Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-06-30T13:20:49.099605Z
Paper Citation Record · LEDGER
Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation
As of 23 July 2026, this Paper Citation Record lists 4 of 4 outbound references and 0 inbound Pith citation observations for arXiv:2605.24535.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-07-23T06:31:01.910684+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
Reference resolution
4 of 4 outbound references displayed
- verified exact0
- verified fuzzy0
- unresolved0
- parse uncertain0
- malformed identifier1
- metadata mismatch3
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 7aa8cc1e-3184-40c1-9032-23576cd17e97 · outbound
This paper cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.
Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
Reference 1
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-06-30T13:24:39.744998Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.
Observation b463e9a4-fd04-496f-97eb-85fef8e5775d · outbound
This paper cites GPT-4 Technical Report.
Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation GPT-4 Technical Report
Reference 2
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-06-30T13:24:39.746576Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.
Observation c0a7e400-10be-448e-baf8-b9f8bbd8871b · outbound
This paper cites Gemma 2: Improving Open Language Models at a Practical Size.
Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation Gemma 2: Improving Open Language Models at a Practical Size
Reference 3
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-06-30T13:24:39.738427Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.
Observation 7d58275e-8596-46b1-aea3-e4a77baaf1ff · outbound
This paper cites Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment.
Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment
Reference 4
- Resolution
- malformed identifier
- doi_truncated, observed 2026-06-30T13:24:39.747222Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.
Pith citing papers
No inbound Pith citation observations are available.