Paper Citation Record · LEDGER

Auditing of Unlearning Algorithms

As of 10 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 0 inbound Pith citation observations for arXiv:2607.05898.

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

pith.paper-citation-record.v1
2607.05898 v1

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-08T21:30:38.122700Z

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+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

25 of 25 outbound references displayed

verified exact6
verified fuzzy9
unresolved2
parse uncertain0
malformed identifier1
metadata mismatch7

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 51d84c9a-b55c-4388-8fc6-29df2f2d9350 · outbound

This paper cites Local Differential Privacy: a tutorial.

Auditing of Unlearning Algorithms Local Differential Privacy: a tutorial

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-07-08T21:35:37.712222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a907bc4a-aa16-4537-87c6-6c393d2134b8 · outbound

This paper cites Membership Inference Attacks From First Principles.

Auditing of Unlearning Algorithms Membership Inference Attacks From First Principles

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-07-08T21:35:37.694884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c5a9d605-cd33-427b-9a56-2aa9b1483387 · outbound

This paper cites unbounded.

Auditing of Unlearning Algorithms unbounded

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-07-08T21:35:37.602530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 26aa60c6-66ce-4275-a01c-f91204987c88 · outbound

This paper cites Cheng, P.

Auditing of Unlearning Algorithms Cheng, P

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-07-08T21:35:37.705041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 128c9eb7-6256-438c-abf3-20c8badb4f60 · outbound

This paper cites 2014.The Algorithmic Foundations of Differential Privacy.

Auditing of Unlearning Algorithms 2014.The Algorithmic Foundations of Differential Privacy

Reference 6

Resolution: metadata mismatch; doi, observed 2026-07-08T21:35:37.605782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d5dc7cbd-7d25-4a08-a467-b036f3cea758 · outbound

This paper cites On the Necessity of Output Distribution Reweighting for Effective Class Unlearning.

Auditing of Unlearning Algorithms On the Necessity of Output Distribution Reweighting for Effective Class Unlearning

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-14T01:19:53.864690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 86cf1d17-a777-42ea-8a1d-3e6d21ba8b78 · outbound

This paper cites Certified Unlearning for Neural Networks.

Auditing of Unlearning Algorithms Certified Unlearning for Neural Networks

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-07-08T21:35:37.709904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 33f20d46-06a6-46d0-b2f5-04a878ba87c8 · outbound

This paper cites Milad Nasr, Shuang Song, Abhradeep Thakurta, Nicolas Papernot, and Nicholas Carlini.

Auditing of Unlearning Algorithms Milad Nasr, Shuang Song, Abhradeep Thakurta, Nicolas Papernot, and Nicholas Carlini

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-07-08T21:35:37.717399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 56adf3c5-d326-49a3-8b29-111313616d2f · outbound

This paper cites Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning.

Auditing of Unlearning Algorithms Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning

Reference 10

Resolution: metadata mismatch; local_arxiv, observed 2026-07-08T21:35:37.699950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9a68df50-837d-4478-807a-8f9e447ef829 · outbound

This paper cites Membership Inference Attacks against Machine Learning Models.

Auditing of Unlearning Algorithms Membership Inference Attacks against Machine Learning Models

Reference 12

Resolution: metadata mismatch; local_arxiv, observed 2026-07-08T21:35:37.702290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5d245d98-8f8e-4cfd-ab5c-4dcea7514038 · outbound

This paper cites Privacy Auditing with One (1) Training Run.

Auditing of Unlearning Algorithms Privacy Auditing with One (1) Training Run

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-07-08T21:35:37.714555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3f848e8a-71fa-4170-bbb9-bf0a39558a93 · outbound

This paper cites URL https://doi.org/ 10.1198/jasa.2009.tm08651.

Auditing of Unlearning Algorithms URL https://doi.org/ 10.1198/jasa.2009.tm08651

Reference 14

Resolution: verified exact; doi, observed 2026-07-08T21:35:37.604080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 24efbdc3-53e3-4518-bc9c-7163d59e9074 · outbound

This paper cites Towards Certified Unlearning for Deep Neural Networks.

