Paper Citation Record · LEDGER

Multi-Agent AI Safety as an Institutional Design Problem

As of 12 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2608.09828.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2608.09828 v1

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T05:56:02.868695Z

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

24 of 24 outbound references displayed

verified exact4
verified fuzzy0
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6da49454-9acd-4bd0-99ac-6df259864ad0 · outbound

This paper cites an unresolved cited work.

Multi-Agent AI Safety as an Institutional Design Problem Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-11T05:56:03.300914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0316ac36-b786-4fb1-8865-ffb46ec67915 · outbound

This paper cites an unresolved cited work.

Multi-Agent AI Safety as an Institutional Design Problem Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-11T05:56:03.290911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f1edf96b-34bb-4976-b671-2c845bd04637 · outbound

This paper cites an unresolved cited work.

Multi-Agent AI Safety as an Institutional Design Problem Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-11T05:56:03.280322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e60da237-f9f9-4b6b-96b2-aff2d395a5f8 · outbound

This paper cites an unresolved cited work.

Multi-Agent AI Safety as an Institutional Design Problem Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T05:56:02.795511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5071e760-b90a-4e09-8ffc-61fadd8fa9c4 · outbound

This paper cites Rodriguez-Aguilar, and Carles Sierra.

Multi-Agent AI Safety as an Institutional Design Problem Rodriguez-Aguilar, and Carles Sierra

Reference 5

Resolution: verified exact; doi, observed 2026-08-11T05:56:02.900068Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 22206f1f-1ffa-4351-8462-e80ba66f34e4 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Multi-Agent AI Safety as an Institutional Design Problem Constitutional AI: Harmlessness from AI Feedback

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T05:56:02.802774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00dab705-8343-464f-8739-3326954e501b · outbound

This paper cites Deliberative Alignment: Reasoning Enables Safer Language Models.

Multi-Agent AI Safety as an Institutional Design Problem Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T05:56:02.806840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d30ddbf-f8cd-48b9-8a35-85ba74f78460 · outbound

This paper cites Defeating Prompt Injections by Design.

Multi-Agent AI Safety as an Institutional Design Problem Defeating Prompt Injections by Design

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T05:56:02.810420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a797cea3-e608-4f53-b795-0a6540fca3d1 · outbound

This paper cites an unresolved cited work.

Multi-Agent AI Safety as an Institutional Design Problem Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T05:56:02.813937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c90ce8fa-8753-4989-aef4-0d9a43da82f9 · outbound

This paper cites ChainCaps: Composition-Safe Tool-Using Agents via Monotonic Capability Attenuation.

Multi-Agent AI Safety as an Institutional Design Problem ChainCaps: Composition-Safe Tool-Using Agents via Monotonic Capability Attenuation

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T05:56:02.817318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7febcf1d-4c64-488c-8e2a-f3fa627f2daa · outbound

This paper cites Safeguarding LLM Agents from Misalignment through Provenance Analysis.

Multi-Agent AI Safety as an Institutional Design Problem Safeguarding LLM Agents from Misalignment through Provenance Analysis

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-11T05:56:03.152983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation c51de420-58fd-4c78-8297-4e37efe17e4c · outbound

This paper cites Normative Modules: A Generative Agent Architecture for Learning Norms that Supports Multi-Agent Cooperation.

Multi-Agent AI Safety as an Institutional Design Problem Normative Modules: A Generative Agent Architecture for Learning Norms that Supports Multi-Agent Cooperation

Reference 12

Resolution: metadata mismatch; local_arxiv, observed 2026-08-11T05:56:03.139163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 550ae035-be3b-4270-934f-2e8d8cc2dee1 · outbound

This paper cites an unresolved cited work.

Multi-Agent AI Safety as an Institutional Design Problem Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T05:56:02.828149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cffe1265-4564-4e66-9ccd-1759de66c0bb · outbound

This paper cites Open Problems in Cooperative AI.

Multi-Agent AI Safety as an Institutional Design Problem Open Problems in Cooperative AI

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T05:56:02.831415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5a0e934-a8eb-48a1-81bf-02bb45895d98 · outbound

This paper cites Mechanism Design Is Not Enough: Prosocial Agents for Cooperative AI.

Multi-Agent AI Safety as an Institutional Design Problem Mechanism Design Is Not Enough: Prosocial Agents for Cooperative AI

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-08-11T05:56:03.036676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d5152a60-8481-47c3-ba8a-fe23512f6f52 · outbound

This paper cites AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents.

Multi-Agent AI Safety as an Institutional Design Problem AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T05:56:02.838662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5aa9538d-40ee-4634-8c7a-6386433d01e5 · outbound

This paper cites Agent-SafetyBench: Evaluating the Safety of LLM Agents.

Multi-Agent AI Safety as an Institutional Design Problem Agent-SafetyBench: Evaluating the Safety of LLM Agents

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T05:56:02.842418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2cbe207-0591-4469-8827-3455c6f9ad2d · outbound

This paper cites Agentic Permissions Policy Algebra for Taint Confinement in LLM Agents.

Multi-Agent AI Safety as an Institutional Design Problem Agentic Permissions Policy Algebra for Taint Confinement in LLM Agents

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-08-11T05:56:03.004575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 13d3b173-ac75-4c3e-b57a-be852552c0ba · outbound

This paper cites Safe Multi-Agent Behavior Must Be Maintained, Not Merely Asserted: Constraint Drift in LLM-Based Multi-Agent Systems.

Multi-Agent AI Safety as an Institutional Design Problem Safe Multi-Agent Behavior Must Be Maintained, Not Merely Asserted: Constraint Drift in LLM-Based Multi-Agent Systems

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T05:56:02.850392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7507c7da-59bb-42ba-a3e6-8154a8af596e · outbound

This paper cites Authorization Propagation in Multi-Agent AI Systems: Identity Governance as Infrastructure.

Multi-Agent AI Safety as an Institutional Design Problem Authorization Propagation in Multi-Agent AI Systems: Identity Governance as Infrastructure

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T05:56:02.854401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 419dd9b1-738f-4393-9187-40a6adad193e · outbound

This paper cites Institutional Red-Teaming: Deployment Rules, Not Just Models, Causally Shape Multi-Agent AI Safety.

Multi-Agent AI Safety as an Institutional Design Problem Institutional Red-Teaming: Deployment Rules, Not Just Models, Causally Shape Multi-Agent AI Safety

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-11T05:56:02.972675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6282a09f-b320-462b-8a01-246956c331c3 · outbound

This paper cites Operational Reframing and Approval-Framed Delegation in Multi-Agent LLM Safety.

Multi-Agent AI Safety as an Institutional Design Problem Operational Reframing and Approval-Framed Delegation in Multi-Agent LLM Safety

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T05:56:02.861975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a4b6a8f-4e41-459a-938e-36fce6c9a768 · outbound

This paper cites an unresolved cited work.

Multi-Agent AI Safety as an Institutional Design Problem Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T05:56:02.865464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d80d210-93ee-4522-93e6-24218230b672 · outbound

This paper cites an unresolved cited work.

Multi-Agent AI Safety as an Institutional Design Problem Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-11T05:56:03.270036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Pith citing papers

No inbound Pith citation observations are available.