Paper Citation Record · LEDGER

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models

As of 8 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 3 inbound Pith citation observations for arXiv:2506.17279.

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

pith.paper-citation-record.v1
2506.17279 v1

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:56:31.634491Z

measured 28 of 28 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T10:39:08.021275Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-20T14:13:21.270655Z

Reference resolution

25 of 25 outbound references displayed

verified exact1
verified fuzzy1
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bdc8e59c-a7b5-4908-9109-9b292287dc29 · outbound

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

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models Do Unlearning Methods Remove Information from Language Model Weights?

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.527816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02947c08-5ca2-44d0-86cb-7613044fa35a · outbound

This paper cites Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.537395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f77c2003-eba1-430b-a78a-010de4ae4e1f · outbound

This paper cites Intrinsic Test of Unlearning Using Parametric Knowledge Traces.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models Intrinsic Test of Unlearning Using Parametric Knowledge Traces

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.542059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b8d6f30-4f26-4db6-aaab-f247156245e1 · outbound

This paper cites Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.546933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56a68388-89da-41c6-ba31-0d16da8edfdb · outbound

This paper cites On Effects of Steering Latent Representation for Large Language Model Unlearning.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models On Effects of Steering Latent Representation for Large Language Model Unlearning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.551842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 361f8a32-4eee-409d-9ea1-fe5c2f0c8023 · outbound

This paper cites Knowledge Unlearning for Mitigating Privacy Risks in Language Models.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models Knowledge Unlearning for Mitigating Privacy Risks in Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.556982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9edc7df-58a0-4387-9c96-75a07e6a84bd · outbound

This paper cites WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.561334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97392904-e4f6-4862-91f5-2e0fae35a55f · outbound

This paper cites An Adversarial Perspective on Machine Unlearning for AI Safety.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models An Adversarial Perspective on Machine Unlearning for AI Safety

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.574139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 978c6968-bb87-44a6-88ef-92275a37f82d · outbound

This paper cites Eight Methods to Evaluate Robust Unlearning in LLMs.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.579425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe641c6d-bf13-4359-9fbe-835593427b04 · outbound

This paper cites Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.588211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8da2733b-f91e-450c-97a0-ffd03518c0a9 · outbound

This paper cites In-Context Unlearning: Language Models as Few Shot Unlearners.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models In-Context Unlearning: Language Models as Few Shot Unlearners

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.592736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa1ed3a2-4b3b-4bf8-8531-354b349b83b2 · outbound

This paper cites Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.597065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a31b78f2-c335-4ec7-ac2d-52202a74f28b · outbound

This paper cites UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.601190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a075f13e-8f9b-48b1-990d-36327b68a518 · outbound

This paper cites Tamper-Resistant Safeguards for Open-Weight LLMs.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models Tamper-Resistant Safeguards for Open-Weight LLMs

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.605239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8f9395b-f403-41bb-9ab1-90b50e17e52b · outbound

This paper cites Guardrail Baselines for Unlearning in LLMs.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models Guardrail Baselines for Unlearning in LLMs

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.609281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7297988f-0490-4414-81ec-4e5c231f4afc · outbound

This paper cites RKLD: Reverse KL-Divergence-based Knowledge Distillation for Unlearning Personal Information in Large Language Models.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models RKLD: Reverse KL-Divergence-based Knowledge Distillation for Unlearning Personal Information in Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.613263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7869cbf-9904-4d29-8fe1-05e08742e9da · outbound

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

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models Machine Unlearning of Pre-trained Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.621944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9653f7ae-a93f-44f8-8e55-67e2c55d42d7 · outbound

This paper cites A Closer Look at Machine Unlearning for Large Language Models.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models A Closer Look at Machine Unlearning for Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.626205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c27cbc1-2030-4101-be4d-824e2aef4e9f · outbound

This paper cites Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.630394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe3ca931-590b-402e-badc-7c0433c9f1dc · outbound

This paper cites Harry Potter and the Philosopher 's Stone.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models Harry Potter and the Philosopher 's Stone

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:56:32.043817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b0eeba5d-c419-48ce-8f02-52dd2272fcce · outbound

This paper cites DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.617645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adab6b89-3101-4e7b-af52-fb0761ecab07 · outbound

This paper cites Large Language Models Relearn Removed Concepts.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models Large Language Models Relearn Removed Concepts

Reference 2022

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:56:31.893913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1264694a-a6e3-4e3c-8563-3c883efaee09 · outbound

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

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.565579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5517323e-66d1-4394-acfb-2d87c6448f53 · outbound

This paper cites UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.532882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbab28a2-d095-43d5-86cb-bb37dfc44c79 · outbound

This paper cites TOFU: A Task of Fictitious Unlearning for LLMs.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models TOFU: A Task of Fictitious Unlearning for LLMs

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.583991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation a956a9d4-9a7b-4fd9-9529-87d41fb15614 · inbound

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models cites this paper.

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models

Reference 215

Resolution: unresolved; no resolver link, observed 2026-08-05T10:39:08.021275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db9a6592-5d7f-4966-bf8f-5cbc40517d7c · inbound

Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning cites this paper.

Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models

Reference 32

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T10:46:17.063339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 720ea40d-07bb-423f-8a62-a48eff257b4d · inbound

Auditing Reasoning-Trace Memorization Claims after Unlearning with Head-Conditioned Canaries cites this paper.

Auditing Reasoning-Trace Memorization Claims after Unlearning with Head-Conditioned Canaries Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:13:21.272205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.