Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-06-28T16:53:09.787904Z
Paper Citation Record · LEDGER
As of 19 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 1 inbound Pith citation observation for arXiv:2606.02644.
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 2026-06-28T16:53:09.787904Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-07-31T22:25:22.286866Z
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 8b028a07-035f-4b7c-880d-f0a1a6f9dda8 · outbound
A New Framework for Cybersecurity Refusals in AI Agents Unresolved cited work
Reference 1
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 277ded33-c659-4f99-aeb5-e3bf0cf89cfe · outbound
A New Framework for Cybersecurity Refusals in AI Agents Unresolved cited work
Reference 2
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 85f7203a-d511-4e80-9e67-496f5fca319e · outbound
A New Framework for Cybersecurity Refusals in AI Agents Unresolved cited work
Reference 3
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 82b1c177-fd14-4479-8b5b-edc9a6716e8e · outbound
A New Framework for Cybersecurity Refusals in AI Agents Unresolved cited work
Reference 4
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ab8a8575-34e8-488e-8389-faeddcee462a · outbound
A New Framework for Cybersecurity Refusals in AI Agents B Grading Methodology Capability grading determines whether an agent successfully identified and exploited a vulnerability
Reference 5
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 554d1fea-5fb9-4c74-abf8-befef495819e · outbound
A New Framework for Cybersecurity Refusals in AI Agents Unresolved cited work
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f02fdd0c-0124-4465-b1e7-d3591bb971c9 · outbound
A New Framework for Cybersecurity Refusals in AI Agents Unresolved cited work
Reference 7
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ad88ef20-4c6b-4c91-8fd7-e85978274392 · outbound
A New Framework for Cybersecurity Refusals in AI Agents Unresolved cited work
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6d41a8e0-6b21-4a35-853e-c7fe7a43ac05 · outbound
A New Framework for Cybersecurity Refusals in AI Agents Unresolved cited work
Reference 9
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a8c14e94-54a6-45df-90fc-3219c11c1c95 · outbound
A New Framework for Cybersecurity Refusals in AI Agents Unresolved cited work
Reference 10
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7a70a2ef-c0e7-45ce-97f5-510736aa9806 · outbound
A New Framework for Cybersecurity Refusals in AI Agents Unresolved cited work
Reference 11
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7ba263b9-efac-4ebc-bd40-6560e2e635bf · outbound
A New Framework for Cybersecurity Refusals in AI Agents Unresolved cited work
Reference 14
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fa8a696c-fb61-4623-8c83-366eee9a7f9e · outbound
A New Framework for Cybersecurity Refusals in AI Agents Unresolved cited work
Reference 15
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2de9b340-ab93-4117-a6bf-2530fc5ea365 · outbound
A New Framework for Cybersecurity Refusals in AI Agents Unresolved cited work
Reference 16
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3ac76830-7d67-4554-bd29-622af99d7d5d · outbound
A New Framework for Cybersecurity Refusals in AI Agents Unresolved cited work
Reference 17
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 169eae40-4498-44d6-9d66-f59292685b2b · outbound
A New Framework for Cybersecurity Refusals in AI Agents Unresolved cited work
Reference 18
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 94b7f5e7-2c87-4e15-90b6-98703a724a12 · outbound
A New Framework for Cybersecurity Refusals in AI Agents Unresolved cited work
Reference 19
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation addb1b9d-4726-4a7a-a05c-cb4d4039e847 · inbound
Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs A New Framework for Cybersecurity Refusals in AI Agents
Reference 36
Source-reported events for the cited work
Unavailable: canonical work link unavailable.