Paper Citation Record · LEDGER

RAS: Measuring LLM Safety Through Refusal Alignment

As of 6 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 0 inbound Pith citation observations for arXiv:2606.25750.

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

pith.paper-citation-record.v1
2606.25750 v1

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-25T20:03:45.355466Z

measured 29 of 29 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+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

29 of 29 outbound references displayed

verified exact0
verified fuzzy0
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ef5df600-1a49-4331-8390-98d783204d58 · outbound

This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics , year =.

RAS: Measuring LLM Safety Through Refusal Alignment Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics , year =

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 311dc596-58c3-4a72-9081-97a899b707f9 · outbound

This paper cites Advances in Neural Information Processing Systems , year =.

RAS: Measuring LLM Safety Through Refusal Alignment Advances in Neural Information Processing Systems , year =

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41c50a7c-e29f-4842-9659-fa25f8ee2d02 · outbound

This paper cites 2024 , eprint =.

RAS: Measuring LLM Safety Through Refusal Alignment 2024 , eprint =

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75cdecd3-8ab0-4c46-868c-70174af4ec1f · outbound

This paper cites 2022 , eprint =.

RAS: Measuring LLM Safety Through Refusal Alignment 2022 , eprint =

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d43f2c0-e3e7-460d-bce5-4d0635ab5b9d · outbound

This paper cites Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing , year =.

RAS: Measuring LLM Safety Through Refusal Alignment Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing , year =

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef781e89-fcae-407d-a706-e12b1df5968d · outbound

This paper cites 2023 , eprint =.

RAS: Measuring LLM Safety Through Refusal Alignment 2023 , eprint =

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b606aff8-4350-43ea-bd48-a9256a08d848 · outbound

This paper cites 2023 , eprint =.

RAS: Measuring LLM Safety Through Refusal Alignment 2023 , eprint =

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3a2db9a-3bbb-4b2e-a145-88b55c00052e · outbound

This paper cites 2023 , eprint =.

RAS: Measuring LLM Safety Through Refusal Alignment 2023 , eprint =

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c647db7-4a11-4062-a462-43f0d1ebc93f · outbound

This paper cites Advances in Neural Information Processing Systems , year =.

RAS: Measuring LLM Safety Through Refusal Alignment Advances in Neural Information Processing Systems , year =

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cffffead-a637-475a-b4f8-dee85402948a · outbound

This paper cites 2022 , eprint =.

RAS: Measuring LLM Safety Through Refusal Alignment 2022 , eprint =

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83f4d8b7-192a-4471-beb9-e9103cf70c16 · outbound

This paper cites 2023 , eprint =.

RAS: Measuring LLM Safety Through Refusal Alignment 2023 , eprint =

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95e120d1-3c94-41f8-b21c-0bdffcf5e714 · outbound

This paper cites Findings of the Association for Computational Linguistics: EMNLP 2020 , year =.

RAS: Measuring LLM Safety Through Refusal Alignment Findings of the Association for Computational Linguistics: EMNLP 2020 , year =

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57147f23-1621-4f50-b8c2-84c1f789cad3 · outbound

This paper cites Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing , year =.

RAS: Measuring LLM Safety Through Refusal Alignment Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing , year =

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5d7441d-a39b-4793-af6a-9752a7567173 · outbound

This paper cites Findings of the Association for Computational Linguistics: ACL 2022 , year =.

RAS: Measuring LLM Safety Through Refusal Alignment Findings of the Association for Computational Linguistics: ACL 2022 , year =

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31e927b2-ecef-4b0f-a22e-06f5ea9f09ef · outbound

This paper cites Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics , year =.

RAS: Measuring LLM Safety Through Refusal Alignment Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics , year =

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1aeacee3-c875-4d08-91ad-5e5f221c26ca · outbound

This paper cites Advances in Neural Information Processing Systems , year =.

RAS: Measuring LLM Safety Through Refusal Alignment Advances in Neural Information Processing Systems , year =

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f1c48cf-b5e2-4250-8d02-b6c68d270a72 · outbound

This paper cites 2023 , eprint =.

RAS: Measuring LLM Safety Through Refusal Alignment 2023 , eprint =

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3226652a-b9c8-48cc-90f4-7ab9b60de9ac · outbound

This paper cites 2022 , eprint =.

RAS: Measuring LLM Safety Through Refusal Alignment 2022 , eprint =

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45d325d0-de6f-4e99-857b-4bb36423caac · outbound

This paper cites 2024 , eprint =.

RAS: Measuring LLM Safety Through Refusal Alignment 2024 , eprint =

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df949979-3f17-4e4e-8cc2-c99fa9cd33a3 · outbound

This paper cites 2023 , eprint =.

RAS: Measuring LLM Safety Through Refusal Alignment 2023 , eprint =

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bb422aa-2d8e-4a24-9483-6a2ced122d7a · outbound

This paper cites International Conference on Learning Representations , year =.

RAS: Measuring LLM Safety Through Refusal Alignment International Conference on Learning Representations , year =

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7428fc9e-0c42-48d6-957d-43f154eeaac4 · outbound

This paper cites Advances in Neural Information Processing Systems , year =.

RAS: Measuring LLM Safety Through Refusal Alignment Advances in Neural Information Processing Systems , year =

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 108928be-a450-455a-83e0-e0768790b43c · outbound

This paper cites Advances in Neural Information Processing Systems , year =.

RAS: Measuring LLM Safety Through Refusal Alignment Advances in Neural Information Processing Systems , year =

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30c6108c-0dab-433c-a324-3d59e2c37746 · outbound

This paper cites International Conference on Learning Representations , year =.

RAS: Measuring LLM Safety Through Refusal Alignment International Conference on Learning Representations , year =

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7e2f881-5680-4492-8b8d-d62355c0f856 · outbound

This paper cites 2026 IEEE Conference on Artificial Intelligence (CAI) , pages=.

RAS: Measuring LLM Safety Through Refusal Alignment 2026 IEEE Conference on Artificial Intelligence (CAI) , pages=

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ff5ffbb-54dd-4679-8347-8de68de34856 · outbound

This paper cites Proceedings of the 41st International Conference on Machine Learning , series=.

RAS: Measuring LLM Safety Through Refusal Alignment Proceedings of the 41st International Conference on Machine Learning , series=

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4f72691-1319-4325-ad34-cc5c09a15d25 · outbound

This paper cites International Conference on Learning Representations , volume=.

RAS: Measuring LLM Safety Through Refusal Alignment International Conference on Learning Representations , volume=

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1b4e55d-8070-4065-9cd4-b710c267489c · outbound

This paper cites The Twelfth International Conference on Learning Representations , year=.

RAS: Measuring LLM Safety Through Refusal Alignment The Twelfth International Conference on Learning Representations , year=

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48334cf4-95eb-4456-a25c-36d1e671ecbd · outbound

This paper cites 2024 , eprint=.

RAS: Measuring LLM Safety Through Refusal Alignment 2024 , eprint=

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-25T20:03:45.355466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.