Pith. sign in

Paper Citation Record · LEDGER

Leveraging Per-Instance Privacy for Machine Unlearning

As of 8 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 0 inbound Pith citation observations for arXiv:2505.18786.

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

pith.paper-citation-record.v1
2505.18786 v1

Coverage vector

measured 23 of 23 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:29:50.166277Z

measured 23 of 23 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

23 of 23 outbound references displayed

  • verified exact1
  • verified fuzzy6
  • unresolved15
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bd3088b7-8dd0-4189-a3c5-5443564621a1 · outbound

This paper cites Cooper, A.

Leveraging Per-Instance Privacy for Machine Unlearning Cooper, A

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-07T14:29:48.729950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:29:48.729950Z digest=sha256:83be2b4eefef286b265cdd9806ebc8121674077931b258a3551e208fa871bbc5

Observation 07fd7e7e-5df8-4c91-92a1-390ab4908f6f · outbound

This paper cites This was despite these forget sets leading to consistent differences in the number of steps to unlearn.

Leveraging Per-Instance Privacy for Machine Unlearning This was despite these forget sets leading to consistent differences in the number of steps to unlearn

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:51.537054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T14:29:49.752704Z digest=sha256:f78f05a345d2c8c763cd5c3af5499ae53e1d67141d2d3c231482059ba2a0117f

Observation c6ed03f9-358a-4894-af0c-a9625f1587e2 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

Leveraging Per-Instance Privacy for Machine Unlearning An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-07T14:29:48.861255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:29:48.861255Z digest=sha256:5e497df6e59754a7c4466dfef22fc5fc96d6c3dcd94df17a70b4099a839e7a3e

Observation 806f4148-256a-4a8f-bc23-8c1e71894a28 · outbound

This paper cites an unresolved cited work.

Leveraging Per-Instance Privacy for Machine Unlearning Unresolved cited work

Reference 6

Resolution
unresolved
raw_fallback, observed 2026-08-07T14:29:50.990187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T14:29:50.028020Z digest=sha256:b59bd6e14aac30827626bc4431cb0b8438901dfe4d8939f0414958279be91d1b

Observation 63fbea36-b84c-4996-9ac9-55698a515267 · outbound

This paper cites Unlearning time vs.

Leveraging Per-Instance Privacy for Machine Unlearning Unlearning time vs

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:50.863261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T14:29:50.108841Z digest=sha256:686ec62854806c89e02f018410afdfb3a86eabe2d13837ee50368c788719d556

Observation 6a0d760c-6bb4-4caa-a031-24d1afbfcd25 · outbound

This paper cites Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy.

Leveraging Per-Instance Privacy for Machine Unlearning Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-07T14:29:49.140311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:29:49.140311Z digest=sha256:332fceb94385a00580adbaca5d72a526146687e19dc692d764da8c10f148eb5f

Observation 01b9509a-f867-4e35-91a2-bdf6efdd56bd · outbound

This paper cites Dataset Difficulty and the Role of Inductive Bias.

Leveraging Per-Instance Privacy for Machine Unlearning Dataset Difficulty and the Role of Inductive Bias

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-07T14:29:49.260633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:29:49.260633Z digest=sha256:0f8c488be5c9166bc11a621b800e1660642e1c999180ee22c9b3c591c5c1ee9f

Observation 1352092c-0a8a-43b8-958b-d6f12e85e2f0 · outbound

This paper cites Threats, Attacks, and Defenses in Machine Unlearning: A Survey.

Leveraging Per-Instance Privacy for Machine Unlearning Threats, Attacks, and Defenses in Machine Unlearning: A Survey

Reference 11

Resolution
verified exact
local_arxiv, observed 2026-08-07T14:29:50.494008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T14:29:49.360552Z digest=sha256:9f2d3aace63e0f9390b43938395b8bf3c2c7d0b4918aab31d2903386851089b9

Observation 4cbbe146-eb18-435a-84c0-a84fd83677b8 · outbound

This paper cites an unresolved cited work.

Leveraging Per-Instance Privacy for Machine Unlearning Unresolved cited work

Reference 12

Resolution
unresolved
raw_fallback, observed 2026-08-07T14:29:51.783903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T14:29:49.424521Z digest=sha256:9c6a1dca4c93380fa4595ffaf1c9e216b595a2afa54e51650391518985b7ca3a

Observation 0a7bbf92-ca70-4545-9de5-55ba05917adc · outbound

This paper cites Z., Lu, Y ., Kamath, G., Sekhari, A., and Neel, S.

Leveraging Per-Instance Privacy for Machine Unlearning Z., Lu, Y ., Kamath, G., Sekhari, A., and Neel, S

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-07T14:29:49.562404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:29:49.562404Z digest=sha256:c1b90692c6ad6c44eff05e9b5474d3fc13d47b06f4e6d6ee1e543c02204caee2

Observation fcfe9af2-08d1-46d8-98ad-eed4679a042b · outbound

This paper cites an unresolved cited work.

Leveraging Per-Instance Privacy for Machine Unlearning Unresolved cited work

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-07T14:29:49.627127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:29:49.627127Z digest=sha256:0c9c4a6acd751f3369f488967f4a7a9500a54e9d4608bf21126fb4eaebb11958

Observation f1fc78b0-d606-427d-bbb8-c3d6df887051 · outbound

This paper cites Scalability of memorization-based machine unlearning.

