Paper Citation Record · LEDGER

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning

As of 12 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2412.18621.

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

pith.paper-citation-record.v1
2412.18621 v1

Coverage vector

measured 46 of 46 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T14:16:49.719101Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+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

46 of 46 outbound references displayed

verified exact1
verified fuzzy1
unresolved44
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9a1cee3f-bef3-4ef6-97c9-79289948d3df · outbound

This paper cites Tackling Copyright Issues in AI Image Generation Through Originality Estimation and Genericization.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Tackling Copyright Issues in AI Image Generation Through Originality Estimation and Genericization

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-08-11T14:16:50.269825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ca89461e-55aa-460a-906e-dac852852ca8 · outbound

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

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.538875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae8db0dc-0a89-4801-9e6e-f8ceda3deb72 · outbound

This paper cites Avoiding Copyright Infringement via Large Language Model Unlearning.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Avoiding Copyright Infringement via Large Language Model Unlearning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.543910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c39f4fc5-b137-4450-bcd7-883eb91e4dd0 · outbound

This paper cites Do Membership Inference Attacks Work on Large Language Models?.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Do Membership Inference Attacks Work on Large Language Models?

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.549944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d267e169-7eca-4d2f-9515-09e00b009aa9 · outbound

This paper cites DE-COP: Detecting Copyrighted Content in Language Models Training Data.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning DE-COP: Detecting Copyrighted Content in Language Models Training Data

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.554741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 057f397f-a759-4412-adec-2e3e97c46494 · outbound

This paper cites The Llama 3 Herd of Models.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning The Llama 3 Herd of Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.559147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06f7771b-bfb6-48bc-bf0b-b8d6ecba7b6d · outbound

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

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.568014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 150cd519-5ed9-470c-b18f-56ebf94dff56 · outbound

This paper cites Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.572410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bec49bc-847d-47c0-9a71-6e933ee8b6aa · outbound

This paper cites Attribute-to-Delete: Machine Unlearning via Datamodel Matching.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Attribute-to-Delete: Machine Unlearning via Datamodel Matching

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.577284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90542fac-12de-4456-9ea7-978a8feb6db3 · outbound

This paper cites Model Editing at Scale leads to Gradual and Catastrophic Forgetting.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Model Editing at Scale leads to Gradual and Catastrophic Forgetting

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.586612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3491c875-63f3-4d79-809d-789d1cfd50c4 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Measuring Massive Multitask Language Understanding

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.591395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 647260e1-c654-4472-bd84-51ef6326bd5e · outbound

This paper cites Model Editing with Canonical Examples.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Model Editing with Canonical Examples

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.595891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e0cf41b-ab9b-4c35-be43-a92cc11d20e4 · outbound

This paper cites Demystifying Verbatim Memorization in Large Language Models.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Demystifying Verbatim Memorization in Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.603887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee65d00f-0e67-490d-8f1f-148f76a4f303 · outbound

This paper cites Editing Models with Task Arithmetic.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Editing Models with Task Arithmetic

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.608080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e6a3ec5-1159-482f-adc6-aad793ae929f · outbound

This paper cites Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.612377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1290bea3-95ba-44b3-b10b-da7b37ab4703 · outbound

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

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Knowledge Unlearning for Mitigating Privacy Risks in Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.616595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4743c857-aeae-482e-9571-0944b8f8f7f6 · outbound

This paper cites Mistral 7B.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Mistral 7B

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.620799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 005e9201-cf01-4772-bbc2-9f4f6c1992c9 · outbound

This paper cites Copyright Violations and Large Language Models.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Copyright Violations and Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.625139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67912089-4376-4316-a6bc-c1e969e75793 · outbound

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

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.629745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9059df53-c993-49e1-abec-00c82dca5dd4 · outbound

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

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning TOFU: A Task of Fictitious Unlearning for LLMs

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.639066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe9bc159-0a97-4049-8ab0-269517264a57 · outbound

This paper cites Copyright Traps for Large Language Models.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Copyright Traps for Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.643305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b449727e-97d9-45c2-af30-f6161c097930 · outbound

This paper cites Mass-Editing Memory in a Transformer.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Mass-Editing Memory in a Transformer

