Paper Citation Record · LEDGER

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning

As of 9 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 4 inbound Pith citation observations for arXiv:2506.00876.

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

pith.paper-citation-record.v1
2506.00876 v1

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:03:35.851539Z

measured 29 of 29 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 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T12:25:04.420234Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T15:36:06.508267Z

Reference resolution

25 of 25 outbound references displayed

verified exact2
verified fuzzy1
unresolved21
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 57d9e77f-524e-4857-9900-e378640ef209 · outbound

This paper cites , " * write output.state after.block = add.period write newline.

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning , " * write output.state after.block = add.period write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T12:03:32.171502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9eda6c2a-785f-46df-a6fd-d88dcd54fe42 · outbound

This paper cites write newline.

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T12:03:32.320024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45f47e06-d0fa-4c4f-809f-1a70a037e1f2 · outbound

This paper cites online" 'onlinestring :=.

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning online" 'onlinestring :=

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T12:03:32.468613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bd112df-c912-4971-bff5-c368a1d73f51 · outbound

This paper cites write newline.

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning write newline

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T12:03:32.638710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 119107d7-5765-416a-8e3c-21886980e1c5 · outbound

This paper cites Brown, Vincent J.

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning Brown, Vincent J

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:03:38.857564Z

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 2e051496-4f74-47e7-b95d-80b90dcd5000 · outbound

This paper cites Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate.

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T12:03:32.972167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 118ec5d4-869c-4633-972e-765a8e5358a0 · outbound

This paper cites an unresolved cited work.

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T12:03:33.112544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b8afc6a-b03c-4dc7-aba1-574fa70df5b3 · outbound

This paper cites an unresolved cited work.

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:03:38.521422Z

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 e3708281-a51d-418a-ae13-18323c286d61 · outbound

This paper cites Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport.

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T12:03:33.449038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c17d84ba-5cf3-49dd-87d1-b0dcc1cc218b · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T12:03:33.632127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fef0d0ee-7731-43d2-8b5f-b8f573d3b3de · outbound

This paper cites an unresolved cited work.

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T12:03:33.776003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf79885e-da3e-433d-93a1-fe5925d139ac · outbound

This paper cites an unresolved cited work.

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:03:38.228076Z

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 877563c6-5bb8-43ae-b7ed-0d986c0eaca0 · outbound

This paper cites Rho-1: Not All Tokens Are What You Need.

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning Rho-1: Not All Tokens Are What You Need

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T12:03:34.041761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 407b1c31-94f4-425d-b8f0-80a3cd8102f9 · outbound

This paper cites an unresolved cited work.

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:03:37.920009Z

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 390c6e2c-f5e1-44dc-be95-2b5d555c7417 · outbound

This paper cites Unveiling Entity-Level Unlearning for Large Language Models: A Comprehensive Analysis.

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning Unveiling Entity-Level Unlearning for Large Language Models: A Comprehensive Analysis

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:03:37.297649Z

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 416bf7ae-c338-4bf2-a155-a64fee593d5a · outbound

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

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning TOFU: A Task of Fictitious Unlearning for LLMs

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T12:03:34.514225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12434431-29d5-480a-9cab-99e075bac78a · outbound

This paper cites an unresolved cited work.

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning Unresolved cited work

Reference 17

Resolution: metadata mismatch; raw_fallback, observed 2026-08-07T12:03:36.884611Z

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 0b03b9f9-c15b-4943-9a5b-0a77508f22bc · outbound

This paper cites an unresolved cited work.

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T12:03:34.895925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11e1a793-6c1a-425b-a962-f257c446a40d · outbound

This paper cites LUME: LLM Unlearning with Multitask Evaluations.

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning LUME: LLM Unlearning with Multitask Evaluations

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T12:03:35.075615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 568e061d-0e35-49cf-8798-a8f7a13b43c5 · outbound

This paper cites an unresolved cited work.

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T12:03:35.190341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a61dfad5-5159-4e1a-b8c3-72049051dcfa · outbound

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

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning MUSE: Machine Unlearning Six-Way Evaluation for Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T12:03:35.340707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4298e1f2-c6bb-4262-b3e7-944768ba0f0c · outbound

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

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning RKLD: Reverse KL-Divergence-based Knowledge Distillation for Unlearning Personal Information in Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T12:03:35.509909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f649b722-3f5e-4160-bf65-76d2b5ab2be7 · outbound

This paper cites Selective Forgetting: Advancing Machine Unlearning Techniques and Evaluation in Language Models.

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning Selective Forgetting: Advancing Machine Unlearning Techniques and Evaluation in Language Models

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:03:36.261774Z

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 ee9df450-9d8c-4548-9f14-aa4eba851817 · outbound

This paper cites Large Language Model Unlearning.

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning Large Language Model Unlearning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T12:03:35.694158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41b80684-ee97-44c7-94d3-3bea6540e079 · outbound

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

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T12:03:35.851539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 4289f6ae-dd92-45bb-85f1-24e489d0b85d · inbound

Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning cites this paper.

Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T12:25:04.420234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c75e962f-a083-4e6f-b515-da826d5ca859 · inbound

A Mechanistic Perspective and Circuit-Guided Difficulty Metric for Unlearning cites this paper.

A Mechanistic Perspective and Circuit-Guided Difficulty Metric for Unlearning Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-03T10:37:03.968826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61fb617a-4094-4ae9-bc0a-6e856aa644f3 · inbound

Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning cites this paper.

Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-11T15:36:06.514291Z

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 8383cf05-cbd9-4bb9-a567-0c77fe1c7064 · inbound

Less is More: Geometric Unlearning for LLMs with Minimal Data Disclosure cites this paper.

Less is More: Geometric Unlearning for LLMs with Minimal Data Disclosure Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning

Reference 16

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T09:26:02.744143Z

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.