Paper Citation Record · LEDGER

Beyond Self-Consistency: Loss-Balanced Perturbation-Based Regularization Improves Industrial-Scale Ads Ranking

As of 15 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2502.18478.

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

pith.paper-citation-record.v1
2502.18478 v1

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T04:12:56.312226Z

measured 15 of 15 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+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

15 of 15 outbound references displayed

verified exact3
verified fuzzy5
unresolved6
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ec0149e4-686e-460f-99cb-71f1f3afb157 · outbound

This paper cites On the Factory Floor: ML Engineering for Industrial-Scale Ads Recommendation Models.

Beyond Self-Consistency: Loss-Balanced Perturbation-Based Regularization Improves Industrial-Scale Ads Ranking On the Factory Floor: ML Engineering for Industrial-Scale Ads Recommendation Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-09T04:12:56.232629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18f0045a-78fe-424a-9ccc-a8fae5736cde · outbound

This paper cites Explicit regularization in overparametrized models via noise injection.

Beyond Self-Consistency: Loss-Balanced Perturbation-Based Regularization Improves Industrial-Scale Ads Ranking Explicit regularization in overparametrized models via noise injection

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:12:56.757074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 81086b4e-6c37-4cbd-9a52-fa7cfb159d58 · outbound

This paper cites Feature Dropout: Revisiting the Role of Augmentations in Contrastive Learning.

Beyond Self-Consistency: Loss-Balanced Perturbation-Based Regularization Improves Industrial-Scale Ads Ranking Feature Dropout: Revisiting the Role of Augmentations in Contrastive Learning

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-09T04:12:56.401495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation dc5e2b4e-abcc-4d67-9509-032039b0ad14 · outbound

This paper cites Dhen: A deep and hierarchical ensemble network for large-scale click-through rate prediction.

Beyond Self-Consistency: Loss-Balanced Perturbation-Based Regularization Improves Industrial-Scale Ads Ranking Dhen: A deep and hierarchical ensemble network for large-scale click-through rate prediction

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:12:56.706309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9839519e-9c8b-4dd5-963a-75068630e817 · outbound

This paper cites mixup: Beyond Empirical Risk Minimization.

Beyond Self-Consistency: Loss-Balanced Perturbation-Based Regularization Improves Industrial-Scale Ads Ranking mixup: Beyond Empirical Risk Minimization

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-09T04:12:56.312226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ef77d27-b7cf-4311-acd6-c76e04522a4d · outbound

This paper cites Hao Wang, Naiyan Wang, and Dit-Yan Yeung.

Beyond Self-Consistency: Loss-Balanced Perturbation-Based Regularization Improves Industrial-Scale Ads Ranking Hao Wang, Naiyan Wang, and Dit-Yan Yeung

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:12:56.740443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 61c06dc8-dc4b-4f25-abee-54b43f6f546d · outbound

This paper cites Deep learning.nature, pages 436–44., 2015 May.

Beyond Self-Consistency: Loss-Balanced Perturbation-Based Regularization Improves Industrial-Scale Ads Ranking Deep learning.nature, pages 436–44., 2015 May

Reference 2003

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:12:56.723729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 40fd9b43-34d7-4e0f-be44-2d75fdfe4084 · outbound

This paper cites Samarth Sinha and Adji Bousso Dieng.

Beyond Self-Consistency: Loss-Balanced Perturbation-Based Regularization Improves Industrial-Scale Ads Ranking Samarth Sinha and Adji Bousso Dieng

Reference 2007

Resolution: malformed identifier; doi_truncated, observed 2026-08-09T04:12:56.359643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation cbb5f9cd-d43e-44bd-ab0a-330848d6d242 · outbound

This paper cites Noise stability regularization for improving bert fine-tuning.

Beyond Self-Consistency: Loss-Balanced Perturbation-Based Regularization Improves Industrial-Scale Ads Ranking Noise stability regularization for improving bert fine-tuning

Reference 2014

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:12:56.773704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9e189a30-4d4b-4b51-85ae-aecdd7235679 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

Beyond Self-Consistency: Loss-Balanced Perturbation-Based Regularization Improves Industrial-Scale Ads Ranking BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-09T04:12:56.244823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e920a69-1077-4c59-9e01-c19dfbad3c49 · outbound

This paper cites SimCSE: Simple Contrastive Learning of Sentence Embeddings.

Beyond Self-Consistency: Loss-Balanced Perturbation-Based Regularization Improves Industrial-Scale Ads Ranking SimCSE: Simple Contrastive Learning of Sentence Embeddings

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-09T04:12:56.258259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61f0db1e-c9a4-4a90-bbf0-d4946d2c1361 · outbound

This paper cites DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings.

Beyond Self-Consistency: Loss-Balanced Perturbation-Based Regularization Improves Industrial-Scale Ads Ranking DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-09T04:12:56.238951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a3d1e36-f3b6-4df7-a70b-4b070f9944b6 · outbound

This paper cites SelfMatch: Combining Contrastive Self-Supervision and Consistency for Semi-Supervised Learning.

Beyond Self-Consistency: Loss-Balanced Perturbation-Based Regularization Improves Industrial-Scale Ads Ranking SelfMatch: Combining Contrastive Self-Supervision and Consistency for Semi-Supervised Learning

Reference 2021

Resolution: verified exact; local_arxiv, observed 2026-08-09T04:12:56.441344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation eb3e3df6-109b-4788-951d-4d522355c3d3 · outbound

This paper cites Deep Learning Recommendation Model for Personalization and Recommendation Systems.

Beyond Self-Consistency: Loss-Balanced Perturbation-Based Regularization Improves Industrial-Scale Ads Ranking Deep Learning Recommendation Model for Personalization and Recommendation Systems

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-09T04:12:56.274426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bce68d11-4411-4bd4-aac5-991d6b575bf0 · outbound

This paper cites doi: https://doi.org/10.1016/j.ins.2023.119838.

Beyond Self-Consistency: Loss-Balanced Perturbation-Based Regularization Improves Industrial-Scale Ads Ranking doi: https://doi.org/10.1016/j.ins.2023.119838

Reference 2024

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-09T04:12:56.639886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

No inbound Pith citation observations are available.