Paper Citation Record · LEDGER

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach

As of 7 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2506.00201.

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

pith.paper-citation-record.v1
2506.00201 v1

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:23:18.130072Z

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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 exact0
verified fuzzy14
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7fa93085-47b0-4bfc-a76f-0e95afe28821 · outbound

This paper cites Goodfellow, H.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach Goodfellow, H

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:20.802375Z

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 f0992954-78bd-4f5b-a9be-79e480050004 · outbound

This paper cites Reconstructing training data with informed adversaries.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach Reconstructing training data with informed adversaries

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:20.601940Z

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 2d42f836-f76a-4141-9e96-ddcff9c109d0 · outbound

This paper cites Protection against reconstruction and its applications in private federated learning, 2019.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach Protection against reconstruction and its applications in private federated learning, 2019

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:20.368097Z

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 2d2cd99f-658b-465d-9a2e-b36213f4fd8e · outbound

This paper cites Private empirical risk minimization: Efficient algorithms and tight error bounds.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach Private empirical risk minimization: Efficient algorithms and tight error bounds

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:20.144541Z

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 615c6b4e-d676-4250-acaf-47a579807328 · outbound

This paper cites On the Use of ArXiv as a Dataset.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach On the Use of ArXiv as a Dataset

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T12:23:16.040012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40b0203c-0be2-4e6a-b650-36b59a1841df · outbound

This paper cites an unresolved cited work.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:23:19.951568Z

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 cdfcacc3-38ed-49a4-8d82-079f7ca63ec2 · outbound

This paper cites Mind the privacy unit! user-level differential privacy for language model fine-tuning.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach Mind the privacy unit! user-level differential privacy for language model fine-tuning

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:19.884934Z

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 07881899-0319-4b96-b202-fdea4fcbec79 · outbound

This paper cites Brendan McMahan, Nicole Mitchell, Krishna Pillutla, and Keith Rush.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach Brendan McMahan, Nicole Mitchell, Krishna Pillutla, and Keith Rush

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T12:23:16.293586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ad3582e-b915-4030-934f-0fc5329bb4e3 · outbound

This paper cites Quantifying memorization across neural language models.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach Quantifying memorization across neural language models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T12:23:16.465263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9219d0c6-e244-4a4b-9aba-5e418cd860fc · outbound

This paper cites Extracting training data from large language models.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach Extracting training data from large language models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T12:23:16.578239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b781f38-b837-4c70-902b-bd6ff34af79a · outbound

This paper cites BERT : Pre-training of deep bidirectional transformers for language understanding.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach BERT : Pre-training of deep bidirectional transformers for language understanding

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:19.752346Z

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 d4e2de4b-ccb3-461e-a40c-5a1df9c037f2 · outbound

This paper cites R2t: Instance-optimal truncation for differentially private query evaluation with foreign keys.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach R2t: Instance-optimal truncation for differentially private query evaluation with foreign keys

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:19.631319Z

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 da5bfb44-152c-4ee4-a3c7-a35db99a56b7 · outbound

This paper cites Calibrating noise to sensitivity in private data analysis.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach Calibrating noise to sensitivity in private data analysis

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:19.509064Z

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 03849e87-b2b9-4159-95e9-9bdb8f390c6b · outbound

This paper cites Google's differential privacy libraries., 2022.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach Google's differential privacy libraries., 2022

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:19.411217Z

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 3dc3d496-3ac2-49a4-85b4-913c27d08585 · outbound

This paper cites It's my data too: Private ml for datasets with multi-user training examples, 2025.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach It's my data too: Private ml for datasets with multi-user training examples, 2025

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T12:23:17.189622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f13ddfd-d10d-442c-bf9e-5c7f7546fafe · outbound

This paper cites Bounding training data reconstruction in DP - SGD.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach Bounding training data reconstruction in DP - SGD

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:19.279865Z

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 e4ca734f-88c7-40df-b168-f01b88a536a3 · outbound

This paper cites Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T12:23:17.454703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 610f935d-7d9f-4507-a6f2-beeb73c72f1d · outbound

This paper cites Conservative or liberal? personalized differential privacy.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach Conservative or liberal? personalized differential privacy

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:18.980338Z

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 be6e8bbe-a6c6-4d80-9612-562ed5597033 · outbound

This paper cites Scalable Extraction of Training Data from (Production) Language Models.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach Scalable Extraction of Training Data from (Production) Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T12:23:17.626720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c45ab347-b745-4216-b0c2-07c14c17028c · outbound

This paper cites The fineweb datasets: Decanting the web for the finest text data at scale, 2024.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach The fineweb datasets: Decanting the web for the finest text data at scale, 2024

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T12:23:17.726823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4584597b-c276-4054-ac51-baf9879ff149 · outbound

This paper cites Stochastic gradient descent with differentially private updates.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach Stochastic gradient descent with differentially private updates

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:18.887926Z

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 ce7b3e87-1c38-492f-9174-4f2e1a1b92b6 · outbound

This paper cites an unresolved cited work.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:23:18.718309Z

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 2e14ec89-9ec6-4945-bd22-af228c20be35 · outbound

This paper cites Individual privacy accounting for differentially private stochastic gradient descent.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach Individual privacy accounting for differentially private stochastic gradient descent

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:18.576318Z

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 bd539190-f018-4a46-9dcf-6f1733163094 · outbound

This paper cites Optimal accounting of differential privacy via characteristic function.

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach Optimal accounting of differential privacy via characteristic function

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:18.404720Z

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.