Paper Citation Record · LEDGER

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories

As of 10 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 1 inbound Pith citation observation for arXiv:2512.04144.

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

pith.paper-citation-record.v1
2512.04144 v3

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T18:41:35.433927Z

measured 33 of 33 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-13T04:30:23.082717Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

32 of 32 outbound references displayed

verified exact0
verified fuzzy0
unresolved32
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ee099214-c90f-4ccd-afb3-a3b4112a8437 · outbound

This paper cites Evaluating the ripple effects of knowledge editing in language models, 2023.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Evaluating the ripple effects of knowledge editing in language models, 2023

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:32.715667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b678310c-67b5-46fd-87e7-4fc6cf614ef6 · outbound

This paper cites Open Problems in Machine Unlearning for AI Safety.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Open Problems in Machine Unlearning for AI Safety

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:32.801107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62b61030-dfc6-4742-890f-b127c6289236 · outbound

This paper cites Are we making progress in unlearning? findings from the first neurips unlearning competition, 2024.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Are we making progress in unlearning? findings from the first neurips unlearning competition, 2024

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:32.864058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04f0f31d-a9e9-4287-941b-46995b0a69ca · outbound

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

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories TOFU: A Task of Fictitious Unlearning for LLMs

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:33.040444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5bcc48f-67b6-441d-b50b-27a509d3cbaa · outbound

This paper cites Lipton, J.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Lipton, J

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:33.157442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9195ab00-e824-41a4-9ef9-dd9eb8448c61 · outbound

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

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:33.209039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d633b40f-b453-4530-b558-748189c05f0e · outbound

This paper cites Measuring massive multitask language understanding, 2021.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Measuring massive multitask language understanding, 2021

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:33.286908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c398949-171e-4658-96d7-5b041eccaad3 · outbound

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

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:33.358328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa4a9a1a-56b9-490d-a486-50b913eda32d · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:33.493629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03c3a2f6-b9a7-42b7-beaf-5b1c4b9a42ac · outbound

This paper cites Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:33.593441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6c009dc-6a89-445f-9866-ee7117d5db89 · outbound

This paper cites Robust LLM safeguarding via refusal feature adversarial training.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Robust LLM safeguarding via refusal feature adversarial training

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:33.670392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1215b09-08ba-4379-adbd-ac7328f4ee6e · outbound

This paper cites Defending Against Unforeseen Failure Modes with Latent Adversarial Training.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Defending Against Unforeseen Failure Modes with Latent Adversarial Training

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:33.782057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce4190c3-1d4a-4ba5-bd09-c5f14d0c0f79 · outbound

This paper cites Rethinking machine unlearning for large language models.Nature Machine Intelligence, pages 1–14, 2025.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Rethinking machine unlearning for large language models.Nature Machine Intelligence, pages 1–14, 2025

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:33.935923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb69cc0c-8a5b-4536-9faa-636ec616d737 · outbound

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

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Who's Harry Potter? Approximate Unlearning in LLMs

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:34.006399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7097da3d-9cc2-4152-854d-cc253646dd09 · outbound

This paper cites Improving alignment and robustness with circuit breakers.Advances in Neural Information Processing Systems, 37:83345–83373, 2024.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Improving alignment and robustness with circuit breakers.Advances in Neural Information Processing Systems, 37:83345–83373, 2024

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:34.059988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8554132-1fc3-4601-bbaf-9f55da832e40 · outbound

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

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:34.112470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5409273a-ae7e-4ee8-beaf-5d42683a99a9 · outbound

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

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Tamper-Resistant Safeguards for Open-Weight LLMs

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:34.212799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 324c2444-c86c-4b36-9d49-f4d036e89f09 · outbound

This paper cites Representation noising effectively prevents harmful fine-tuning on llms.CoRR, 2024.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Representation noising effectively prevents harmful fine-tuning on llms.CoRR, 2024

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:34.319879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3232c1fd-3222-41a1-b376-671ec4eb6824 · outbound

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

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:34.380063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe197041-53af-4820-98ae-29e7f2f57528 · outbound

This paper cites Redirection for erasing memory (rem): Towards a universal unlearning method for corrupted data.arXiv preprint arXiv:2505.17730, 2025.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Redirection for erasing memory (rem): Towards a universal unlearning method for corrupted data.arXiv preprint arXiv:2505.17730, 2025

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:34.450577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b21c3fa2-4f87-4799-92c4-e41572e64493 · outbound

This paper cites Saes can improve unlearning: Dynamic sparse autoencoder guardrails for precision unlearning in llms.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Saes can improve unlearning: Dynamic sparse autoencoder guardrails for precision unlearning in llms

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:34.526575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 107ab70d-df49-491e-bb37-c934545094e5 · outbound

This paper cites Model Unlearning via Sparse Autoencoder Subspace Guided Projections.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Model Unlearning via Sparse Autoencoder Subspace Guided Projections

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:34.610283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a015d92-9ae4-4d2c-bfc5-f7ea840608ce · outbound

This paper cites C-pack: Packaged resources to advance general chinese embedding, 2023.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories C-pack: Packaged resources to advance general chinese embedding, 2023

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:34.715225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1d3079b-479a-4d3d-b1c7-7eb7d71fb16e · outbound

This paper cites The faiss library.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories The faiss library

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:34.780216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 275fbbdb-f6c4-41af-9fc1-a40aa2232cde · outbound

This paper cites an unresolved cited work.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:34.855405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 636bf27a-ddaf-4096-8c9c-e9c8cae7bbb9 · outbound

This paper cites Continual learning and private unlearning.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Continual learning and private unlearning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:34.934648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f13f6837-af46-40be-b7a2-77e31a36686a · outbound

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

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:35.007554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1510b40-0e7e-4389-a742-16c8752b8df6 · outbound

This paper cites Erasing Conceptual Knowledge from Language Models.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Erasing Conceptual Knowledge from Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:35.115153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b351cc9-3623-4c8f-98bf-8cfa64702c4d · outbound

This paper cites Unlearning in large language models via activation projections.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Unlearning in large language models via activation projections

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:35.209629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4eddb53-6309-4684-adbd-07bcef20f5bc · outbound

This paper cites Model tampering attacks enable more rigorous evaluations of llm capabilities, 2025.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Model tampering attacks enable more rigorous evaluations of llm capabilities, 2025

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:35.272194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73906e04-d433-4e11-ba98-c0573d4ce187 · outbound

This paper cites Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:35.335649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cab5c894-e8a8-41e6-b7fc-4abe7c157e06 · outbound

This paper cites unknowledgeable.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories unknowledgeable

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:35.433927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 8e61e3ad-40a0-478c-8275-59f56490515d · inbound

Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem cites this paper.

Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-13T04:30:23.082717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.