Paper Citation Record · LEDGER

What Can Grokking Teach Us About Learning Under Nonstationarity?

As of 21 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 2 inbound Pith citation observations for arXiv:2507.20057.

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

pith.paper-citation-record.v1
2507.20057 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T17:59:10.428787Z

measured 32 of 32 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T10:34:43.639777Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-21T07:34:02.917248Z

Reference resolution

30 of 30 outbound references displayed

verified exact2
verified fuzzy9
unresolved19
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a33e064c-2a2f-46d9-89b2-1aafb51075dd · outbound

This paper cites LayerNorm layers, when incorporated, are applied to the attention inputs and outputs, and the MLP outputs.

What Can Grokking Teach Us About Learning Under Nonstationarity? LayerNorm layers, when incorporated, are applied to the attention inputs and outputs, and the MLP outputs

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:59:10.867629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 266f8e5a-1112-465f-8fed-f6f71db8c494 · outbound

This paper cites an unresolved cited work.

What Can Grokking Teach Us About Learning Under Nonstationarity? Unresolved cited work

Reference 2

Resolution: verified exact; raw_fallback, observed 2026-08-15T17:59:10.581087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0ddf42b4-9fac-4894-b765-744d56dec34b · outbound

This paper cites Unveiling grokking: Analyzing feature learning dynamics during training.

What Can Grokking Teach Us About Learning Under Nonstationarity? Unveiling grokking: Analyzing feature learning dynamics during training

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:59:10.997182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ea857991-2d3c-4e33-a3b1-3b7bf41b1cc6 · outbound

This paper cites Unifying Grokking and Double Descent.

What Can Grokking Teach Us About Learning Under Nonstationarity? Unifying Grokking and Double Descent

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T17:59:10.311153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a560902e-5e70-47a7-ac13-2172d4976cb3 · outbound

This paper cites Continual Backprop: Stochastic Gradient Descent with Persistent Randomness.

What Can Grokking Teach Us About Learning Under Nonstationarity? Continual Backprop: Stochastic Gradient Descent with Persistent Randomness

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T17:59:10.317139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8f42cc5-76a6-41ed-ba1f-4fec4504961e · outbound

This paper cites Learning continually by spectral regularization.

What Can Grokking Teach Us About Learning Under Nonstationarity? Learning continually by spectral regularization

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:59:10.968839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8c0cf492-03d2-4990-b1a7-3629ed7108d7 · outbound

This paper cites An exponential learning rate schedule for deep learning.

What Can Grokking Teach Us About Learning Under Nonstationarity? An exponential learning rate schedule for deep learning

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:59:10.956588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 16dde9bc-2408-4715-b719-5b47ac63b3c6 · outbound

This paper cites Disentangling the Causes of Plasticity Loss in Neural Networks.

What Can Grokking Teach Us About Learning Under Nonstationarity? Disentangling the Causes of Plasticity Loss in Neural Networks

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T17:59:10.354242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b146f3d7-a4dc-443f-91cd-fbf5a2c14fd1 · outbound

This paper cites Progress measures for grokking via mechanistic interpretability.

What Can Grokking Teach Us About Learning Under Nonstationarity? Progress measures for grokking via mechanistic interpretability

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T17:59:10.359160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8c28d6f-f892-471e-aba1-994cd6ea9756 · outbound

This paper cites Cyclical learning rates for training neural networks.

What Can Grokking Teach Us About Learning Under Nonstationarity? Cyclical learning rates for training neural networks

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:59:10.924145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6296aa7e-7ab0-4bf5-948a-3493b1eb89bd · outbound

This paper cites On the infinite width limit of neural networks with a standard parameterization.

What Can Grokking Teach Us About Learning Under Nonstationarity? On the infinite width limit of neural networks with a standard parameterization

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T17:59:10.379132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1ef3a8a-7be3-4aef-8eb8-f0d4e38c79ec · outbound

This paper cites Susskind.

What Can Grokking Teach Us About Learning Under Nonstationarity? Susskind

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:59:10.910375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3fffa72d-907f-408b-b12a-e2e11041e324 · outbound

This paper cites Deep Reinforcement Learning and the Deadly Triad.

What Can Grokking Teach Us About Learning Under Nonstationarity? Deep Reinforcement Learning and the Deadly Triad

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T17:59:10.388260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02155c98-8f02-46db-a674-054dc9e7c979 · outbound

This paper cites Explaining grokking through circuit efficiency.

What Can Grokking Teach Us About Learning Under Nonstationarity? Explaining grokking through circuit efficiency

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T17:59:10.393060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08ce421a-91b0-482a-bcce-9c909a8c2ec1 · outbound

This paper cites Small-scale proxies for large-scale Transformer training instabilities.

What Can Grokking Teach Us About Learning Under Nonstationarity? Small-scale proxies for large-scale Transformer training instabilities

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T17:59:10.398905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 906f71b4-4a82-43e3-a8d2-dd814fdffe8e · outbound

This paper cites Wide feedforward or recurrent neural networks of any architecture are gaussian processes.

