Paper Citation Record · LEDGER

Safety Alignment via Constrained Knowledge Unlearning

As of 8 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 3 inbound Pith citation observations for arXiv:2505.18588.

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

pith.paper-citation-record.v1
2505.18588 v1

Coverage vector

measured 13 of 13 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:34:05.740402Z

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:52:12.987900Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T18:05:36.791514Z

Reference resolution

13 of 13 outbound references displayed

verified exact0
verified fuzzy12
unresolved1
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 25282edb-c120-478b-8bed-fe9b694a7aa6 · outbound

This paper cites Goldilocks.

Safety Alignment via Constrained Knowledge Unlearning Goldilocks

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:34:06.821840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1f74dd3a-0489-4be7-86ce-4689dab97ec7 · outbound

This paper cites Xiaowei Huang, Wenjie Ruan, Wei Huang, Gaojie Jin, Yi Dong, and Changshun Wu.

Safety Alignment via Constrained Knowledge Unlearning Xiaowei Huang, Wenjie Ruan, Wei Huang, Gaojie Jin, Yi Dong, and Changshun Wu

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:34:08.282893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 66649d5a-45a2-426c-8e98-ebe048d354b0 · outbound

This paper cites Masahiro Kaneko, Danushka Bollegala, and Naoaki Okazaki.

Safety Alignment via Constrained Knowledge Unlearning Masahiro Kaneko, Danushka Bollegala, and Naoaki Okazaki

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:34:08.034569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 559b9eec-a351-4e11-8af8-21e1aedabc07 · outbound

This paper cites Xiaogeng Liu, Nan Xu, Muhao Chen, and Chaowei Xiao.

Safety Alignment via Constrained Knowledge Unlearning Xiaogeng Liu, Nan Xu, Muhao Chen, and Chaowei Xiao

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:34:07.859026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 864eb210-1d09-4a33-9ad7-7d8e54b0a87f · outbound

This paper cites Ximing Lu, Sean Welleck, Jack Hessel, Liwei Jiang, Lianhui Qin, and Peter West.

Safety Alignment via Constrained Knowledge Unlearning Ximing Lu, Sean Welleck, Jack Hessel, Liwei Jiang, Lianhui Qin, and Peter West

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:34:07.687575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 45f6ae85-43a2-44e2-9e53-df3bfc0a6e70 · outbound

This paper cites I’m sorry.

Safety Alignment via Constrained Knowledge Unlearning I’m sorry

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:34:07.089973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2ddcce01-dbc4-4459-bf61-ba13e38fc3a2 · outbound

This paper cites an unresolved cited work.

Safety Alignment via Constrained Knowledge Unlearning Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:34:06.598910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ffdd48ad-25c3-4621-9a6b-40fa1752471e · outbound

This paper cites entailment.

Safety Alignment via Constrained Knowledge Unlearning entailment

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:34:06.423128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2e89e71c-3b5b-44a3-bb98-d42400195e55 · outbound

This paper cites The task involves choosing the correct option from binary choices to fill in the blank in a given sentence, re- quiring the application of commonsense reasoning6.

Safety Alignment via Constrained Knowledge Unlearning The task involves choosing the correct option from binary choices to fill in the blank in a given sentence, re- quiring the application of commonsense reasoning6

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:34:06.207079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 22221407-a155-462f-877c-4bc03f41d11f · outbound

This paper cites It consists of 12,102 questions, each with one correct answer and four distractor an- swers7.

Safety Alignment via Constrained Knowledge Unlearning It consists of 12,102 questions, each with one correct answer and four distractor an- swers7

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:34:05.985470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2eac1142-603d-4a2d-af41-307d62a9a929 · outbound

This paper cites In Proceedings of Advances in Neural Information Processing Systems (NeurIPS).

Safety Alignment via Constrained Knowledge Unlearning In Proceedings of Advances in Neural Information Processing Systems (NeurIPS)

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:34:07.263141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c9efc5c0-a389-4289-ab58-3672cfb3a594 · outbound

This paper cites Jiaao Chen and Diyi Yang.

Safety Alignment via Constrained Knowledge Unlearning Jiaao Chen and Diyi Yang

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:34:08.400845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c22b9af4-0762-4a6e-9f11-5633cc09c9ed · outbound

This paper cites In Pro- ceedings of the AAAI Conference on Artificial Intelli- gence.

Safety Alignment via Constrained Knowledge Unlearning In Pro- ceedings of the AAAI Conference on Artificial Intelli- gence

Reference 2025

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:34:07.502454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

Observation 134d8f83-dfae-4c21-a068-4120c04e4bd8 · inbound

Multi-objective Large Language Model Alignment with Hierarchical Experts cites this paper.

Multi-objective Large Language Model Alignment with Hierarchical Experts Safety Alignment via Constrained Knowledge Unlearning

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T13:52:12.987900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a4173f3-380f-432e-ab91-936d58356508 · inbound

Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge Editing cites this paper.

Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge Editing Safety Alignment via Constrained Knowledge Unlearning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T13:15:55.676872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38cde0cb-9668-492f-a94d-a8052ea6c6f3 · inbound

SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks cites this paper.

SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks Safety Alignment via Constrained Knowledge Unlearning

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-08-05T18:05:36.850394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.