Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T00:14:58.564634Z
Paper Citation Record · LEDGER
As of 8 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2608.02683.
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 2026-08-07T00:14:58.564634Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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
38 of 38 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation afb7197a-f188-45d3-bcb2-05259d4f7dc9 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense arXiv preprint arXiv:2511.21990 , year=
Reference 1
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 40cc3a29-9212-44ad-af56-09b22fb3e56e · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense arXiv preprint arXiv:2510.02373 , year=
Reference 2
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8d2c7d24-0bb3-46b8-9581-2047b59b82a2 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense , author=
Reference 3
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 906efac7-b59b-4994-97b8-8d566dedf967 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense AIR: Improving Agent Safety through Incident Response
Reference 4
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9326f6b4-d499-4951-ba63-cbd0ffa9dd24 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=
Reference 5
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ee551d2b-0e54-48d2-98df-eed99961d73b · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense 2025 , howpublished =
Reference 6
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation b5a1c539-f314-42aa-9d25-26aee460be6d · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense 2024 , howpublished =
Reference 7
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 4d0cb8da-7b9a-47e9-83cd-49033d268016 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense 2022 , note =
Reference 8
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation c88d3408-781e-4429-8738-71d56c96e533 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense Proceedings of the 36th annual acm symposium on user interface software and technology , pages=
Reference 9
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9b156c2c-1b36-46ad-8c9a-3a7bd6f9dbd9 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense 2025 , howpublished =
Reference 10
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d06905fc-b75c-47a3-85fa-476501c3fb17 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense Unresolved cited work
Reference 11
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation c13e6408-ea05-41dc-bcf9-097721f278ca · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense Unresolved cited work
Reference 12
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 5e7a0f68-979c-4ad9-bd7c-8dbe24e3b931 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
Reference 13
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 73fdfbbb-ea83-46f0-b5c7-7113c49022b6 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions
Reference 14
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c8bd3207-13d8-40dc-b5d4-a773d0407b7b · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models
Reference 15
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1de972a0-65c9-483d-bc7a-6cef8dca0b61 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense Agent Safety Alignment via Reinforcement Learning
Reference 16
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 95b11092-cdbf-4388-b858-3fe9aad23243 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense 2025 , note =
Reference 17
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 4c734725-94af-4a8b-892c-ae544f3cfec2 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense arXiv preprint arXiv:2601.05504 , year=
Reference 18
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 06492a6b-8673-4304-a557-553490f5b00a · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense Architecting Resilient LLM Agents: A Guide to Secure Plan-then-Execute Implementations
Reference 19
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9c60b4ff-b85e-439f-afb6-87156955c3e9 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense arXiv preprint arXiv:2601.10156 , year=
Reference 20
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cdf31f13-865f-4563-8a08-500b063ec190 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense arXiv preprint arXiv:2602.14281 , year=
Reference 21
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation facaf944-11d1-4a8a-9198-611c9ad079b7 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense arXiv preprint arXiv:2601.04795 , year=
Reference 22
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c4fc9c64-e12d-4d2f-a8c0-625e991591c8 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
Reference 23
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 347f6691-128f-45ca-b4ba-17257377482a · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction
Reference 24
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1506c92c-486a-4421-a122-65d19768a590 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis
Reference 25
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8778f5a9-2433-4530-a099-4592f41cd379 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense arXiv preprint arXiv:2603.28807 , year=
Reference 26
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 37a249f5-c0ea-4e87-bf4b-7ddea907d309 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
Reference 27
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0e54de4a-ac97-45d2-a82c-36e4c3d48be5 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis
Reference 28
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ff03c969-b1d4-4e84-859b-8b7ab56ad5af · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense SafeHarness: Lifecycle-Integrated Security Architecture for LLM-based Agent Deployment
Reference 29
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 74633031-927a-4244-969d-952e45893d43 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense 2026 , eprint=
Reference 30
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 9eb5d07c-b148-440c-beee-44da24204f79 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense The eleventh international conference on learning representations , year=
Reference 31
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 48dd8b98-917d-4cb3-958b-49cd9bd379fe · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense International Conference on Learning Representations , volume=
Reference 32
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 4d6bdb13-a1b0-412a-a1f3-3492e0a0ae9a · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense 2025 , howpublished =
Reference 33
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 636a8164-b70f-40c7-92c3-bc3565450251 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense LlamaFirewall: An open source guardrail system for building secure AI agents
Reference 34
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a86f9904-1060-486d-ab6f-0d99022bff3e · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense 2026 , url =
Reference 35
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 78a9750d-8ab2-4dab-be3b-1167ce6133d2 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense arXiv preprint arXiv:2412.13178 , year=
Reference 36
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d1773241-7f66-4d07-bb8e-648d48b6a0b2 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense IEEE Access , year=
Reference 37
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 09d5f75e-b324-43e0-a7a9-4c6e70545759 · outbound
$S^3$: Improving Agent Safety through Multi-Stage Defense 2025 , eprint=
Reference 38
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
No inbound Pith citation observations are available.