Paper Citation Record · LEDGER

Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization

As of 10 August 2026, this Paper Citation Record lists 8 of 8 outbound references and 0 inbound Pith citation observations for arXiv:2602.00827.

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

pith.paper-citation-record.v1
2602.00827 v2

Coverage vector

measured 8 of 8 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T06:00:15.484909Z

measured 8 of 8 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 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

8 of 8 outbound references displayed

verified exact0
verified fuzzy0
unresolved7
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1eabee19-7a0e-400e-a354-3d2bfa6eeeaa · outbound

This paper cites an unresolved cited work.

Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T06:00:15.170988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41830fe2-f680-421c-92e5-ccb2742dc407 · outbound

This paper cites (2024, Appendix D.2), andβ:= (λx min)2/(32xmax).

Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization (2024, Appendix D.2), andβ:= (λx min)2/(32xmax)

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T06:00:15.306784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7eb00b84-6ccc-4e33-91f7-944b3fd7f28d · outbound

This paper cites Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization.

Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T06:00:14.874974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60233ebf-fd6a-4d52-88b8-e0fb2b91695e · outbound

This paper cites U-shape,.

Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization U-shape,

Reference 5

Resolution: malformed identifier; no resolver link, observed 2026-08-03T06:00:15.066357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation deeba83c-85ff-4928-a338-afd306d7099d · outbound

This paper cites (2022).)sign(v j(t)) = sign(vj(0)).

Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization (2022).)sign(v j(t)) = sign(vj(0))

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T06:00:15.430895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1886f39-d632-465e-b98b-08042dcdd6bd · outbound

This paper cites AUXILIARYLEMMATA Before start, we define Π∥ to be a orthogonal projection onto s and Π⊥ to be the orthogonal projection onto its complement.

Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization AUXILIARYLEMMATA Before start, we define Π∥ to be a orthogonal projection onto s and Π⊥ to be the orthogonal projection onto its complement

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T06:00:15.484909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 586fda19-a8a8-40da-b22c-a0822fc908b7 · outbound

This paper cites Saddle-to-Saddle Dynamics in Deep Linear Networks: Small Initialization Training, Symmetry, and Sparsity.

Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization Saddle-to-Saddle Dynamics in Deep Linear Networks: Small Initialization Training, Symmetry, and Sparsity

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-03T06:00:14.652992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c268e8d9-313c-417a-bb82-179ea1854510 · outbound

This paper cites Gradient Descent Quantizes ReLU Network Features.

Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization Gradient Descent Quantizes ReLU Network Features

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-03T06:00:14.707112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.