Paper Citation Record · LEDGER

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining

As of 17 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2506.20025.

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

pith.paper-citation-record.v1
2506.20025 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:29:35.146512Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+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

30 of 30 outbound references displayed

verified exact1
verified fuzzy16
unresolved12
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 57233c14-d197-45a1-a906-3bc22e6425b7 · outbound

This paper cites Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:29:35.665738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a08d7a6c-03e8-4225-bf35-0d9b6ab0a94b · outbound

This paper cites On Feature Learning in the Presence of Spurious Correlations.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining On Feature Learning in the Presence of Spurious Correlations

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T18:29:35.037870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01a463e6-558a-440c-9934-fc534d129b8d · outbound

This paper cites Theoretical guarantees of data augmented last layer retraining methods.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining Theoretical guarantees of data augmented last layer retraining methods

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:29:35.653685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7d065efe-f796-475a-b6cf-ecb72a905c1f · outbound

This paper cites an unresolved cited work.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:29:35.641355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a1a6a84e-609b-4f98-80a8-d087f21bb760 · outbound

This paper cites Long-tail learning via logit adjustment.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining Long-tail learning via logit adjustment

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T18:29:35.051045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35af50d4-de42-4ce6-8f63-5726ca9f9e81 · outbound

This paper cites Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T18:29:35.055449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7216259e-29da-4f70-a907-d5ba9fce2331 · outbound

This paper cites Towards a Theoretical Framework of Out-of-Distribution Generalization.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining Towards a Theoretical Framework of Out-of-Distribution Generalization

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:29:35.629161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a73eabc4-1ad3-468a-a1b0-ec3f77022c7e · outbound

This paper cites A statistical theory of overfitting for imbalanced classification.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining A statistical theory of overfitting for imbalanced classification

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T18:29:35.063712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 663e8d15-0f62-456f-aee0-a4d5f2038dd3 · outbound

This paper cites Label- imbalanced and group-sensitive classification under overparameterization.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining Label- imbalanced and group-sensitive classification under overparameterization

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:29:35.614507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1526a489-435c-4640-817b-e3f8f7d5c4d4 · outbound

This paper cites importance- weighted.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining importance- weighted

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T18:29:35.070509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96f6208d-1e2d-446e-be7f-e51a64761db8 · outbound

This paper cites an unresolved cited work.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:29:35.602432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4623a560-e431-4a55-80d9-fbc1499efa62 · outbound

This paper cites Understanding the role of importance weighting for deep learn- ing.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining Understanding the role of importance weighting for deep learn- ing

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:29:35.590476Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a05a3797-1087-4a1a-bc84-0ba92cb77039 · outbound

This paper cites The implicit bias of gradient descent on separable data.The Journal of Machine Learning Research, 19(1):2822–2878, January 2018.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining The implicit bias of gradient descent on separable data.The Journal of Machine Learning Research, 19(1):2822–2878, January 2018

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:29:35.579697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 95a3cae8-847a-4774-a6bc-e87945a2ab3a · outbound

This paper cites The implicit bias of gradient descent on nonseparable data.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining The implicit bias of gradient descent on nonseparable data

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:29:35.567734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation fbde042c-6f9a-4858-8297-643d82e9df6c · outbound

This paper cites Characterizing Implicit Bias in Terms of Optimization Geometry.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining Characterizing Implicit Bias in Terms of Optimization Geometry

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:29:35.558533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c3d7f983-0c1e-4930-b15d-747711764f52 · outbound

This paper cites Understanding the role of importance weighting for deep learning.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining Understanding the role of importance weighting for deep learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T18:29:35.093196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb3dd42c-0d7a-450a-a42b-1df318e41a3b · outbound

This paper cites An Investigation of Why Overparameterization Exacerbates Spurious Correlations.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining An Investigation of Why Overparameterization Exacerbates Spurious Correlations

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T18:29:35.097658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fe50037-2739-41c9-ae99-f6678114a3d2 · outbound

This paper cites On how to avoid exacerbating spurious correlations when models are overparameterized.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining On how to avoid exacerbating spurious correlations when models are overparameterized

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-08-15T18:29:35.284881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 340d54e9-dcde-42e9-998e-2340a9d2c878 · outbound

This paper cites Towards last-layer retraining for group robust- ness with fewer annotations.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining Towards last-layer retraining for group robust- ness with fewer annotations

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:29:35.548452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 11665f37-afe3-4c08-85da-9ace4bb7f1a7 · outbound

This paper cites For robust worst-group accuracy, ignore group annotations.Transactions on Machine Learning Research,.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining For robust worst-group accuracy, ignore group annotations.Transactions on Machine Learning Research,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:29:35.537404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation cbed6ee9-b849-45aa-94fd-1b4a5f9bf021 · outbound

This paper cites A framework to characterize performance of LASSO algorithms.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining A framework to characterize performance of LASSO algorithms

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T18:29:35.113218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da03af35-e805-48ce-ad36-24c9e5ac2ade · outbound

This paper cites Regularized Linear Regression: A Precise Analysis of the Estimation Error.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining Regularized Linear Regression: A Precise Analysis of the Estimation Error

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:29:35.525568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 13a74dc7-202d-465c-b1d3-94b08739e258 · outbound

This paper cites Precise error analysis of regularized m- estimators in high dimensions.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining Precise error analysis of regularized m- estimators in high dimensions

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:29:35.512519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8c9eec6a-e345-4a70-aa19-93aa890bda46 · outbound

This paper cites The Role of Regularization in Classification of High-dimensional Noisy Gaussian Mixture.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining The Role of Regularization in Classification of High-dimensional Noisy Gaussian Mixture

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:29:35.500105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7244c2b3-43ce-4c55-93a5-5b57b70b6e53 · outbound

This paper cites Deep learning face attributes in the wild.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining Deep learning face attributes in the wild

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T18:29:35.127905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a99349c4-7de3-4a27-89aa-4a0205796fff · outbound

This paper cites Learning multiple layers of features from tiny images.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining Learning multiple layers of features from tiny images

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:29:35.475983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation be0a3df1-93ba-41c3-b968-abf00451b5b6 · outbound

This paper cites Evaluation of neural architectures trained with square loss vs cross-entropy in classification tasks.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining Evaluation of neural architectures trained with square loss vs cross-entropy in classification tasks

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:29:35.463166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 984ff939-6742-42b4-8b69-cde68ee91a6a · outbound

This paper cites LQF: Linear Quadratic Fine-Tuning.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining LQF: Linear Quadratic Fine-Tuning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T18:29:35.137989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cba8e8be-83f8-4dc7-97e2-37437208a9f3 · outbound

This paper cites Sharp Asymptotics and Optimal Performance for Inference in Binary Models.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining Sharp Asymptotics and Optimal Performance for Inference in Binary Models

Reference 29

Resolution: malformed identifier; local_arxiv, observed 2026-08-15T18:29:35.184194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 65c17675-fa3f-4657-a4aa-4e2e43c8c6e8 · outbound

This paper cites We see that up toρ = 60, the per-class errors do not meet.

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining We see that up toρ = 60, the per-class errors do not meet

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:29:35.450766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

No inbound Pith citation observations are available.