Paper Citation Record · LEDGER

New Evidence of the Two-Phase Learning Dynamics of Neural Networks

As of 18 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2505.13900.

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

pith.paper-citation-record.v1
2505.13900 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:13:29.997803Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+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

38 of 38 outbound references displayed

verified exact0
verified fuzzy24
unresolved14
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7de84ed3-6723-4b3e-8b1d-43f7b343714d · outbound

This paper cites Critical Learning Periods in Deep Neural Networks.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Critical Learning Periods in Deep Neural Networks

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T20:13:29.679072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48e33b7d-6855-4f01-83d1-1a0ff7438316 · outbound

This paper cites Ainsworth, Jonathan Hayase, and Siddhartha S.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Ainsworth, Jonathan Hayase, and Siddhartha S

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:31.927424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7e6b8784-264c-4951-988e-0a961ded2d71 · outbound

This paper cites A convergence theory for deep learning via over- parameterization.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks A convergence theory for deep learning via over- parameterization

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:31.846345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b21adc22-f271-4819-9ea7-c3893b9e1465 · outbound

This paper cites On exact computation with an infinitely wide neural net.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks On exact computation with an infinitely wide neural net

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:31.746850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9d3ef832-a61a-43fb-b6b6-0bc56548dd49 · outbound

This paper cites A survey on deep learning applied to medical images: from simple artificial neural networks to generative models.Neural Computing and Applications, 35(3):2291–2323, 2023.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks A survey on deep learning applied to medical images: from simple artificial neural networks to generative models.Neural Computing and Applications, 35(3):2291–2323, 2023

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:31.729169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c42b6945-b3a4-43e1-a93a-46d7d09e3c3a · outbound

This paper cites On lazy training in differentiable programming.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks On lazy training in differentiable programming

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:31.712861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 38b682b7-7f87-4130-9190-42710c9def53 · outbound

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

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T20:13:29.732360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8953a0cf-5c37-4f25-9f2a-5e6ff50212d9 · outbound

This paper cites an unresolved cited work.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:13:31.696308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 34de2252-102f-465d-85bc-96155e2fba25 · outbound

This paper cites Gradient descent finds global minima of deep neural networks.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Gradient descent finds global minima of deep neural networks

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:31.494528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6eb35913-093a-4500-b6ac-63e937934eb5 · outbound

This paper cites Du, Xiyu Zhai, Barnabas Poczos, and Aarti Singh.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Du, Xiyu Zhai, Barnabas Poczos, and Aarti Singh

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T20:13:29.747693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c0e2b99-c62b-46aa-8b2c-b8a018eacb16 · outbound

This paper cites an unresolved cited work.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T20:13:29.752369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34b1e7c5-c93c-4568-b4ca-bac2e5a1de86 · outbound

This paper cites Linear mode connectivity and the lottery ticket hypothesis.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Linear mode connectivity and the lottery ticket hypothesis

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T20:13:29.757180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f56ddbc-07be-410b-b785-1b7af9124770 · outbound

This paper cites Schwab, and Ari S.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Schwab, and Ari S

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:31.229786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b50c45ab-e12c-47e1-b6c9-02e4ceecb103 · outbound

This paper cites An investigation into neural net optimization via hessian eigenvalue density.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks An investigation into neural net optimization via hessian eigenvalue density

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T20:13:29.766480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61b9e24e-fe07-48a8-8973-65a4ab906024 · outbound

This paper cites Gradient Descent Happens in a Tiny Subspace.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Gradient Descent Happens in a Tiny Subspace

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T20:13:29.771210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ac6bff8-0044-4deb-af4a-4b081f6eb9b5 · outbound

This paper cites Deep residual learning for image recognition.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Deep residual learning for image recognition

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T20:13:29.776453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15be1226-57b9-48bb-a542-bb0b4f2bdb77 · outbound

This paper cites Neural tangent kernel: Convergence and generalization in neural networks.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Neural tangent kernel: Convergence and generalization in neural networks

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:31.044548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5f37249c-2dc9-42d2-bbd2-97e11019ac2a · outbound

This paper cites The Break-Even Point on Optimization Trajectories of Deep Neural Networks.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks The Break-Even Point on Optimization Trajectories of Deep Neural Networks

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T20:13:29.786110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 688b3afa-7afd-4dcb-9f3e-3a9a89728fba · outbound

This paper cites Assessing generalization of SGD via disagreement.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Assessing generalization of SGD via disagreement

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:30.987294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 950d4d1b-84a3-4791-9c0d-388bd69531be · outbound

This paper cites Wide neural networks of any depth evolve as linear models under gradient descent.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Wide neural networks of any depth evolve as linear models under gradient descent

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:30.971993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation df13fba8-fcfc-417e-bc83-06aeabefc0c4 · outbound