Auditing of Unlearning Algorithms Towards Certified Unlearning for Deep Neural Networks

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-08T21:35:37.697381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c5f0fd6e-4ae8-458a-ad0f-8f22b14c0f6e · outbound

This paper cites an unresolved cited work.

Auditing of Unlearning Algorithms Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-07-08T21:35:38.010587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b4fe7a65-1f8c-4b44-9623-c41fd7251d33 · outbound

This paper cites 16 Define the upper tailP ε(v) :=Pr u=v πε(u).

Auditing of Unlearning Algorithms 16 Define the upper tailP ε(v) :=Pr u=v πε(u)

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T21:35:37.997811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3e1387e8-31fd-43bf-a9b7-f2c3d7176e6f · outbound

This paper cites From the training portion, we designate 10% of the points as the forget set Df (4,500 points), and use the remaining 40,500 points as the retain set Dr.

Auditing of Unlearning Algorithms From the training portion, we designate 10% of the points as the forget set Df (4,500 points), and use the remaining 40,500 points as the retain set Dr

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T21:35:38.003362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5df96742-13ed-4e7c-a615-03d6c8405cfc · outbound

This paper cites A discussion of why this split between auditor instantiations is appropriate is given in Section F.4, with a more detailed study in Section F.

Auditing of Unlearning Algorithms A discussion of why this split between auditor instantiations is appropriate is given in Section F.4, with a more detailed study in Section F

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T21:35:37.994131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1054eea2-faf3-4b97-add4-439cc9336e31 · outbound

This paper cites The retain samples and sampled forget samples are then pooled and shuffled to form the training dataset.

Auditing of Unlearning Algorithms The retain samples and sampled forget samples are then pooled and shuffled to form the training dataset

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T21:35:37.995965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 90a972a5-c78f-4147-a676-0d2c377a77c6 · outbound

This paper cites Model.The model is a 2-layer stacked character-level LSTM following McMahan et al.

Auditing of Unlearning Algorithms Model.The model is a 2-layer stacked character-level LSTM following McMahan et al

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T21:35:37.999598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c3ac2bda-97ba-4eb4-81c1-ed8e025befc5 · outbound

This paper cites further, however, perfect overlap becomes harder to attain — the auditor is forced to commit to low-confidence batches, which dilute the overlap score and pull the bound back down.

Auditing of Unlearning Algorithms further, however, perfect overlap becomes harder to attain — the auditor is forced to commit to low-confidence batches, which dilute the overlap score and pull the bound back down

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T21:35:38.001474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e94e4c6e-de47-47ef-b333-43582c009d95 · outbound

This paper cites an unresolved cited work.

Auditing of Unlearning Algorithms Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-07-08T21:35:38.008879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ce264f85-26dd-4518-8deb-536b96c89ca1 · outbound

This paper cites To obtain tighter bounds in this regime we use L= 500 runs.

Auditing of Unlearning Algorithms To obtain tighter bounds in this regime we use L= 500 runs

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T21:35:37.992203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d1f436f0-0172-410f-8366-3d1e54d28f09 · outbound

This paper cites Shakespeare.We vary q∈ {1,2,4} , Ef ∈ {5,7} , and λ∈ {0.5,1.0,1.5}.

Auditing of Unlearning Algorithms Shakespeare.We vary q∈ {1,2,4} , Ef ∈ {5,7} , and λ∈ {0.5,1.0,1.5}

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T21:35:38.005246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1d8998bf-03f0-47a4-8a92-7daf7cc2df04 · outbound

This paper cites an unresolved cited work.

Auditing of Unlearning Algorithms Unresolved cited work

Reference 26

Resolution: malformed identifier; raw_fallback, observed 2026-07-08T21:35:38.007058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6bc596f3-f53e-4de5-a9ed-c626fb16afc8 · outbound

This paper cites [2021]); this is because the norm bound (∆) used for the addition of Gaussian noise is closer to what is actually attained empirically.

Auditing of Unlearning Algorithms [2021]); this is because the norm bound (∆) used for the addition of Gaussian noise is closer to what is actually attained empirically

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T21:35:38.012459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

No inbound Pith citation observations are available.