Paper Citation Record · LEDGER

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning

As of 6 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 2 inbound Pith citation observations for arXiv:2602.20062.

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

pith.paper-citation-record.v1
2602.20062 v2

Coverage vector

measured 55 of 55 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T21:30:54.180653Z

measured 57 of 57 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-25T05:55:10.325836Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-25T05:55:24.019027Z

Reference resolution

55 of 55 outbound references displayed

verified exact0
verified fuzzy0
unresolved55
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 59f0bb67-2507-4970-87db-f3892ad1695e · outbound

This paper cites Neural networks as kernel learners: The silent alignment effect, 10 2021.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning Neural networks as kernel learners: The silent alignment effect, 10 2021

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:49.884441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d0ee721-d2a7-4e30-901a-9730a05b89ad · outbound

This paper cites M., Cholakkal, H., Shah, M., Yang, M.-H., and Khan, F.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning M., Cholakkal, H., Shah, M., Yang, M.-H., and Khan, F

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:49.916160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3297e28c-2d48-4d67-b953-fdf13188f00a · outbound

This paper cites S., Woodworth, B.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning S., Woodworth, B

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:49.987592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a16299bb-75e6-4c5b-9694-15f43c8e3e70 · outbound

This paper cites and Montanari, A.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning and Montanari, A

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:50.100342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d868dc36-ebcd-4177-854a-f6cf7a26873c · outbound

This paper cites and Montanari, A.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning and Montanari, A

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:50.209440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5a0ad6c-a66f-41b8-98f5-5e4d34c5beb6 · outbound

This paper cites and M \"u ller, R.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning and M \"u ller, R

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:50.268733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a85d9e5-1126-4fbe-84b9-7ecf1f339ec9 · outbound

This paper cites R., and Schulz-Baldes, H.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning R., and Schulz-Baldes, H

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:50.313876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f92376a-e77e-4f63-accc-5c40b8e580df · outbound

This paper cites Incremental learning in diagonal linear networks.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning Incremental learning in diagonal linear networks

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:50.353814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95dbc523-b5af-490f-8cd6-81973723dfed · outbound

This paper cites On the Opportunities and Risks of Foundation Models.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning On the Opportunities and Risks of Foundation Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:50.405308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9bd822d-ec60-4d37-873a-60dec6d26665 · outbound

This paper cites Exact learning dynamics of deep linear networks with prior knowledge.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning Exact learning dynamics of deep linear networks with prior knowledge

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:50.492722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a2baf06-380f-498c-b65c-b4dbbb39ae9e · outbound

This paper cites and Bach, F.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning and Bach, F

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:50.594416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a2c5efa-99cf-474b-894c-aa759a367748 · outbound

This paper cites On lazy training in differentiable programming.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning On lazy training in differentiable programming

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:50.695889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8a90f2f-58a3-470e-a3b1-6b9a35e89265 · outbound

This paper cites Ask Your Distribution Shift if Pre-Training is Right for You.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning Ask Your Distribution Shift if Pre-Training is Right for You

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:50.791331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb9fab7a-155a-40e6-b22b-bbfcdc86025d · outbound

This paper cites From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:50.893495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 006c9240-117a-46f7-b735-45e46987d7d1 · outbound

This paper cites an unresolved cited work.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:51.033052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76a65956-41f3-47e9-8680-0dae8e3b0dbf · outbound

This paper cites K., Paul, M., Kharaghani, S., Roy, D.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning K., Paul, M., Kharaghani, S., Roy, D

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:51.097585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 449667df-ff04-4aab-ae3d-870c14bdd642 · outbound

This paper cites A theory of multineuronal dimensionality, dynamics and measurement.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning A theory of multineuronal dimensionality, dynamics and measurement

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:51.127385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21a581be-8d00-40fb-94b9-e67b2ec89420 · outbound

This paper cites R., and Aoi, M.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning R., and Aoi, M

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:51.197288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a714be6b-bd1d-4a54-b47a-0eb60c3b47c2 · outbound

This paper cites Characterizing implicit bias in terms of optimization geometry.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning Characterizing implicit bias in terms of optimization geometry

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:51.243328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5c43e10-ea5f-4ffb-9dc0-33ff57426479 · outbound

This paper cites and Verd \'u , S.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning and Verd \'u , S

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:51.288371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55c7ae16-7424-40ce-a31a-a65023293add · outbound

This paper cites What makes ImageNet good for transfer learning?.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning What makes ImageNet good for transfer learning?

