Paper Citation Record · LEDGER

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees

As of 11 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2605.20521.

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

pith.paper-citation-record.v1
2605.20521 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-21T07:06:34.274842Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+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

33 of 33 outbound references displayed

verified exact6
verified fuzzy22
unresolved1
parse uncertain0
malformed identifier1
metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fe3f90e4-eb02-49e4-8fd6-98255ca17107 · outbound

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

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Calibrating noise to sensitivity in private data analysis

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:09:47.165138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 7fcbd85f-dcc4-4b39-a348-890e511ac7c2 · outbound

This paper cites Differential privacy: A survey of results.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Differential privacy: A survey of results

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:09:47.159473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 036a037a-ea06-4578-9953-8f3db89037fa · outbound

This paper cites Differentially private empir- ical risk minimization with input perturbation.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Differentially private empir- ical risk minimization with input perturbation

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:09:47.161287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b6c41b2c-0cf1-45eb-a399-150419429f6a · outbound

This paper cites Certified robustness to adversarial examples with differential privacy.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Certified robustness to adversarial examples with differential privacy

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:09:47.169449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d6086493-11f4-446b-a953-c79ff3af7d69 · outbound

This paper cites Heterogeneous gaussian mechanism: Preserving differential privacy in deep learning with provable robustness.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Heterogeneous gaussian mechanism: Preserving differential privacy in deep learning with provable robustness

Reference 5

Resolution: verified exact; doi, observed 2026-05-21T07:09:46.162982Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 738513bf-1e38-412f-b9c5-831c575ec2ed · outbound

This paper cites Differential privacy preservation for deep auto-encoders: an application of human behavior prediction.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Differential privacy preservation for deep auto-encoders: an application of human behavior prediction

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:09:47.150444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 56585f6b-0587-4280-b0b7-4d19441f0178 · outbound

This paper cites Preserving differential privacy in convolutional deep belief networks.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Preserving differential privacy in convolutional deep belief networks

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:09:47.152227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 5311b344-87b9-469a-bedd-a3e9696efb95 · outbound

This paper cites Adaptive laplace mechanism: Differential privacy preservation in deep learning.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Adaptive laplace mechanism: Differential privacy preservation in deep learning

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:09:47.153956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 4271d88c-fe1b-4017-a0ca-fee123d50056 · outbound

This paper cites Towards practical differentially private convex optimization.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Towards practical differentially private convex optimization

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:09:47.148537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 7f9339b1-662d-4cc6-b147-89d11d54fcd9 · outbound

This paper cites Goodfellow, H.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Goodfellow, H

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T07:09:46.160060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 88c5ed19-eea1-409e-bca1-010e9c3db4d6 · outbound

This paper cites Concentrated differentially private gradient descent with adaptive per-iteration privacy budget.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Concentrated differentially private gradient descent with adaptive per-iteration privacy budget

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T07:09:46.167514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 51d4e67e-1fe0-4d56-84c3-a38fcfe76d50 · outbound

This paper cites Do not let privacy overbill utility: Gradient embedding perturbation for private learning.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Do not let privacy overbill utility: Gradient embedding perturbation for private learning

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:09:47.157683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation fcf0b2be-5dc9-4262-983b-af8eeaca315f · outbound

This paper cites Medical imaging deep learning with differential privacy.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Medical imaging deep learning with differential privacy

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:09:47.144696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation bd6f8966-0b75-4c77-8ec0-8b05da552bcf · outbound

This paper cites Differential privacy for deep learning in medicine.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Differential privacy for deep learning in medicine

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-21T07:09:46.329969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ec9ac697-feb0-4b66-8665-a38159d03f23 · outbound

This paper cites Analysis of application examples of dif- ferential privacy in deep learning.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Analysis of application examples of dif- ferential privacy in deep learning

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:09:47.142856Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b41b09b4-7ce1-4997-9b31-ae876e93253d · outbound

This paper cites Mechanism design via differential privacy.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Mechanism design via differential privacy

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:09:47.141028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 14cd9299-b38c-4897-ac63-337da6dbc077 · outbound

This paper cites Data mining with differential privacy.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Data mining with differential privacy

