Paper Citation Record · LEDGER

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization

As of 18 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2607.15977.

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

pith.paper-citation-record.v1
2607.15977 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T21:47:02.992276Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+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

38 of 38 outbound references displayed

verified exact8
verified fuzzy0
unresolved30
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d00c10e2-a451-457f-a55b-b5162d1adc0b · outbound

This paper cites 2026 , isbn =.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization 2026 , isbn =

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T21:46:59.214081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da6bc5dc-c63b-40cb-b991-674561f72688 · outbound

This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume=.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization Proceedings of the AAAI Conference on Artificial Intelligence , volume=

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T21:46:59.250762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d0db242-5ba6-42ef-93f8-d354a5618946 · outbound

This paper cites and Jain, Lalit K and Nowak, Robert D and Mankoff, Bob and Zhang, Jifan.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization and Jain, Lalit K and Nowak, Robert D and Mankoff, Bob and Zhang, Jifan

Reference 3

Resolution: verified exact; doi, observed 2026-08-01T21:48:23.550091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0d4e8f00-1de4-4374-99d9-950de50da173 · outbound

This paper cites Small But Funny: A Feedback-Driven Approach to Humor Distillation.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization Small But Funny: A Feedback-Driven Approach to Humor Distillation

Reference 4

Resolution: verified exact; doi, observed 2026-08-01T21:48:23.247303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c251c4ea-5caf-4751-8fd6-9ccb20b9e448 · outbound

This paper cites Pun Unintended: LLM s and the Illusion of Humor Understanding.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization Pun Unintended: LLM s and the Illusion of Humor Understanding

Reference 5

Resolution: verified exact; doi, observed 2026-08-01T21:48:22.969822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e2b425c1-0c06-4467-a7bb-8fef9088760d · outbound

This paper cites 2024 , isbn =.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization 2024 , isbn =

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T21:46:59.574639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 231cf2a2-8af6-485d-862b-e5f37f023f0e · outbound

This paper cites Engagement Undermines Safety: How Stereotypes and Toxicity Shape Humor in Language Models.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization Engagement Undermines Safety: How Stereotypes and Toxicity Shape Humor in Language Models

Reference 7

Resolution: verified exact; doi, observed 2026-08-01T21:48:22.811132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 49451c19-92e7-4b23-b306-f3e8477008b5 · outbound

This paper cites arXiv preprint arXiv:2603.17759 , year=.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization arXiv preprint arXiv:2603.17759 , year=

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T21:46:59.743705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ad4d120-1488-4fef-81fc-319e04fd7fba · outbound

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

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization The Thirteenth International Conference on Learning Representations , year=

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T21:46:59.817854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2292e0e-af6e-4c70-8b09-25448e10a053 · outbound

This paper cites ICML 2026 , year=.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization ICML 2026 , year=

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T21:46:59.902434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 801be5ed-3fb4-4ca8-8b89-25ac015e97d1 · outbound

This paper cites Getting Serious about Humor: Crafting Humor Datasets with Unfunny Large Language Models.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization Getting Serious about Humor: Crafting Humor Datasets with Unfunny Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T21:46:59.986828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac00da6f-e595-4d55-beb5-fc7b71980d0d · outbound

This paper cites Chumor 2.0: Towards Better Benchmarking C hinese Humor Understanding from (Ruo Zhi Ba).

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization Chumor 2.0: Towards Better Benchmarking C hinese Humor Understanding from (Ruo Zhi Ba)

Reference 12

Resolution: verified exact; doi, observed 2026-08-01T21:48:22.621662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2aae92ec-fea7-459d-b20e-aebebaf1df51 · outbound

This paper cites Chumor 1.0: A Truly Funny and Challenging Chinese Humor Understanding Dataset from Ruo Zhi Ba.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization Chumor 1.0: A Truly Funny and Challenging Chinese Humor Understanding Dataset from Ruo Zhi Ba

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:00.171514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ed88eb5-da00-4681-af60-152b06456e23 · outbound

This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume=.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization Proceedings of the AAAI Conference on Artificial Intelligence , volume=

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:00.251140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed96807e-efa9-45ff-bbd0-8f69125ef509 · outbound

This paper cites Incomplete Prompt Jailbreaks in Large Language Models.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization Incomplete Prompt Jailbreaks in Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:00.391154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a58fdeea-1000-457e-b6cc-23162859590d · outbound

This paper cites Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency , url =.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency , url =

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:00.562639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 635f8b6e-abe6-4ef2-96b1-38a5f73bcde4 · outbound

This paper cites 2024 , isbn =.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization 2024 , isbn =

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:00.681639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f7a9a9a-fd45-4bf4-9120-8fcf7dfd4105 · outbound

This paper cites 2025 , isbn =.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization 2025 , isbn =