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:51.355068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38796d70-5e70-4226-9189-acd7406fa9f2 · outbound

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

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning Neural tangent kernel: Convergence and generalization in neural networks

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:51.404512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e5ea2a4-2672-4f16-8bd4-25c9f88dae83 · outbound

This paper cites Train on Validation (ToV): Fast data selection with applications to fine-tuning.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning Train on Validation (ToV): Fast data selection with applications to fine-tuning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:51.439162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 222ab62a-eff7-478f-b07d-541fd0edfdff · outbound

This paper cites Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:51.482772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dc8c455-ea4b-42ea-9e8c-799e53dfad81 · outbound

This paper cites Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:51.528872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc8c2ec6-ab9b-4ab2-bf1e-6a43de119877 · outbound

This paper cites A., Xu, W., Avestimehr, A.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning A., Xu, W., Avestimehr, A

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:51.572721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08a4bd9c-c927-490c-9ea0-52ee5443f3ed · outbound

This paper cites an unresolved cited work.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:51.614373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22023ff0-97d8-4172-bf1d-f773f17e3571 · outbound

This paper cites Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:51.714613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be810198-8210-43b1-879f-11a02e250506 · outbound

This paper cites Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:51.868185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4def346e-c0ed-42d8-85a5-c6bde3e50cd3 · outbound

This paper cites An analytic theory of generalization dynamics and transfer learning in deep linear networks.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning An analytic theory of generalization dynamics and transfer learning in deep linear networks

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:51.976081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92933dcf-3120-44e7-9713-58a2446c998f · outbound

This paper cites and Lindsey, J.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning and Lindsey, J

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:52.128369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f06f2f7-2c4f-4e83-8e0d-6896c75f72d3 · outbound

This paper cites Gradient Descent Maximizes the Margin of Homogeneous Neural Networks.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning Gradient Descent Maximizes the Margin of Homogeneous Neural Networks

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:52.266398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9431c584-f450-432a-abe9-9a46a7809795 · outbound

This paper cites A kernel-based view of language model fine-tuning.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning A kernel-based view of language model fine-tuning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:52.404458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9c035d6-40c7-4937-bdd4-7cd8522e6607 · outbound

This paper cites Abide by the law and follow the flow: conservation laws for gradient flows, 12 2023.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning Abide by the law and follow the flow: conservation laws for gradient flows, 12 2023

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:52.571553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c29b522-a8f3-4d71-8ca1-f5a0f933ceb3 · outbound

This paper cites an unresolved cited work.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:52.693140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93f1a70e-722c-4fa2-acf2-d6f997f13faf · outbound

This paper cites Applications of Large Random Matrices in Communications Engineering.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning Applications of Large Random Matrices in Communications Engineering

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:52.805911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bde92dd5-183e-47a9-8a75-8ee7c50c5330 · outbound

This paper cites S., Gunasekar, S., Lee, J., Srebro, N., and Soudry, D.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning S., Gunasekar, S., Lee, J., Srebro, N., and Soudry, D

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:52.899019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c22e3cac-db5c-47f0-9256-e3f8d218b7ab · outbound

This paper cites S., Ravichandran, K., Srebro, N., and Soudry, D.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning S., Ravichandran, K., Srebro, N., and Soudry, D

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:52.975413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f21c03c0-66a1-4bba-9af9-ef00efa212d4 · outbound

