e26-0ac0fa993359 · outbound

This paper cites CINIC-10 is not ImageNet or CIFAR-10.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis CINIC-10 is not ImageNet or CIFAR-10

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T16:19:56.086727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e33c2b51-c691-42d8-a33a-43339a942753 · outbound

This paper cites Deep Residual Learning for Image Recognition.

Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis Deep Residual Learning for Image Recognition

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-11T16:19:55.988073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.