Paper Citation Record · LEDGER

DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning

As of 17 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 0 inbound Pith citation observations for arXiv:2605.13418.

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

pith.paper-citation-record.v1
2605.13418 v1

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-14T19:49:10.067376Z

measured 16 of 16 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

16 of 16 outbound references displayed

verified exact1
verified fuzzy7
unresolved4
parse uncertain0
malformed identifier3
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c5eecee8-8277-448c-8e90-93f39be33bf1 · outbound

This paper cites Goodfellow, H.

DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning Goodfellow, H

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T19:49:23.642363Z

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 d2a50b67-273b-410a-86e7-15c50941d88e · outbound

This paper cites On Design Principles for Private Adaptive Optimizers.

DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning On Design Principles for Private Adaptive Optimizers

Reference 2

Resolution: malformed identifier; arxiv_id, observed 2026-05-14T19:49:25.489440Z

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 9d053373-5a56-45c0-94a6-bcb8c5e6d56f · outbound

This paper cites Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting.

DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting

Reference 3

Resolution: malformed identifier; doi_truncated, observed 2026-05-14T19:49:23.632585Z

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 7e5d6ccc-bb63-41d9-b896-245b129a14c1 · outbound

This paper cites Thakkar, O., Andrew, G., and McMahan, H.

DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning Thakkar, O., Andrew, G., and McMahan, H

Reference 4

Resolution: verified exact; doi, observed 2026-05-14T19:49:23.651737Z

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 a85d8fc5-49f6-4ea8-99aa-40bfd8dd5050 · outbound

This paper cites an unresolved cited work.

DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-05-14T19:49:26.265239Z

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 ec84e33e-ce4f-47aa-bbbf-db9de9841776 · outbound

This paper cites By Assumption A.2, the privacy noise ξt is statistically independent of the gradient estimate¯gt and the fixed preconditionerP t.

DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning By Assumption A.2, the privacy noise ξt is statistically independent of the gradient estimate¯gt and the fixed preconditionerP t

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T19:49:26.261153Z

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 660e67fd-1446-4890-92ad-d1df2c8fbb44 · outbound

This paper cites an unresolved cited work.

DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-05-14T19:49:26.273928Z

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 18baf0b6-8755-4764-9136-50037303a89c · outbound

This paper cites This confirms that the algorithm converges to a stationary point despite the injected privacy noise.

DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning This confirms that the algorithm converges to a stationary point despite the injected privacy noise

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T19:49:26.277997Z

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 2f59db69-878f-49f0-a78c-b54138588ec2 · outbound

This paper cites an unresolved cited work.

DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-05-14T19:49:26.269876Z

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 21b87667-6297-47ac-b21b-4691a979efc9 · outbound

This paper cites We scale the amplitude of the noise by the inverse frequency: ˜Zu =Z u · 1 ∥u∥α/2 2 +ϵ (42) whereϵprevents division by zero at the DC component.

DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning We scale the amplitude of the noise by the inverse frequency: ˜Zu =Z u · 1 ∥u∥α/2 2 +ϵ (42) whereϵprevents division by zero at the DC component

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T19:49:26.237621Z

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 fb3914a9-a61b-4234-b4ec-05f200fd28f3 · outbound

This paper cites an unresolved cited work.

DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-05-14T19:49:26.252514Z

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 69c72459-765b-4ed2-b93a-04a69af9a9db · outbound

This paper cites Algorithm 3 details the implementation.

DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning Algorithm 3 details the implementation

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T19:49:26.232476Z

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 78077843-3622-483c-8349-0c242dbcccc8 · outbound

This paper cites For each synthetic batch, we sample a random active lengthL act ∼ U(L min, Lmax).

DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning For each synthetic batch, we sample a random active lengthL act ∼ U(L min, Lmax)

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T19:49:26.242545Z

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 a9d99bb8-2c0f-4130-8aa3-6469076d20fd · outbound

This paper cites This ensures that when projected through the model’s embedding layer, the inputs activate the lookup table with the correct varianceq 0 =Var(W embed).

DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning This ensures that when projected through the model’s embedding layer, the inputs activate the lookup table with the correct varianceq 0 =Var(W embed)

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T19:49:26.257060Z

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 fd6f2816-0f52-431f-b547-dd679f57ac2d · outbound

This paper cites 19 Data-Free Preconditioning for Private Deep Learning Algorithm 3Synthetic Pink Noise Generator (1/f α) Input:Batch sizeB, ChannelsC, HeightH, WidthW, Decayα(default 1.0).

DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning 19 Data-Free Preconditioning for Private Deep Learning Algorithm 3Synthetic Pink Noise Generator (1/f α) Input:Batch sizeB, ChannelsC, HeightH, WidthW, Decayα(default 1.0)

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T19:49:26.247872Z

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 5ea5a4d8-101e-4bd9-84df-b815853ab5db · outbound

This paper cites Positions i > L act are set to 0 (padded).

DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning Positions i > L act are set to 0 (padded)

Reference 16

Resolution: malformed identifier; raw_fallback, observed 2026-05-14T19:49:26.233134Z

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.