Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-03T10:48:28.727875Z
Paper Citation Record · LEDGER
As of 7 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2607.29254.
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 2026-08-03T10:48:28.727875Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+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
39 of 39 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation bfb69fce-708f-41f3-9233-a849b655b2a2 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Detecting Language Model Attacks with Perplexity
Reference 1
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ed484406-c8ba-4310-baa5-54286cd966c1 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Andriushchenko, A
Reference 2
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 99baa1ca-f688-4607-8885-59c49d6f1f84 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Arditi, O
Reference 3
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3817c2ef-ebd5-46a4-9a11-65abd1044932 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Constitutional AI: Harmlessness from AI Feedback
Reference 4
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3c9fd8da-dda3-41d7-8108-1f032a2019ca · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
Reference 5
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a8ea6266-b83d-4b9e-b6c7-9fbe79df6b1b · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Debenedetti, J
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 95d364fd-7c64-4560-86b5-256f99701786 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Unresolved cited work
Reference 7
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1b39eb52-fc65-4cdf-8585-ee272f399a11 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Unresolved cited work
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2eeef283-6f10-4b53-8149-066d14c72bb2 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents The Llama 3 Herd of Models
Reference 9
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 47aeea7c-564e-4302-8308-63b078be14e7 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Hadeliya, M
Reference 10
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0a743bf8-fddc-4a25-becd-6e6d544e25af · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Unresolved cited work
Reference 11
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 17872181-1f58-4416-8249-66f088b403ac · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Unresolved cited work
Reference 12
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2d7a81b1-3373-4219-afa1-806978a9578e · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Jeung, Y
Reference 13
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2fb2e557-6664-4dfa-964a-df988e34d57a · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Kumar, E
Reference 14
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 25aff37b-78fc-45b0-b3f3-fccc2604950d · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Unresolved cited work
Reference 15
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e5fb9317-9976-45ca-a7e5-64e92c80c921 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Unresolved cited work
Reference 16
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3c3000c7-404c-446a-b058-0b6bc6fad581 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Unresolved cited work
Reference 17
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a79ca7bc-8139-45a4-8c89-b2e731d116dd · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Unresolved cited work
Reference 18
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b0b958a9-9da2-4d29-a99a-2a28db92d77a · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Unresolved cited work
Reference 19
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2f6790b3-caba-42ef-ba2c-dbf379882812 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents WebGPT: Browser-assisted question-answering with human feedback
Reference 20
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2ea3e866-cf86-4670-b00d-ec772f74f515 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Unresolved cited work
Reference 21
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2632b1d4-e320-40c3-aa95-038a78eb7c13 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Unresolved cited work
Reference 22
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2bd39459-1f31-415e-88ea-cabd2ac9bcbd · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents OpenAI GPT-5 System Card
Reference 23
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 807aec0a-a93c-44ed-9040-f7e2fbbbfdff · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Gemini: A Family of Highly Capable Multimodal Models
Reference 24
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a244309d-cb3c-4541-b003-af6e9111cb20 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Topsakal and T
Reference 25
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6b888889-f7ed-4005-be85-928ae41e8e85 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Unresolved cited work
Reference 26
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6cb050c9-9e37-4be6-a541-0afa3d29a3f0 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Unresolved cited work
Reference 27
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 45957388-5754-4ae9-8d9c-a0b57ba4676f · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Unresolved cited work
Reference 28
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 16c8dcc5-99ea-4e63-834e-8e90fb27e31b · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents HuggingFace's Transformers: State-of-the-art Natural Language Processing
Reference 29
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c4a7fe79-fc33-430e-97ee-60887fdbaa78 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Unresolved cited work
Reference 30
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c2463a38-5a31-4300-bb75-36e12426de71 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Unresolved cited work
Reference 31
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e5b91a35-1efe-42c1-8a89-34b1b9f7bea9 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Qwen3 Technical Report
Reference 32
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 993f798a-c7d0-4c6f-b9db-154a5bfbc2f3 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions
Reference 33
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2f215096-7a02-41f8-b175-5e10a0d1125d · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents ReAct: Synergizing Reasoning and Acting in Language Models
Reference 34
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 81df08d1-f146-4eca-8ce9-0b7b0b5361f7 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Unresolved cited work
Reference 35
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2753e761-92c8-45ff-810b-31e5d9371928 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Unresolved cited work
Reference 36
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ecc00cb6-2127-4b50-a399-b09b0d2d0709 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models
Reference 37
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b74dc9af-55fb-48c1-ada2-af7fe1a1e44d · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Unresolved cited work
Reference 38
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0c491ad3-c891-4225-82f1-cba4740e8716 · outbound
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents Unresolved cited work
Reference 39
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
No inbound Pith citation observations are available.