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-21T07:09:46.171259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation f2f545cb-c953-40a1-b03e-65a104a2deae · outbound

This paper cites Kapralov and K.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Kapralov and K

Reference 18

Resolution: verified exact; doi, observed 2026-05-21T07:09:46.155848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a97ec3e1-6aab-4c41-8cce-93d43c259f44 · outbound

This paper cites Differentially private hierarchical count-of-counts histograms.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Differentially private hierarchical count-of-counts histograms

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T07:09:46.152735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a7e4a62a-9b7b-4c61-841e-49d7e80d7eed · outbound

This paper cites Differential privacy without sensitivity.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Differential privacy without sensitivity

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:09:47.134580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 63b685f3-2dc1-4d7f-ae23-4c219b206b25 · outbound

This paper cites Are normalizing flows the key to unlocking the exponential mechanism? a path through the accuracy-privacy ceiling constraining differentially private ml.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Are normalizing flows the key to unlocking the exponential mechanism? a path through the accuracy-privacy ceiling constraining differentially private ml

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:09:47.136621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 9782cf85-6ccc-4af2-aae2-1a55f1f28edc · outbound

This paper cites The algorithmic foundations of differential privacy.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees The algorithmic foundations of differential privacy

Reference 22

Resolution: malformed identifier; raw_fallback, observed 2026-05-21T07:09:47.132742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation cb67307a-a333-4194-9814-6d1052e6beae · outbound

This paper cites How to dp-fy ml: A practical tutorial to machine learning with differential privacy.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees How to dp-fy ml: A practical tutorial to machine learning with differential privacy

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-21T07:09:46.148156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 23578c6f-a480-477f-8674-e1536ec32baa · outbound

This paper cites Opacus: User-Friendly Differential Privacy Library in PyTorch.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Opacus: User-Friendly Differential Privacy Library in PyTorch

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-21T07:09:46.326541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 07a2dcc3-715e-4062-9ccc-dcb80530c7ec · outbound

This paper cites Model-agnostic meta-learning for fast adaptation of deep networks.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Model-agnostic meta-learning for fast adaptation of deep networks

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:09:47.131011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 5588f9d5-abaf-4c19-b816-a63122271055 · outbound

This paper cites Gradient-based learning applied to document recognition.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Gradient-based learning applied to document recognition

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:09:47.139032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0ae2dd6c-5f65-40b5-85d4-89b96d399b57 · outbound

This paper cites The eicu collaborative research database, a freely available multi-center database for critical care research.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees The eicu collaborative research database, a freely available multi-center database for critical care research

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:09:47.146711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 7cdf2d71-d96e-43ae-a361-6beeabb7ffa0 · outbound

This paper cites Mimic-iv, a freely accessible electronic health record dataset.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Mimic-iv, a freely accessible electronic health record dataset

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:09:47.155870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 135cc581-21ee-4abd-94cf-cc3018ed521b · outbound

This paper cites Introducing the blendedicu dataset, the first harmonized, international intensive care dataset.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Introducing the blendedicu dataset, the first harmonized, international intensive care dataset

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:09:47.163284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b7bcce44-7202-45a1-bf3f-209d0f29d3ae · outbound

This paper cites An Extensive Data Processing Pipeline for MIMIC-IV.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees An Extensive Data Processing Pipeline for MIMIC-IV

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:09:47.166987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 653b0688-2dee-4edd-a3cb-07b27045fa12 · outbound

This paper cites an unresolved cited work.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-05-21T07:09:47.124752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d439d0a0-11de-47c7-b703-022fa7c7a60b · outbound

This paper cites His research interests include compressed sensing, machine learning, high-dimensional approximations and numerical solution of partial differential equations.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees His research interests include compressed sensing, machine learning, high-dimensional approximations and numerical solution of partial differential equations

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:09:47.126826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 903bb997-5274-4dc9-8871-cedb9f383eff · outbound

This paper cites Her research interests include federated learning, differential privacy, synthetic data generation, and distributed optimization.

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees Her research interests include federated learning, differential privacy, synthetic data generation, and distributed optimization

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T07:09:47.129008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Pith citing papers

No inbound Pith citation observations are available.