Paper Citation Record · LEDGER

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature

As of 10 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 1 inbound Pith citation observation for arXiv:2602.05600.

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

pith.paper-citation-record.v1
2602.05600 v2

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T04:17:45.882008Z

measured 29 of 29 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-29T18:15:03.796618Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-06-29T18:23:51.076527Z

Reference resolution

28 of 28 outbound references displayed

verified exact0
verified fuzzy0
unresolved26
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c418e14f-dc0c-4b16-b73e-9312c7de28f4 · outbound

This paper cites suppression experiment.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature suppression experiment

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:44.590842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61cc9a48-047c-438f-bbcc-bb509b235db3 · outbound

This paper cites an unresolved cited work.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:44.909876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3f89f5a-8831-4128-a8c4-c580b34e1e14 · outbound

This paper cites To ensure rank-1 dominance, we suppress their tail modes (m >1) by a factor ofϵ tail = 10−5.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature To ensure rank-1 dominance, we suppress their tail modes (m >1) by a factor ofϵ tail = 10−5

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:45.035029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2912cf9-bdfd-46aa-89f8-1cf4d183ca16 · outbound

This paper cites heavy-tailed.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature heavy-tailed

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:45.100766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a98d3e27-a1f2-41eb-8e0b-ad5bcfd134fb · outbound

This paper cites Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes

Reference 5

Resolution: malformed identifier; no resolver link, observed 2026-08-03T04:17:44.355637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3d00c1f-9d64-44f0-92af-435f2b9d9849 · outbound

This paper cites Noise-Driven Exploration and Transient Freezing Select Flat Minima in Stochastic Gradient Descent.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature Noise-Driven Exploration and Transient Freezing Select Flat Minima in Stochastic Gradient Descent

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:44.476232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c8bc5cd-48f9-42e9-902e-01f18ef25e3b · outbound

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

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature PyHessian: Neural Networks Through the Lens of the Hessian

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:44.481481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4aac30e6-9676-47ca-9430-b6e4060e67a9 · outbound

This paper cites an unresolved cited work.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:44.743407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f39f2708-df7d-40a3-82b5-9d45862bfdb0 · outbound

This paper cites an unresolved cited work.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:45.266710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ab5cde6-a310-4cb0-95e8-4209289f43f6 · outbound

This paper cites SinceQ ik andQ jk are independent (fori̸=j),E[X k] = 0.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature SinceQ ik andQ jk are independent (fori̸=j),E[X k] = 0

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:45.343660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32880826-3b49-422c-bfaa-6ae0dcbc560f · outbound

This paper cites random noise floor.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature random noise floor

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:45.419856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0942a091-09e7-4493-a32a-bde09d0518f3 · outbound

This paper cites an unresolved cited work.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:45.566786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a82d50a-ff03-4445-9112-a840fe8f3586 · outbound

This paper cites an unresolved cited work.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:45.664022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a474821-63e2-4906-b13f-83893585725b · outbound

This paper cites an unresolved cited work.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:45.672041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6924365c-4e02-467b-b464-fe78aafddfed · outbound

This paper cites Numerical Evaluation We apply this framework to our experimental observations (CNN on CIFAR-10) with the following parameters: • Matrix Dimension:D≈2560.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature Numerical Evaluation We apply this framework to our experimental observations (CNN on CIFAR-10) with the following parameters: • Matrix Dimension:D≈2560

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:45.736636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d7ae028-48f7-4e8b-9c8c-7f022da65db1 · outbound

This paper cites As the model approaches a global minimum (or a high-quality local minimum), the per-sample gradients for correctly classified examples tend to vanish (i.e., ∥∇ℓ∥ →0).

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature As the model approaches a global minimum (or a high-quality local minimum), the per-sample gradients for correctly classified examples tend to vanish (i.e., ∥∇ℓ∥ →0)

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:45.777568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 658df946-f5cf-41bc-8d12-f9878884d5c8 · outbound

This paper cites an unresolved cited work.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:45.836922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5afd9c0-811f-458e-9033-0d6ead1d644d · outbound

This paper cites an unresolved cited work.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:45.847429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98208c24-c4e4-4faf-a74a-40c1d25a0898 · outbound

This paper cites 23 On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature 23 On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:45.858854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac8404c9-7cbf-4992-9722-a920cf6ad065 · outbound

This paper cites This tiny fluctuations contribute to the bulk eigenvalues of Global Hessian which is the source of heavy-tailed spectrum.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature This tiny fluctuations contribute to the bulk eigenvalues of Global Hessian which is the source of heavy-tailed spectrum

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:45.864908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68a641e2-ac0d-42b4-9255-7fc29326a302 · outbound

This paper cites an unresolved cited work.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:45.869286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4443deab-0104-4f51-aba2-0856ee98e9c5 · outbound

This paper cites an unresolved cited work.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:45.873590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b23bbd0-0d32-4a94-b9b0-6e980707b4f0 · outbound

This paper cites an unresolved cited work.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:45.877546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1435520d-957a-49f0-ae2c-dbac0dfb108a · outbound

This paper cites Vanishing Gradients.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature Vanishing Gradients

Reference 28

Resolution: malformed identifier; no resolver link, observed 2026-08-03T04:17:45.882008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98da0dfc-0ae5-4f21-a704-527efb892a7c · outbound

This paper cites On the diffusion approximation of nonconvex stochastic gradient descent.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature On the diffusion approximation of nonconvex stochastic gradient descent

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:43.552962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a276e497-6f62-4fc2-ab10-ae02623b0652 · outbound

This paper cites On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs).

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:43.984749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc628e36-9230-418d-bbee-f639c8967586 · outbound

This paper cites Sun, R., Li, D., Liang, S., Ding, T., and Srikant, R.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature Sun, R., Li, D., Liang, S., Ding, T., and Srikant, R

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:44.194756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05d014da-8712-44f8-8ba1-17afbc31da6a · outbound

This paper cites Hessian based analysis of SGD for Deep Nets: Dynamics and Generalization.

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature Hessian based analysis of SGD for Deep Nets: Dynamics and Generalization

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-03T04:17:43.712084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 1918ce67-fa02-4a2f-b3dd-3d4d53d2d41c · inbound

Worker Disagreement Reveals Sharp Directions in Local SGD cites this paper.

Worker Disagreement Reveals Sharp Directions in Local SGD On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-06-29T18:23:51.077809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.