Paper Citation Record · LEDGER

Model Unlearning via Sparse Autoencoder Subspace Guided Projections

As of 14 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 1 inbound Pith citation observation for arXiv:2505.24428.

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

pith.paper-citation-record.v1
2505.24428 v1

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:28:04.568797Z

measured 29 of 29 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T18:41:34.610283Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

28 of 28 outbound references displayed

verified exact0
verified fuzzy3
unresolved24
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4b97d0b5-33af-40b0-9afa-85c315af921a · outbound

This paper cites an unresolved cited work.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:02.386481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef42f86e-ef8d-4b6f-8983-e1032f7e8297 · outbound

This paper cites A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:02.569189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbda50ed-7741-4656-a487-d612b215cafa · outbound

This paper cites an unresolved cited work.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:02.756833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66e493e2-c3ad-4d58-8ebc-1df9f9bf2b2f · outbound

This paper cites URL https://aclanthology.org/2025.naacl-long.325/.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections URL https://aclanthology.org/2025.naacl-long.325/

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:28:05.595420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 7c37861a-6828-4c35-b6cd-091167234bc9 · outbound

This paper cites Don't Forget It! Conditional Sparse Autoencoder Clamping Works for Unlearning.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections Don't Forget It! Conditional Sparse Autoencoder Clamping Works for Unlearning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:02.908526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33b3ceda-3f88-45b7-81a3-61a7050ce093 · outbound

This paper cites Nevermind: Instruction Override and Moderation in Large Language Models.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections Nevermind: Instruction Override and Moderation in Large Language Models

Reference 10

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T12:28:04.970013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9c4f932f-75f5-4474-9c6f-16f0fe0812b3 · outbound

This paper cites Nathaniel Li, Alexander Pan, Anjali Gopal, Summer Yue, Daniel Berrios, Alice Gatti, Justin D.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections Nathaniel Li, Alexander Pan, Anjali Gopal, Summer Yue, Daniel Berrios, Alice Gatti, Justin D

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:03.090704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58ecd773-b009-4ff2-9767-0f2a585c72cf · outbound

This paper cites doi: 10.18653/v1/2024.blackboxnlp-1.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections doi: 10.18653/v1/2024.blackboxnlp-1

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:03.157427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c6e3d75-b31b-414c-9a06-3e2c785846a8 · outbound

This paper cites Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:03.407434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4452de4e-8742-450c-9f84-c245aa3d8327 · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections Gemma: Open Models Based on Gemini Research and Technology

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:03.630850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2352fc18-5796-4812-8e8d-5b42bd263789 · outbound

This paper cites SAEs $\textit{Can}$ Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections SAEs $\textit{Can}$ Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:03.711536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d287ace0-dd53-458f-bbb7-0a7b93bda44b · outbound

This paper cites Johnny Lin.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections Johnny Lin

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:28:05.419159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ded5aedb-cd8b-4873-9f94-7ee66554a4a4 · outbound

This paper cites Prompt Obfuscation for Large Language Models.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections Prompt Obfuscation for Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:03.823380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc3ca153-233d-4563-9bdd-0c2964a75b15 · outbound

This paper cites Dissecting Language Models: Machine Unlearning via Selective Pruning.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections Dissecting Language Models: Machine Unlearning via Selective Pruning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:03.915252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b89de06-0a22-45f9-8b3c-56011ed8bfa3 · outbound

This paper cites Dissecting Language Models: Machine Unlearning via Selective Pruning.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections Dissecting Language Models: Machine Unlearning via Selective Pruning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:03.990672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d2b8d8b-d715-4eb1-a70a-bb19f0608553 · outbound

This paper cites Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:04.084704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64f102bb-1eb5-475e-a75f-db5c91b6f8b6 · outbound

This paper cites Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:04.135791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 242decb0-4487-4d25-b233-f063ff27e9fc · outbound

This paper cites Steering Language Models With Activation Engineering.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections Steering Language Models With Activation Engineering

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:04.200440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 664f688d-6bc8-4cbc-bec4-fc0ad7ffbd1e · outbound

This paper cites Steering Language Models With Activation Engineering.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections Steering Language Models With Activation Engineering

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:04.279476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06e06667-049f-4e68-a0ca-1b8fe074ff6b · outbound

This paper cites ReLearn: Unlearning via Learning for Large Language Models.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections ReLearn: Unlearning via Learning for Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:04.367778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 394f9315-6ef3-4e93-9e87-33e4bfa6a0be · outbound

This paper cites org/abs/2503.03710.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections org/abs/2503.03710

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:04.476560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3d64bf6-eb37-4c42-aa73-d8656368ad89 · outbound

This paper cites relevant.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections relevant

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:28:05.247651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8ac8a231-e4a5-4497-9d3b-7f6fa36249c2 · outbound

This paper cites Pointer Sentinel Mixture Models.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections Pointer Sentinel Mixture Models

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:03.533373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ad4ed36-043a-4f2b-86cb-ecce2c44ff6e · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections Training Verifiers to Solve Math Word Problems

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:02.485523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 274ef466-b369-4108-be8a-6158886e5655 · outbound

This paper cites doi: 10.18653/v1/2022.acl-long.229.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections doi: 10.18653/v1/2022.acl-long.229

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:03.319269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c26a9ff3-cf01-4adc-95db-63479e2cf879 · outbound

This paper cites SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:02.662563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e0aa99b-2460-412e-8b24-e34c5fb437eb · outbound

This paper cites Soft Prompting for Unlearning in Large Language Models.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections Soft Prompting for Unlearning in Large Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:02.312793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 424affdb-564a-45a6-90f9-e5d535904bea · outbound

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

Model Unlearning via Sparse Autoencoder Subspace Guided Projections Open Problems in Machine Unlearning for AI Safety

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:02.261829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

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

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories cites this paper.

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.