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:00.825299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 128e6b02-ed6d-4fb8-a677-bb1c3cea5503 · outbound

This paper cites 33rd USENIX Security Symposium (USENIX Security 24) , year =.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization 33rd USENIX Security Symposium (USENIX Security 24) , year =

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:00.931734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaad7948-05c9-4d22-ae6c-be7e1c74d4af · outbound

This paper cites Rothblum , booktitle=.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization Rothblum , booktitle=

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:01.045844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e05f6ce-6445-47fb-93ad-cdc56cadc595 · outbound

This paper cites an unresolved cited work.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:01.086898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3be2e25c-c8fd-44d8-ac54-2c0cabb13eda · outbound

This paper cites gpt-oss-120b & gpt-oss-20b Model Card.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization gpt-oss-120b & gpt-oss-20b Model Card

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:01.180010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62c8ff9b-b573-46e6-8cf0-087eeb2f3096 · outbound

This paper cites OS -Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization OS -Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows

Reference 23

Resolution: verified exact; doi, observed 2026-08-01T21:48:22.337470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a7f3c676-74ee-4de1-89bc-1db186f1c5d7 · outbound

This paper cites arXiv preprint arXiv:2601.10527 , year=.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization arXiv preprint arXiv:2601.10527 , year=

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:01.375929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 301d3e81-7332-4677-9117-8484f79131c8 · outbound

This paper cites Proceedings of the 34th USENIX Conference on Security Symposium , articleno =.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization Proceedings of the 34th USENIX Conference on Security Symposium , articleno =

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:01.515989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f65f516e-f30c-45a8-9016-7cfe9257966c · outbound

This paper cites 34th USENIX Security Symposium (USENIX Security 25) , pages=.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization 34th USENIX Security Symposium (USENIX Security 25) , pages=

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:01.644159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88c93aa0-0367-4240-95d8-dadbbe8514c0 · outbound

This paper cites TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:01.765950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91f50f54-ab44-40d8-aa45-50da8411fe5b · outbound

This paper cites AgentHarm: A Benchmark for Measuring Harmfulness of.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization AgentHarm: A Benchmark for Measuring Harmfulness of

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:01.924481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9597f2b5-eaa0-4e58-8c84-75cc6ede34a5 · outbound

This paper cites Vulnerability of Large Language Models to Output Prefix Jailbreaks: Impact of Positions on Safety.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization Vulnerability of Large Language Models to Output Prefix Jailbreaks: Impact of Positions on Safety

Reference 29

Resolution: verified exact; doi, observed 2026-08-01T21:48:22.101117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 640a0cd5-e7da-4f5e-86be-223175b8d369 · outbound

This paper cites Humans welcome to observe.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization Humans welcome to observe

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:02.252833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e34d067-d2b7-4a47-9f7e-03fbbd7758c9 · outbound

This paper cites and Chu, Eric and Behbahani, Feryal and Faust, Aleksandra and Larochelle, Hugo , booktitle =.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization and Chu, Eric and Behbahani, Feryal and Faust, Aleksandra and Larochelle, Hugo , booktitle =

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:02.391217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47c1efde-1479-4c5f-a2c1-02e593962036 · outbound

This paper cites ``What do you call a dog that is incontrovertibly true? Dogma'': Testing LLM Generalization through Humor.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization ``What do you call a dog that is incontrovertibly true? Dogma'': Testing LLM Generalization through Humor

Reference 32

Resolution: verified exact; doi, observed 2026-08-01T21:48:21.795206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a62c85a0-2ba1-4ea2-9f02-c39b204b265c · outbound

This paper cites and Lee, Lillian and Da, Jeff and Zellers, Rowan and Mankoff, Robert and Choi, Yejin.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization and Lee, Lillian and Da, Jeff and Zellers, Rowan and Mankoff, Robert and Choi, Yejin

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:02.433639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b53b31d0-2b3a-496a-9455-c5eea47bc95f · outbound

This paper cites PIG uard: Prompt Injection Guardrail via Mitigating Overdefense for Free.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization PIG uard: Prompt Injection Guardrail via Mitigating Overdefense for Free

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:02.535422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5097350a-49c0-4297-8af3-603e2da70b83 · outbound

This paper cites Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge , url =.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge , url =

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:02.618087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19955a6f-658c-4b33-a1af-67c02f4b52e5 · outbound

This paper cites Agent Data Injection Attacks are Realistic Threats to AI Agents.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization Agent Data Injection Attacks are Realistic Threats to AI Agents

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:02.723794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc7a7e8f-003e-4c28-90c8-d9ad024c0548 · outbound

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

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization Proceedings of the 41st International Conference on Machine Learning , articleno =

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:02.881957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bbdd3d9-0400-40a4-adf8-88faa7a8f1d2 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T21:47:02.992276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.