Paper Citation Record · LEDGER

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks

As of 9 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2603.14830.

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

pith.paper-citation-record.v1
2603.14830 v3

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-14T20:55:11.027028Z

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

24 of 24 outbound references displayed

verified exact3
verified fuzzy0
unresolved18
parse uncertain0
malformed identifier3
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b27e129f-135d-4f49-bef8-fe761d18d523 · outbound

This paper cites Dataset Distillation.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks Dataset Distillation

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-14T20:55:11.027028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c21b861-4da7-4d62-b34a-c78b80bfd7fa · outbound

This paper cites Guang Li, Ren Togo, Takahiro Ogawa, and Miki Haseyama.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks Guang Li, Ren Togo, Takahiro Ogawa, and Miki Haseyama

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-14T20:55:11.027028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be0dbcf7-5f7b-44a6-b6ad-1b355744680e · outbound

This paper cites 2020.9191357.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks 2020.9191357

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-14T20:55:11.027028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04ff2851-ca92-4222-8ee6-671876caafaa · outbound

This paper cites Hanfei Guo, Junhao Xu, Chang Li, Wei Zhao, Hu Peng, Zhihui Han, Yuanguo Wang, and Xun Chen.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks Hanfei Guo, Junhao Xu, Chang Li, Wei Zhao, Hu Peng, Zhihui Han, Yuanguo Wang, and Xun Chen

Reference 4

Resolution: verified exact; doi, observed 2026-07-14T21:00:45.570800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation aa061007-b48d-45f2-a8cd-d6ea85c0d5d8 · outbound

This paper cites Hybrid Memory Replay: Blending Real and Distilled Data for Class Incremental Learning.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks Hybrid Memory Replay: Blending Real and Distilled Data for Class Incremental Learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-14T20:55:11.027028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c6e414a-78fa-4311-8848-e7c584164688 · outbound

This paper cites Distilled One-Shot Federated Learning.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks Distilled One-Shot Federated Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-14T20:55:11.027028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22ced8c0-0803-468b-a80d-ca84ac8c10d7 · outbound

This paper cites A theoretical study of dataset distillation.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks A theoretical study of dataset distillation

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-14T20:55:11.027028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 896afd2f-9748-4978-ae45-399771c3eadc · outbound

This paper cites Provable and efficient dataset distillation for kernel ridge regression.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks Provable and efficient dataset distillation for kernel ridge regression

Reference 8

Resolution: verified exact; doi, observed 2026-07-14T21:00:45.565515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 42ecc9ea-0c65-4fbb-b3ac-c4cdbf0cf2a8 · outbound

This paper cites Timothy Nguyen, Zhourong Chen, and Jaehoon Lee.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks Timothy Nguyen, Zhourong Chen, and Jaehoon Lee

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-07-14T21:00:45.567556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f8a9d480-4683-442d-9c0d-11c907a06238 · outbound

This paper cites Justin Cui, Ruochen Wang, Si Si, and Cho-Jui Hsieh.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks Justin Cui, Ruochen Wang, Si Si, and Cho-Jui Hsieh

Reference 10

Resolution: malformed identifier; no resolver link, observed 2026-07-14T20:55:11.027028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfe539d0-84f2-4625-9161-9cd58fa43007 · outbound

This paper cites Data distillation can be like vodka: Distilling more times for better quality.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks Data distillation can be like vodka: Distilling more times for better quality

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-14T20:55:11.027028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2fe77bd-ae7d-4f94-8e33-d36bf32ef225 · outbound

This paper cites A Precise Performance Analysis of Learning with Random Features.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks A Precise Performance Analysis of Learning with Random Features

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-14T20:55:11.027028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16e48971-a956-4474-8dfc-7d64d201ee96 · outbound

This paper cites On Learning Gaussian Multi-index Models with Gradient Flow.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks On Learning Gaussian Multi-index Models with Gradient Flow

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-14T20:55:11.027028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18ebb3ba-18fe-4eb2-8cc3-b44bf3d64cf8 · outbound

This paper cites an unresolved cited work.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks Unresolved cited work

Reference 14

Resolution: malformed identifier; no resolver link, observed 2026-07-14T20:55:11.027028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b056dbea-9e0a-4075-a63e-d683980ea4f8 · outbound

This paper cites an unresolved cited work.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-14T20:55:11.027028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9afb0223-b062-40b8-b7ca-ecd26194d275 · outbound

This paper cites Moreover, in Appendix C, we will treat a well-defined update for ReLU, which will also lead to similar result shown in this appendix.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks Moreover, in Appendix C, we will treat a well-defined update for ReLU, which will also lead to similar result shown in this appendix

Reference 16

Resolution: malformed identifier; no resolver link, observed 2026-07-14T20:55:11.027028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fb3343c-60cb-4498-99be-90e224843a03 · outbound

This paper cites We define the first term of the right hand side as∆1,1 and the second as∆ 1,2.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks We define the first term of the right hand side as∆1,1 and the second as∆ 1,2

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-14T20:55:11.027028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5022e286-099e-4e4f-98db-40afc452c362 · outbound

This paper cites (2022), we know that with high probability, sup w∈S�� 1 N � n ˆf ∗(xn)xnσ′(�wj, xn�)�� x � ˆf ∗(x)xσ′(�wj, x�) �� = ˜O � � d N �.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks (2022), we know that with high probability, sup w∈S�� 1 N � n ˆf ∗(xn)xnσ′(�wj, xn�)�� x � ˆf ∗(x)xσ′(�wj, x�) �� = ˜O � � d N �

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-14T20:55:11.027028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e51990a8-a899-40d6-aa16-ec2efc7ab540 · outbound

This paper cites Finally, we can prove Theorem B.4.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks Finally, we can prove Theorem B.4

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-14T20:55:11.027028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5ea51dc-0678-4e5f-a7ca-fc341ffb9e6f · outbound

This paper cites B.5.2 Proof of Theorem B.29 Lemma B.30(Lemma 23 from Nishikawa et al.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks B.5.2 Proof of Theorem B.29 Lemma B.30(Lemma 23 from Nishikawa et al

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-14T20:55:11.027028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30eaab3d-f9df-4d75-806c-9c7b27f83a9e · outbound

This paper cites We will first evaluate conditions onηR 1 , ηD 1 , N and J ∗ =LJ/2 to satisfy conditions P= ˜Θ(1) and c(x) =o d(Plog −2p+2 d) of Lemma B.30.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks We will first evaluate conditions onηR 1 , ηD 1 , N and J ∗ =LJ/2 to satisfy conditions P= ˜Θ(1) and c(x) =o d(Plog −2p+2 d) of Lemma B.30

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-14T20:55:11.027028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2137dd36-ba94-4d68-828a-7920a5c637a6 · outbound

This paper cites Moreover, �β, w�=st+ � 1�t 2�β⊥, v�, where s=�β,˜x� , and β⊥ =β� �β,˜x�˜x.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks Moreover, �β, w�=st+ � 1�t 2�β⊥, v�, where s=�β,˜x� , and β⊥ =β� �β,˜x�˜x

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-14T20:55:11.027028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d644c653-8264-48cb-bcef-fbd9fde30400 · outbound

This paper cites Let us now move on to proving our main statements.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks Let us now move on to proving our main statements

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-14T20:55:11.027028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c791ff7-0f30-4b25-9482-d4d7980638c1 · outbound

This paper cites (2022) to analyze the behavior of DD and show that the resulting distilled data provide high generalization performance at retraining.

Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks (2022) to analyze the behavior of DD and show that the resulting distilled data provide high generalization performance at retraining

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-14T20:55:11.027028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.