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.647588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a198e3bd-5bc5-4588-bad7-c1f05d69eccd · outbound

This paper cites SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.652265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c515383-bd54-478e-b674-4083138fae47 · outbound

This paper cites Adversarial Training Methods for Semi-Supervised Text Classification.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Adversarial Training Methods for Semi-Supervised Text Classification

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.656561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98f51d3c-a9b4-44ae-8948-3130ad202ca1 · outbound

This paper cites Adding Gradient Noise Improves Learning for Very Deep Networks.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Adding Gradient Noise Improves Learning for Very Deep Networks

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.664817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26ba975b-bc1e-4f27-939f-0963c74af78e · outbound

This paper cites MUSE: Machine Unlearning Six-Way Evaluation for Language Models.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning MUSE: Machine Unlearning Six-Way Evaluation for Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.677777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3080bab-9420-4b6a-8948-00f41382fc25 · outbound

This paper cites Evaluating Copyright Takedown Methods for Language Models.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Evaluating Copyright Takedown Methods for Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.692646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c182c07-1710-4ca2-a6e2-0f02ae5d6dca · outbound

This paper cites Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.697089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4709e452-aa59-48de-b72e-e18f681ad7f9 · outbound

This paper cites Large Language Model Unlearning.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Large Language Model Unlearning

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.701698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b953a5c9-57bf-41e4-a0b8-7b0b2957d1d9 · outbound

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

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning A Closer Look at Machine Unlearning for Large Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.706145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1c253b5-150d-4c2a-aef6-4fb44b2212a1 · outbound

This paper cites Towards Certified Unlearning for Deep Neural Networks.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Towards Certified Unlearning for Deep Neural Networks

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.710392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd29068c-296f-4f26-8256-0d0e87fa0ac0 · outbound

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

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.714804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6543750c-93fc-426d-b19d-c36ead801591 · outbound

This paper cites Making Harmful Behaviors Unlearnable for Large Language Models.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Making Harmful Behaviors Unlearnable for Large Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.719101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46a199ee-c8e1-498e-91d4-1037fd098780 · outbound

This paper cites Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens

Reference 2004

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.634194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b754c5f-7b4f-4e29-9f85-2657d6db224d · outbound

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

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Who's Harry Potter? Approximate Unlearning in LLMs

Reference 2006

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.563449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e108eb5c-0e2e-41f0-9cc8-52bbaf758238 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 2014

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.687358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 007e6cd8-f837-4206-85dc-012c38fb8b2a · outbound

This paper cites Unlearning graph classifiers with limited data re- sources.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Unlearning graph classifiers with limited data re- sources

Reference 2015

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:16:50.335017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4c0e54df-3fd9-4261-802a-bf834968c223 · outbound

This paper cites Scalable Extraction of Training Data from (Production) Language Models.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Scalable Extraction of Training Data from (Production) Language Models

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.660947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fea05911-684a-47c5-9762-be3970a63a67 · outbound

This paper cites Dropout: a simple way to prevent neural networks from overfitting.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Dropout: a simple way to prevent neural networks from overfitting

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.682041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ecbbef2-d013-4b50-ac5c-4e1520e33017 · outbound

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

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.673348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c10115f-893b-4d7d-9652-6494be2f1e5f · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning LoRA: Low-Rank Adaptation of Large Language Models

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.599654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94f78574-0d16-4316-af45-10163091ff34 · outbound

This paper cites Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.581897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6fa9423-304f-40a7-ae83-64f1a82ec388 · outbound

This paper cites Quantifying Memorization Across Neural Language Models.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Quantifying Memorization Across Neural Language Models

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.518698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29cc6546-d532-4115-8d47-aa1277fcb6d2 · outbound

This paper cites AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.523666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8c958f5-2381-49b3-8d1d-58d63529a575 · outbound

This paper cites Language models are few-shot learners.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Language models are few-shot learners

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.512184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f50f80d9-c81b-4a8a-817f-0e24d5f384cf · outbound

This paper cites Unlearn What You Want to Forget: Efficient Unlearning for LLMs.

Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning Unlearn What You Want to Forget: Efficient Unlearning for LLMs

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-11T14:16:49.528739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.