What Can Grokking Teach Us About Learning Under Nonstationarity? Wide feedforward or recurrent neural networks of any architecture are gaussian processes

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:59:10.897574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1047ff90-9f4a-4071-b21a-0992968c40b8 · outbound

This paper cites an unresolved cited work.

What Can Grokking Teach Us About Learning Under Nonstationarity? Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-15T17:59:10.881650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b8b0d6d6-9114-441b-94a5-d3018f54b6be · outbound

This paper cites an unresolved cited work.

What Can Grokking Teach Us About Learning Under Nonstationarity? Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-15T17:59:10.852763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 13248f8d-f4d2-443d-9996-0fa5537002ea · outbound

This paper cites A study on the plasticity of neural networks.

What Can Grokking Teach Us About Learning Under Nonstationarity? A study on the plasticity of neural networks

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-15T17:59:10.297015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22351bf8-d39f-499c-9a2d-8a3492c02aef · outbound

This paper cites Early stopping in deep networks: Double descent and how to eliminate it.

What Can Grokking Teach Us About Learning Under Nonstationarity? Early stopping in deep networks: Double descent and how to eliminate it

Reference 2015

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:59:10.982639Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f10a81b3-d873-4188-85fc-b4b62b004891 · outbound

This paper cites Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets.

What Can Grokking Teach Us About Learning Under Nonstationarity? Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-15T17:59:10.364239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4ed09f4-f5bc-4d29-b807-e3b34f9ec5b0 · outbound

This paper cites Second-order regression models exhibit progressive sharpening to the edge of stability.

What Can Grokking Teach Us About Learning Under Nonstationarity? Second-order regression models exhibit progressive sharpening to the edge of stability

Reference 2017

Resolution: verified exact; local_arxiv, observed 2026-08-15T17:59:10.821562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 838c3a9d-5e08-49ea-95ad-313b3546d625 · outbound

This paper cites Maintaining Plasticity in Continual Learning via Regenerative Regularization.

What Can Grokking Teach Us About Learning Under Nonstationarity? Maintaining Plasticity in Continual Learning via Regenerative Regularization

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-15T17:59:10.328060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a37ad0a8-7f91-4b32-8004-f57355b9e24e · outbound

This paper cites Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer.

What Can Grokking Teach Us About Learning Under Nonstationarity? Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-15T17:59:10.409472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb2fe723-d15c-4539-8965-aa09ce56a16a · outbound

This paper cites Implicit Gradient Regularization.

What Can Grokking Teach Us About Learning Under Nonstationarity? Implicit Gradient Regularization

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-15T17:59:10.285588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b8d9fe0-d696-4300-b765-3bd6a747fbb2 · outbound

This paper cites Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability.

What Can Grokking Teach Us About Learning Under Nonstationarity? Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-15T17:59:10.303191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18ada590-9283-4b06-a50a-f6bf1017c784 · outbound

This paper cites On the interplay between stepsize tuning and progressive sharpening.

What Can Grokking Teach Us About Learning Under Nonstationarity? On the interplay between stepsize tuning and progressive sharpening

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:59:10.937999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5ed21da5-a930-4c5a-a6a4-f090cd75db1c · outbound

This paper cites Critical Learning Periods in Deep Neural Networks.

What Can Grokking Teach Us About Learning Under Nonstationarity? Critical Learning Periods in Deep Neural Networks

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-15T17:59:10.274377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5533ea32-393c-4d80-8b1f-a1ab9b0a3c80 · outbound

This paper cites Directions of Curvature as an Explanation for Loss of Plasticity.

What Can Grokking Teach Us About Learning Under Nonstationarity? Directions of Curvature as an Explanation for Loss of Plasticity

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T17:59:10.333300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb9e2d4a-14b5-43f3-a56b-4156a41cbec7 · outbound

This paper cites The large learning rate phase of deep learning: the catapult mechanism.

What Can Grokking Teach Us About Learning Under Nonstationarity? The large learning rate phase of deep learning: the catapult mechanism

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-15T17:59:10.343791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 15211429-16f3-4e8c-8bec-d330d49ab307 · inbound

Weight Decay Regimes in Grokking Transformers: Cheap Online Diagnostics cites this paper.

Weight Decay Regimes in Grokking Transformers: Cheap Online Diagnostics What Can Grokking Teach Us About Learning Under Nonstationarity?

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-21T07:34:02.918767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4c48ecc3-b73b-48ea-b9a8-4099b40208ce · inbound

The Kinetics of Training: A Driven-Nucleation Rate Law for Emergence, Plasticity Loss, and Circuit Control in Language Models cites this paper.

The Kinetics of Training: A Driven-Nucleation Rate Law for Emergence, Plasticity Loss, and Circuit Control in Language Models What Can Grokking Teach Us About Learning Under Nonstationarity?

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-01T10:34:43.639777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.