Paper Citation Record · LEDGER

Optimizing Canaries for Privacy Auditing with Metagradient Descent

As of 21 August 2026, this Paper Citation Record lists 10 of 10 outbound references and 1 inbound Pith citation observation for arXiv:2507.15836.

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

pith.paper-citation-record.v1
2507.15836 v1

Coverage vector

measured 10 of 10 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T15:29:28.738932Z

measured 11 of 11 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T11:15:48.105239Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

10 of 10 outbound references displayed

verified exact0
verified fuzzy5
unresolved5
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b602389f-9112-4be8-90fd-936e484f9513 · outbound

This paper cites Deep learning with differential privacy.

Optimizing Canaries for Privacy Auditing with Metagradient Descent Deep learning with differential privacy

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:29:29.088745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7032a4e7-3775-4b01-96cb-e272d7c9a12c · outbound

This paper cites Stabilizing differentiable architecture search via perturbation- based regularization.

Optimizing Canaries for Privacy Auditing with Metagradient Descent Stabilizing differentiable architecture search via perturbation- based regularization

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:29:29.077671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0a691785-1193-4fda-8188-6bb5e43365d2 · outbound

This paper cites Tight auditing of differentially private machine learning.

Optimizing Canaries for Privacy Auditing with Metagradient Descent Tight auditing of differentially private machine learning

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:29:29.066893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation eec48a3f-a3de-4567-be3f-031c0450e9bf · outbound

This paper cites Adversary instantiation: Lower bounds for differentially private machine learning.

Optimizing Canaries for Privacy Auditing with Metagradient Descent Adversary instantiation: Lower bounds for differentially private machine learning

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:29:29.056156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ef1cda07-1e42-4bbe-a839-f154d62acca1 · outbound

This paper cites Meta-learning with implicit gradients.

Optimizing Canaries for Privacy Auditing with Metagradient Descent Meta-learning with implicit gradients

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:29:29.044630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4fe010f6-33d6-48e1-9f52-bc4aa994893c · outbound

This paper cites Forward and reverse gradient-based hyperparameter optimization.

Optimizing Canaries for Privacy Auditing with Metagradient Descent Forward and reverse gradient-based hyperparameter optimization

Reference 1135

Resolution: unresolved; no resolver link, observed 2026-08-06T15:29:28.720329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b05eb3d5-bd76-40df-a0df-b8a017f1cfaf · outbound

This paper cites Unlocking High-Accuracy Differentially Private Image Classification through Scale.

Optimizing Canaries for Privacy Auditing with Metagradient Descent Unlocking High-Accuracy Differentially Private Image Classification through Scale

Reference 1565

Resolution: unresolved; no resolver link, observed 2026-08-06T15:29:28.717014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4f19330-916e-4e04-8213-b2882dff0a6c · outbound

This paper cites Debugging Differential Privacy: A Case Study for Privacy Auditing.

Optimizing Canaries for Privacy Auditing with Metagradient Descent Debugging Differential Privacy: A Case Study for Privacy Auditing

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-06T15:29:28.738932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d17410b7-4dab-4440-b8f9-814a336b687f · outbound

This paper cites It’s Our Loss: No Privacy Amplification for Hidden State DP-SGD With Non-Convex Loss.

Optimizing Canaries for Privacy Auditing with Metagradient Descent It’s Our Loss: No Privacy Amplification for Hidden State DP-SGD With Non-Convex Loss

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-06T15:29:28.724806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 114a5357-67f0-428f-9ee0-59373ce2d18b · outbound

This paper cites Gradient-based optimization of hyperparameters.

Optimizing Canaries for Privacy Auditing with Metagradient Descent Gradient-based optimization of hyperparameters

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-06T15:29:28.710418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation e9cf0070-7f81-46f4-843c-fe04624f8457 · inbound

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data cites this paper.

Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Optimizing Canaries for Privacy Auditing with Metagradient Descent

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T11:15:48.105239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.