Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-06T17:35:00.594186Z
Paper Citation Record · LEDGER
On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance
As of 7 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2507.10536.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
18 of 18 outbound references displayed
- verified exact2
- verified fuzzy2
- unresolved12
- parse uncertain0
- malformed identifier2
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation a992f701-8020-40dc-8b91-8857adb02f3c · outbound
This paper cites Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang.
On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T17:35:00.416500Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2e934b2d-0e85-4b31-9c3f-849976e802b3 · outbound
This paper cites Scalable sec- ond order optimization for deep learning, 2021.
On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance Scalable sec- ond order optimization for deep learning, 2021
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T17:35:00.808225Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 77948df8-f2ae-4a6a-9eeb-3f0a4ab7d5c2 · outbound
This paper cites Extracting Training Data from Large Language Models.
On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance Extracting Training Data from Large Language Models
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T17:35:00.426132Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1c2f29fd-3204-4f81-b0f3-ed1ae42bbcf6 · outbound
This paper cites Adaptive subgradient methods for online learning and stochastic optimization.
On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance Adaptive subgradient methods for online learning and stochastic optimization
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T17:35:00.801586Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 9591ba3a-046d-4fdd-989b-9782a552fd3e · outbound
This paper cites LoRA: Low-Rank Adaptation of Large Language Models.
On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance LoRA: Low-Rank Adaptation of Large Language Models
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T17:35:00.468978Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1ad4f1b9-5674-4d76-91bc-8bebd22b79a5 · outbound
This paper cites Adam: A Method for Stochastic Optimization.
On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance Adam: A Method for Stochastic Optimization
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T17:35:00.483545Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c0083046-e54e-499b-8941-7fc4662516be · outbound
This paper cites Noise Is Not the Main Factor Behind the Gap Between SGD and Adam on Transformers, but Sign Descent Might Be.
On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance Noise Is Not the Main Factor Behind the Gap Between SGD and Adam on Transformers, but Sign Descent Might Be
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T17:35:00.502564Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 804db7b2-bcdb-4899-85ca-a5638c30b740 · outbound
This paper cites Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models.
On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T17:35:00.523005Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6f731f1d-530c-464c-84b5-096da2279561 · outbound
This paper cites Understanding the Difficulty of Training Transformers.
On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance Understanding the Difficulty of Training Transformers
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T17:35:00.542162Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d774b2d5-52cb-424f-847d-609911d2e59c · outbound
This paper cites Optimizing Neural Networks with Kronecker-factored Approximate Curvature.
On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance Optimizing Neural Networks with Kronecker-factored Approximate Curvature
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T17:35:00.556327Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 120019b7-ce92-47c9-9947-8df7d4ec3ba9 · outbound
This paper cites Memorization in NLP Fine-tuning Methods.
On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance Memorization in NLP Fine-tuning Methods
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T17:35:00.577638Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7d3e614e-c18c-4e5c-ba14-080fc4a61c8b · outbound
This paper cites The E2E Dataset: New Challenges For End-to-End Generation.
On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance The E2E Dataset: New Challenges For End-to-End Generation
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T17:35:00.580123Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 49d4fa1a-4059-4975-ba31-c28d13c79a9f · outbound
This paper cites Does fine-tuning GPT-3 with the OpenAI API leak personally-identifiable information?.
On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance Does fine-tuning GPT-3 with the OpenAI API leak personally-identifiable information?
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T17:35:00.582631Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 54e0f782-48ec-430a-818a-6795c9ddcde4 · outbound
This paper cites DP-AdamBC: Your DP-Adam Is Actually DP-SGD (Unless You Apply Bias Correction).
On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance DP-AdamBC: Your DP-Adam Is Actually DP-SGD (Unless You Apply Bias Correction)
Reference 14
- Resolution
- verified exact
- local_arxiv, observed 2026-08-06T17:35:00.639766Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation d2d3ba6f-77b1-4448-bdb3-b3e4e9eeb817 · outbound
This paper cites Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods.
On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods
Reference 15
- Resolution
- verified exact
- local_arxiv, observed 2026-08-06T17:35:00.630475Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation db00a1ec-2ecd-4c95-a287-a58f604edc16 · outbound
This paper cites Differentially Private Fine-tuning of Language Models.
On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance Differentially Private Fine-tuning of Language Models
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T17:35:00.589460Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0351a6d9-9cd4-48a8-8d70-89e37877fdaf · outbound
This paper cites Why are Adaptive Methods Good for Attention Models?.
On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance Why are Adaptive Methods Good for Attention Models?
Reference 17
- Resolution
- malformed identifier
- no resolver link, observed 2026-08-06T17:35:00.591858Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 06846fe7-9227-4269-b8c9-42b55fc3c2ec · outbound
This paper cites an unresolved cited work.
On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance Unresolved cited work
Reference 18
- Resolution
- malformed identifier
- raw_fallback, observed 2026-08-06T17:35:00.794589Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Pith citing papers
No inbound Pith citation observations are available.