Paper Citation Record · LEDGER

Early Stopping Against Label Noise Without Validation Data

As of 23 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 3 inbound Pith citation observations for arXiv:2502.07551.

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

pith.paper-citation-record.v1
2502.07551 v1

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T12:26:42.679260Z

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T21:07:28.883883Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-30T20:15:04.558767Z

Reference resolution

22 of 22 outbound references displayed

verified exact1
verified fuzzy7
unresolved13
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 98f17a77-5c6e-4802-a0da-bd6f3b52f93b · outbound

This paper cites learning confusing patterns.

Early Stopping Against Label Noise Without Validation Data learning confusing patterns

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:26:42.969997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9697d4ec-1223-4c45-af01-683e3abd09c0 · outbound

This paper cites WebVision Database: Visual Learning and Understanding from Web Data.

Early Stopping Against Label Noise Without Validation Data WebVision Database: Visual Learning and Understanding from Web Data

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T12:26:42.602995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c54237b-ce7a-4866-bf58-5503a4b247cf · outbound

This paper cites On the Over-Memorization During Natural, Robust and Catastrophic Overfitting.

Early Stopping Against Label Noise Without Validation Data On the Over-Memorization During Natural, Robust and Catastrophic Overfitting

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T12:26:42.607927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a07d8c61-c57a-4610-aaf6-a18fafb0392f · outbound

This paper cites SELC: Self-Ensemble Label Correction Improves Learning with Noisy Labels.

Early Stopping Against Label Noise Without Validation Data SELC: Self-Ensemble Label Correction Improves Learning with Noisy Labels

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-08-08T12:26:42.818207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6ebbae61-e05e-434a-9fe3-d68944fae6ec · outbound

This paper cites Early Stopping without a Validation Set.

Early Stopping Against Label Noise Without Validation Data Early Stopping without a Validation Set

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T12:26:42.617957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 434945aa-7861-44d2-8c62-a73a8bf63fb6 · outbound

This paper cites Characterizing datapoints via second-split forgetting.

Early Stopping Against Label Noise Without Validation Data Characterizing datapoints via second-split forgetting

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:26:43.015069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d3ee704d-5626-414c-9028-9933eb4066a9 · outbound

This paper cites How does Early Stopping Help Generalization against Label Noise?.

Early Stopping Against Label Noise Without Validation Data How does Early Stopping Help Generalization against Label Noise?

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T12:26:42.646205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 089a78fe-c8de-4f60-aa3a-64f3b6372e37 · outbound

This paper cites Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude.

Early Stopping Against Label Noise Without Validation Data Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:26:43.000059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e6042159-613c-46cc-9815-28b4faad2517 · outbound

This paper cites Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations.

Early Stopping Against Label Noise Without Validation Data Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-08T12:26:42.656031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67d1fb17-fbf3-497b-b31d-7292f974f287 · outbound

This paper cites an unresolved cited work.

Early Stopping Against Label Noise Without Validation Data Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-08T12:26:42.984321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e12deb08-180a-4623-a10c-9a03db4f8369 · outbound

This paper cites This method, as detailed in the paper, employs moving averages of Prediction Changes (PC) for early stopping in training models with noisy labels.

Early Stopping Against Label Noise Without Validation Data This method, as detailed in the paper, employs moving averages of Prediction Changes (PC) for early stopping in training models with noisy labels

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:26:42.926829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d0272a49-f816-4c1f-bd50-4d31dfe1f267 · outbound

This paper cites Difference.

Early Stopping Against Label Noise Without Validation Data Difference

Reference 256

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:26:42.941619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation da66f368-b4a5-4dee-8f79-192c0e64f7cb · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Early Stopping Against Label Noise Without Validation Data Adam: A Method for Stochastic Optimization

Reference 1938

Resolution: unresolved; no resolver link, observed 2026-08-08T12:26:42.598282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffccf4bb-8271-40d3-b0d0-a17beea5cbc7 · outbound

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

Early Stopping Against Label Noise Without Validation Data Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets

Reference 1964

Resolution: unresolved; no resolver link, observed 2026-08-08T12:26:42.636926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e79cd6bf-b699-405e-809e-679d30ec3af4 · outbound

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

Early Stopping Against Label Noise Without Validation Data Very Deep Convolutional Networks for Large-Scale Image Recognition

Reference 1999

Resolution: unresolved; no resolver link, observed 2026-08-08T12:26:42.641622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89c2ca7a-cfda-42dd-a601-9b9e4b8d0b3a · outbound

This paper cites On the importance of single directions for generalization.

Early Stopping Against Label Noise Without Validation Data On the importance of single directions for generalization

Reference 2014

Resolution: unresolved; no resolver link, observed 2026-08-08T12:26:42.627401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d89980de-48d7-4d78-915e-870ca2ec313b · outbound

This paper cites Predicting the Generalization Gap in Deep Networks with Margin Distributions.

Early Stopping Against Label Noise Without Validation Data Predicting the Generalization Gap in Deep Networks with Margin Distributions

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-08T12:26:42.593184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 794278ea-8ab9-4ae8-85a4-0ae4214ee88d · outbound

This paper cites A Survey of Label-noise Representation Learning: Past, Present and Future.

Early Stopping Against Label Noise Without Validation Data A Survey of Label-noise Representation Learning: Past, Present and Future

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-08T12:26:42.583153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68361961-1d18-4647-bc1b-81ad08864c94 · outbound

This paper cites Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning.

Early Stopping Against Label Noise Without Validation Data Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning

Reference 2017

Resolution: verified exact; local_arxiv, observed 2026-08-08T12:26:42.895689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7d04f8d5-3579-474b-8a00-a4895b1d7fbd · outbound

This paper cites Table 4: Differences (mean±std) among the model selection methods.

Early Stopping Against Label Noise Without Validation Data Table 4: Differences (mean±std) among the model selection methods

Reference 2019

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:26:42.955770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2bad46f7-2d0c-496c-99f7-c7bae58c21be · outbound

This paper cites Leveraging unlabeled data to track memoriza- tion.

Early Stopping Against Label Noise Without Validation Data Leveraging unlabeled data to track memoriza- tion

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:26:43.029203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 73b8cc4b-8f59-4f72-a70a-34279da9f1f9 · outbound

This paper cites Progress measures for grokking via mechanistic interpretability.

Early Stopping Against Label Noise Without Validation Data Progress measures for grokking via mechanistic interpretability

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-08T12:26:42.632050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation dfa74679-f104-439c-a3b9-8df4caf6e540 · inbound

Is Supervised Learning Really That Different from Unsupervised? cites this paper.

Is Supervised Learning Really That Different from Unsupervised? Early Stopping Against Label Noise Without Validation Data

Reference 5662

Resolution: unresolved; no resolver link, observed 2026-08-15T21:07:28.883883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce5d14f9-edb7-430e-ace7-c59d85981bab · inbound

CLID-MU: Cross-Layer Information Divergence Based Meta Update Strategy for Learning with Noisy Labels cites this paper.

CLID-MU: Cross-Layer Information Divergence Based Meta Update Strategy for Learning with Noisy Labels Early Stopping Against Label Noise Without Validation Data

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T17:06:44.006796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2c84aa8-0c42-4fe6-b13c-1cdea6bfbf9d · inbound

Analyzing Codes of Conduct for Online Safety in Video Games at Scale cites this paper.

Analyzing Codes of Conduct for Online Safety in Video Games at Scale Early Stopping Against Label Noise Without Validation Data

Reference 112

Resolution: verified exact; arxiv_id, observed 2026-06-30T20:15:04.560347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.