Leveraging Per-Instance Privacy for Machine Unlearning Scalability of memorization-based machine unlearning

Reference 16

Resolution
metadata mismatch
local_arxiv, observed 2026-08-07T14:29:50.326665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T14:29:49.682059Z digest=sha256:e79026e8983d8fd9cfe847eb0b31652e8473989908b0606b0d55c33cf77f6adc

Observation 45f8379b-1825-4688-a586-f82b6c91bc0d · outbound

This paper cites The x-axis represents the number of epochs.

Leveraging Per-Instance Privacy for Machine Unlearning The x-axis represents the number of epochs

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:51.424659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T14:29:49.842011Z digest=sha256:2c7653cde6565889cefee87239f499a4556798c09fa916f08f85bf4bd2c1eaaf

Observation 81129e1d-5665-4bf3-a770-208981f5223e · outbound

This paper cites an unresolved cited work.

Leveraging Per-Instance Privacy for Machine Unlearning Unresolved cited work

Reference 19

Resolution
unresolved
raw_fallback, observed 2026-08-07T14:29:51.280633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T14:29:49.902512Z digest=sha256:6556a7e330968d222c8f78e042011432bf103e5f3517f96b5a33c2fdaaa7a335

Observation 2a41ab00-8e2d-4bfc-80ce-00978d7bee1d · outbound

This paper cites We report the mean over 20 estimates (given the stochasticity in our estimates for the per-step terms ln Gt,α(D, D′, w)) and shaded in one standard deviation.

Leveraging Per-Instance Privacy for Machine Unlearning We report the mean over 20 estimates (given the stochasticity in our estimates for the per-step terms ln Gt,α(D, D′, w)) and shaded in one standard deviation

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:51.133534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T14:29:49.950124Z digest=sha256:7e28aad0a04c50346a3124022839299c9215d77bc4023c8519b3598fccaa7912

Observation 80a08c25-cb59-40bf-bd41-91158c1beedb · outbound

This paper cites Unlearning time is reported as the number of training steps required to achieve a UA error within 5%.

Leveraging Per-Instance Privacy for Machine Unlearning Unlearning time is reported as the number of training steps required to achieve a UA error within 5%

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:50.759566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T14:29:50.166277Z digest=sha256:8b130473913ce616170d26c37cf54b6770a46d85887f642d820a8fb5e4d6bbf7

Observation 53945f0a-8582-4e0d-b19d-20b8dceaabc5 · outbound

This paper cites Unlearning in- vs. out-of-distribution data in LLMs under gradient-based method.

Leveraging Per-Instance Privacy for Machine Unlearning Unlearning in- vs. out-of-distribution data in LLMs under gradient-based method

Reference 2009

Resolution
unresolved
no resolver link, observed 2026-08-07T14:29:48.561222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:29:48.561222Z digest=sha256:b64cc1a7144760c2d5c4b3494a6490dee3774e8feba5dbcc45d0b35930954b8d

Observation 07fad513-a354-45bb-b525-dc59e1b8ce1c · outbound

This paper cites Towards Adversarial Evaluations for Inexact Machine Unlearning.

Leveraging Per-Instance Privacy for Machine Unlearning Towards Adversarial Evaluations for Inexact Machine Unlearning

Reference 2019

Resolution
unresolved
no resolver link, observed 2026-08-07T14:29:49.062968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:29:49.062968Z digest=sha256:9504c6025da1d007dae4ae1d41fe588f434f804807c2068eba52ca3f8562bd5d

Observation 65722495-2614-4feb-bf56-cee0196905b2 · outbound

This paper cites Do Unlearning Methods Remove Information from Language Model Weights?.

Leveraging Per-Instance Privacy for Machine Unlearning Do Unlearning Methods Remove Information from Language Model Weights?

Reference 2020

Resolution
unresolved
no resolver link, observed 2026-08-07T14:29:48.810330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:29:48.810330Z digest=sha256:0cf7ee8883001cf763a144d693dd49d43b5872de6ab00ef28cc34a4e0c5927e9

Observation be25e5b7-3ab7-44e5-80aa-f02f6f00d01a · outbound

This paper cites Y ., et al.

Leveraging Per-Instance Privacy for Machine Unlearning Y ., et al

Reference 2021

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:51.655403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-07T14:29:49.478202Z digest=sha256:d81fc1297c8292b79380d317254c2e7ef902828b52d7fd278f0d9347cb6f71d7

Observation 8d5559d7-78e2-4d5d-8e4e-aaac0829fa62 · outbound

This paper cites SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation.

Leveraging Per-Instance Privacy for Machine Unlearning SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation

Reference 2022

Resolution
unresolved
no resolver link, observed 2026-08-07T14:29:48.976252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:29:48.976252Z digest=sha256:88f2934be8383d80d162a791cf1f091b6a6248832a9891015b6769d0254c28f1

Observation db83ac53-054a-45b3-92fb-ea8df8817392 · outbound

This paper cites Characterizing Structural Regularities of Labeled Data in Overparameterized Models.

Leveraging Per-Instance Privacy for Machine Unlearning Characterizing Structural Regularities of Labeled Data in Overparameterized Models

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-07T14:29:49.200586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:29:49.200586Z digest=sha256:90eeb6297299a203e450a3a7b1358097daccca788423063a339ca8dc67de5be5

Observation a9536f05-ffa6-4c42-b79f-2ab5ff392a3c · outbound

This paper cites To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models.

Leveraging Per-Instance Privacy for Machine Unlearning To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-07T14:29:48.640081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:29:48.640081Z digest=sha256:7a8af352fa5aeb2eacfe42281c0c73f6907326513e0ba0e2941b220cd198f5c3

Pith citing papers

No inbound Pith citation observations are available.