Paper Citation Record · LEDGER

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods

As of 9 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2506.10236.

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

pith.paper-citation-record.v1
2506.10236 v2

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:37:08.568150Z

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

24 of 24 outbound references displayed

verified exact1
verified fuzzy3
unresolved20
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6224a955-ca34-442b-aeb5-51011391d676 · outbound

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

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods Who's Harry Potter? Approximate Unlearning in LLMs

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:06.784382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 784e5666-a270-4ef5-a7d0-1fb1b4a0cedc · outbound

This paper cites 6 Ryan Greenblatt, Fabien Roger, Dmitrii Krasheninnikov, and David Krueger.

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods 6 Ryan Greenblatt, Fabien Roger, Dmitrii Krasheninnikov, and David Krueger

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:06.905230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 063ad588-eda8-45ea-9ed0-4369c984792e · outbound

This paper cites Mistral 7B.

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods Mistral 7B

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:07.100886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa825a17-919c-4dcf-a4ee-b15251b88615 · outbound

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

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:07.250365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c4baf1d-82b2-43f2-ad2d-084173759af0 · outbound

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

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods TOFU: A Task of Fictitious Unlearning for LLMs

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:07.358259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81467daf-364b-48ba-afc0-c08fe4e21be5 · outbound

This paper cites McKinney, Anvith Thudi, Juhan Bae, Tara Rezaei Kheirkhah, Nicolas Papernot, Sheila A.

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods McKinney, Anvith Thudi, Juhan Bae, Tara Rezaei Kheirkhah, Nicolas Papernot, Sheila A

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:37:09.534487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3f40819a-a57e-4375-ae14-5ec259a731e8 · outbound

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

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:07.507769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21c52f53-8e11-467b-b0bb-db5c958e57cc · outbound

This paper cites tinyBenchmarks: evaluating LLMs with fewer examples.

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods tinyBenchmarks: evaluating LLMs with fewer examples

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:07.670301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e31cf72-4903-4ae0-b01f-ba26f6d10686 · outbound

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

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:07.725074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f7bb65d-affd-40f1-97b4-2e08bda272ab · outbound

This paper cites UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI.

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:07.816508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72cbd017-c19c-46bb-ae8f-632a1a95f874 · outbound

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

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods Tamper-Resistant Safeguards for Open-Weight LLMs

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:07.881113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd246f8c-77b8-44ad-b04e-a47d6ebc2c5e · outbound

This paper cites AI Sandbagging: Language Models can Strategically Underperform on Evaluations.

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods AI Sandbagging: Language Models can Strategically Underperform on Evaluations

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:07.975951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d61c81e3-d491-44ad-b92a-caff49b54915 · outbound

This paper cites Jailbroken: How Does LLM Safety Training Fail?.

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods Jailbroken: How Does LLM Safety Training Fail?

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:08.055115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2497b4e0-902a-4fe1-87aa-e909ac647df9 · outbound

This paper cites In-Context Learning Can Re-learn Forbidden Tasks.

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods In-Context Learning Can Re-learn Forbidden Tasks

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-08-07T04:37:08.751340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e7b22fde-4c56-45b1-8e2e-19c8d5f09556 · outbound

This paper cites Low-Resource Languages Jailbreak GPT-4.

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods Low-Resource Languages Jailbreak GPT-4

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:08.222926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9b446f5-9593-4ab4-8bb8-172c1d9c5ae5 · outbound

This paper cites Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models.

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:08.295456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation daf4a539-e064-49db-90ab-d9a500267018 · outbound

This paper cites Improving Alignment and Robustness with Circuit Breakers.

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods Improving Alignment and Robustness with Circuit Breakers

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:08.378893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff311a48-1010-47e9-b739-5526929b2600 · outbound

This paper cites [2024], a subset of 100 data points selected from MMLU (Massive Multitask Language Understanding) Hendrycks et al.

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods [2024], a subset of 100 data points selected from MMLU (Massive Multitask Language Understanding) Hendrycks et al

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:37:09.299362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f746d274-9a40-4499-b45c-c5bba14a7e2d · outbound

This paper cites Right Format.

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods Right Format

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:37:09.131821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 381b5830-0b54-4e86-b56f-edf92e64f8bd · outbound

This paper cites The Elicitation Game: Evaluating Capability Elicitation Techniques.

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods The Elicitation Game: Evaluating Capability Elicitation Techniques

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:07.012174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 546dad7a-a2f3-4619-85ee-905b22e762e5 · outbound

This paper cites Continual Learning and Private Unlearning.

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods Continual Learning and Private Unlearning

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:07.178037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e0fc9f6-87cb-4b06-91ca-970599e27cbd · outbound

This paper cites Erasing Conceptual Knowledge from Language Models.

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods Erasing Conceptual Knowledge from Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:06.829821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ac562e3-c5b1-46c0-8e04-7102890168a9 · outbound

This paper cites Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities.

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:06.683217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c1bd043-7b6f-478f-bcbb-b698ff529c13 · outbound

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

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:06.722626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.