This paper cites The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:53.064503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d851012b-3a44-4755-92f1-c5e1f9d2b4b1 · outbound

This paper cites and Flammarion, N.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning and Flammarion, N

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:53.136876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d819b0ae-55b1-4cc3-a180-33aa0570a2d3 · outbound

This paper cites Implicit bias of sgd for diagonal linear networks: a provable benefit of stochasticity.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning Implicit bias of sgd for diagonal linear networks: a provable benefit of stochasticity

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:53.229231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42bd3e56-58a5-40ed-96d2-94e6a7334b4c · outbound

This paper cites an unresolved cited work.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning Unresolved cited work

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:53.323905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af03399a-9ae5-4531-9cc8-f0deb651bc0d · outbound

This paper cites How do infinite width bounded norm networks look in function space? In Conference on Learning Theory, pp.\ 2667--2690.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning How do infinite width bounded norm networks look in function space? In Conference on Learning Theory, pp.\ 2667--2690

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:53.386758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21bbf31b-07a8-4f02-a7f4-ae55c7ab8873 · outbound

This paper cites L., and Ganguli, S.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning L., and Ganguli, S

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:53.456359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02b0c49d-8e12-4dd6-a58d-8edafaa4affe · outbound

This paper cites M., McClelland, J.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning M., McClelland, J

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:53.551434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d87e80e0-6f31-4e46-8bbc-5cb87865e881 · outbound

This paper cites A theoretical analysis of fine-tuning with linear teachers.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning A theoretical analysis of fine-tuning with linear teachers

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:53.658605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9f7f493-3d3b-4472-ba5c-e4d11c9c1d5f · outbound

This paper cites S., Gunasekar, S., and Srebro, N.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning S., Gunasekar, S., and Srebro, N

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:53.766153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b790542-f1a9-42bf-bbc1-41d2f62b412d · outbound

This paper cites Features are fate: a theory of transfer learning in high-dimensional regression.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning Features are fate: a theory of transfer learning in high-dimensional regression

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:53.816520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a2fa254-11d8-406b-8bd3-4bc99f466981 · outbound

This paper cites and Sato, I.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning and Sato, I

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:53.872616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17d811cc-42a8-4554-9269-ea3569dda412 · outbound

This paper cites and Lu, W.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning and Lu, W

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:53.922347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e20161cf-43e6-4be2-8c21-a002f48ac39d · outbound

This paper cites Limitations of the NTK for Understanding Generalization in Deep Learning.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning Limitations of the NTK for Understanding Generalization in Deep Learning

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:53.974565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a1577c9-56bd-489a-9557-235a30a3ba19 · outbound

This paper cites D., Moroshko, E., Savarese, P., Golan, I., Soudry, D., and Srebro, N.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning D., Moroshko, E., Savarese, P., Golan, I., Soudry, D., and Srebro, N

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:54.028680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbc813df-f6c7-4054-a144-af0f6cdfda0a · outbound

This paper cites How transferable are features in deep neural networks? Advances in neural information processing systems, 27, 2014.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning How transferable are features in deep neural networks? Advances in neural information processing systems, 27, 2014

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:54.086358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e137aa50-0b28-4426-a65f-3f5aec7f2996 · outbound

This paper cites Understanding deep learning requires rethinking generalization.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning Understanding deep learning requires rethinking generalization

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:54.126249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37204e22-915a-4584-a8e6-0c62d39a36f1 · outbound

This paper cites write newline.

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning write newline

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-02T21:30:54.180653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 745444f6-ea4e-46ff-8ee8-50d251a35440 · inbound

Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing cites this paper.

Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning

Reference 63

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T02:17:19.837651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f93d44aa-e97b-45a6-8c3c-e82d51431e77 · inbound

A mathematical theory of balancing relational generalization and memorization cites this paper.

A mathematical theory of balancing relational generalization and memorization A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning

Reference 93

Resolution: verified exact; arxiv_id, observed 2026-07-01T02:17:19.837651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.