Paper Citation Record · LEDGER

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification

As of 19 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 0 inbound Pith citation observations for arXiv:2607.19442.

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

pith.paper-citation-record.v1
2607.19442 v1

Coverage vector

measured 19 of 19 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T14:11:43.528504Z

measured 19 of 19 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+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

19 of 19 outbound references displayed

verified exact0
verified fuzzy0
unresolved19
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 724b7aaa-782d-4928-b56a-e74cdf712e32 · outbound

This paper cites Extracting Training Data from Large Language Models.

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification Extracting Training Data from Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:43.482286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f2a2e23-ca17-40d9-895a-ac3b4c821b06 · outbound

This paper cites Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening.

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:43.495873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee689732-e088-4efb-beed-fdae4b194b76 · outbound

This paper cites Towards Unbounded Machine Unlearning.

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification Towards Unbounded Machine Unlearning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:43.503645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c48267b7-705f-4d69-963f-e2153c429c44 · outbound

This paper cites The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning.

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:43.505699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d18b517d-5a0c-4f13-8a62-bb17ebe97c69 · outbound

This paper cites Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective.

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:43.508526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5598f7b0-aa03-4051-a2bd-dcab87b93f60 · outbound

This paper cites Merging Models with Fisher-Weighted Averaging.

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification Merging Models with Fisher-Weighted Averaging

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:43.513912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c10bc5d-86dd-4aa8-a693-7f5102e8ae40 · outbound

This paper cites Descent-to-Delete: Gradient-Based Methods for Machine Unlearning.

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification Descent-to-Delete: Gradient-Based Methods for Machine Unlearning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:43.516027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6347962f-ef96-47f3-a3a0-5833f65871bf · outbound

This paper cites Remember What You Want to Forget: Algorithms for Machine Unlearning.

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification Remember What You Want to Forget: Algorithms for Machine Unlearning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:43.520887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f13dc33c-24da-4c4a-a1f3-5bd849bff8a2 · outbound

This paper cites Membership Inference Attacks against Machine Learning Models.

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification Membership Inference Attacks against Machine Learning Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:43.523562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f50fbd0e-7592-4ca3-aabc-cc99e6d75619 · outbound

This paper cites Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time.

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:43.526214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16cbd9f7-b654-42aa-b90e-5b5eff96a735 · outbound

This paper cites Machine Unlearning of Pre-trained Large Language Models.

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification Machine Unlearning of Pre-trained Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:43.528504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ef6ad8a-1cdc-4c52-a7f9-960d57c10ca0 · outbound

This paper cites Ayush Sekhari, Jayadev Acharya, Gautam Kamath, and Ananda Theertha Suresh.

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification Ayush Sekhari, Jayadev Acharya, Gautam Kamath, and Ananda Theertha Suresh

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:43.518620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77e12263-feb9-4678-88b1-8dcc42f9659b · outbound

This paper cites Abstracting Causal Models.

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification Abstracting Causal Models

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:43.476121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4af236f9-48ae-4223-a374-580248292770 · outbound

This paper cites Certified Data Removal from Machine Learning Models.

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification Certified Data Removal from Machine Learning Models

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:43.498537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f07e45b-fcf8-4514-b928-9ac337b5f767 · outbound

This paper cites Machine Unlearning.

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification Machine Unlearning

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:43.479431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7ae9c9f-c035-4102-b4bf-fd39e6845596 · outbound

This paper cites Membership Inference Attacks From First Principles.

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification Membership Inference Attacks From First Principles

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:43.485050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1f25f05-704a-4deb-bbdf-2d74ab36da30 · outbound

This paper cites Who's Harry Potter? Approximate Unlearning in LLMs.

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification Who's Harry Potter? Approximate Unlearning in LLMs

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:43.493346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4cd6759-47e3-4638-96c7-aa229b8855be · outbound

This paper cites Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods.

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:43.490759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6394b5f9-8562-48e6-98fb-19b2b4c8f201 · outbound

This paper cites Jai Doshi and Asa Cooper Stickland.

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification Jai Doshi and Asa Cooper Stickland

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:43.488429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.