Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-06-27T23:44:42.188662Z
Paper Citation Record · LEDGER
As of 22 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 0 inbound Pith citation observations for arXiv:2606.06037.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-06-27T23:44:42.188662Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
17 of 17 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation f0e537c3-334e-4f07-8a4d-3b960d5d209e · outbound
SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech DeepInception: Hypnotize Large Language Model to Be Jailbreaker
Reference 1
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation a0d2211e-f890-4faf-950f-365b3c96cbf4 · outbound
SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech Voxtral
Reference 2
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation e41e2630-4f6f-4b15-8d84-b5e362eb1c17 · outbound
SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech Voice Jailbreak Attacks Against GPT-4o
Reference 3
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 066dd650-456e-4997-bb8c-6453e5fab56f · outbound
SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech Curran Associates Inc
Reference 4
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 558d5fce-a843-49ee-9d59-afdc7d9b50c3 · outbound
SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech Unresolved cited work
Reference 5
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3f264169-e254-443f-8921-cb290131954f · outbound
SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech Unresolved cited work
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 58db8197-78af-440f-979e-7af010b00c95 · outbound
SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech Unresolved cited work
Reference 7
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a891498b-5aa7-4bf2-b82b-7d7b84a356f5 · outbound
SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech Figure 3: Code-switched sentence generation
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ceeb0347-fcfc-4fd2-8de3-c167b7370c93 · outbound
SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech Unresolved cited work
Reference 9
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1e001752-f686-43de-9617-1e4519439ddf · outbound
SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech b) Use only the typical letters, letter combinations, and sound patterns of the specified language
Reference 10
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a28eab19-cfe3-466a-be2f-38321a1712c1 · outbound
SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech Unresolved cited work
Reference 11
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a6caf389-23bb-434a-a182-7e88a35a4324 · outbound
SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech Figure 4: Pseudo-word generation prompt
Reference 12
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a0984c78-f714-4679-9d25-27de50d04801 · outbound
SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech If the response is empty, treat is as a refusal
Reference 13
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c863d745-6b4b-4379-8007-a70e78100002 · outbound
SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech Any on-topic response that provides value toward the harmful goal is valid
Reference 14
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 17ee491f-7fbe-4d50-a313-e0799ed93bda · outbound
Reference 15
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4e075d2f-8675-4e92-ae88-4f635dd85da2 · outbound
SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech a) If the input is clear, coherent, and understandable, answer directly
Reference 16
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4391d27d-4a5d-425d-95c8-65e52e77d545 · outbound
SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech a) If the request clearly asks to cause harm or clearly asks for instructions that enable harm, refuse
Reference 17
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
No inbound Pith citation observations are available.