This paper cites Learning overparameterized neural networks via stochastic gradient descent on structured data.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Learning overparameterized neural networks via stochastic gradient descent on structured data

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:30.898297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 57864035-d4bf-4107-b8aa-be124642e3a7 · outbound

This paper cites What happens after SGD reaches zero loss? –a mathematical framework.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks What happens after SGD reaches zero loss? –a mathematical framework

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:30.806664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4aaa7dca-ce47-40be-a908-c86e90f94368 · outbound

This paper cites Task arithmetic in the tangent space: Improved editing of pre-trained models.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Task arithmetic in the tangent space: Improved editing of pre-trained models

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:30.778035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9a8f9344-aaf0-48bf-8437-bbd304c96c3e · outbound

This paper cites Deep learning-based weather prediction: a survey.Big Data Research, 23:100178, 2021.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Deep learning-based weather prediction: a survey.Big Data Research, 23:100178, 2021

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:30.761658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 47e81bda-07a5-4567-bbd6-c98b13dfb8a4 · outbound

This paper cites Very Deep Convolutional Networks for Large-Scale Image Recognition.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Very Deep Convolutional Networks for Large-Scale Image Recognition

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T20:13:29.823505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa1e766a-4168-4371-b31a-0d395e49246e · outbound

This paper cites The directionality of optimization trajectories in neural networks.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks The directionality of optimization trajectories in neural networks

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:30.745789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e895e113-11a2-4826-8939-15d878945eca · outbound

This paper cites A survey on statistical theory of deep learning: Approximation, training dynamics, and generative models.Annual Review of Statistics and Its Application, 12, 2024.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks A survey on statistical theory of deep learning: Approximation, training dynamics, and generative models.Annual Review of Statistics and Its Application, 12, 2024

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:30.714657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b53df735-f7d5-4d19-a196-2d22720fbe4f · outbound

This paper cites Deep reinforcement learning for robotics: A survey of real-world successes.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Deep reinforcement learning for robotics: A survey of real-world successes

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:30.598999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a4311636-0f69-4d2e-94ee-99c02db9abb2 · outbound

This paper cites Analyzing sharpness along gd trajectory: Progressive sharpening and edge of stability.Advances in Neural Information Processing Systems, 35:9983–9994, 2022.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Analyzing sharpness along gd trajectory: Progressive sharpening and edge of stability.Advances in Neural Information Processing Systems, 35:9983–9994, 2022

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:30.524046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 603f0ea1-1e6c-42be-84d0-f4a962cd7324 · outbound

This paper cites Model soups: aver- aging weights of multiple fine-tuned models improves accuracy without increasing inference time.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Model soups: aver- aging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:30.507224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4670cb38-136d-44f5-997e-1f5fe9c7dcde · outbound

This paper cites Robust fine-tuning of zero-shot models.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Robust fine-tuning of zero-shot models

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:30.488597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b35d1f7b-bccf-4022-9799-d1e85cd941d7 · outbound

This paper cites How sgd selects the global minima in over-parameterized learning: A dynamical stability perspective.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks How sgd selects the global minima in over-parameterized learning: A dynamical stability perspective

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:30.354567Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2c5c2bfd-66fd-47a1-bdc5-76a3ab71567e · outbound

This paper cites Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T20:13:29.977799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44e1d77c-0e50-45a0-b3d1-5ae2a9bf10c5 · outbound

This paper cites Swing-by dynamics in concept learning and compositional generalization.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Swing-by dynamics in concept learning and compositional generalization

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:30.276528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 47a22bdb-fa18-4cb6-b48b-2ea7b7a69f22 · outbound

This paper cites Going beyond linear mode connectivity: The layerwise linear feature connectivity.Advances in neural information processing systems, 36:60853–60877, 2023.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Going beyond linear mode connectivity: The layerwise linear feature connectivity.Advances in neural information processing systems, 36:60853–60877, 2023

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T20:13:29.988384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1e2713f-3f23-40e6-8833-f8390927f994 · outbound

This paper cites On the emergence of cross-task linearity in pretraining-finetuning paradigm.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks On the emergence of cross-task linearity in pretraining-finetuning paradigm

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:30.248172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 408770bd-781c-4fb3-9838-f1d5b8573072 · outbound

This paper cites Gradient descent optimizes over-parameterized deep relu networks.Machine learning, 109:467–492, 2020.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Gradient descent optimizes over-parameterized deep relu networks.Machine learning, 109:467–492, 2020

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:13:30.207822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation caf29d74-1275-450b-980c-7bb2cbd59895 · outbound

This paper cites an unresolved cited work.

New Evidence of the Two-Phase Learning Dynamics of Neural Networks Unresolved cited work

Reference 2025

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:13:30.730930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Pith citing papers

No inbound Pith citation observations are available.