Paper Citation Record · LEDGER

Policy-Invisible Violations in LLM-Based Agents

As of 5 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 1 inbound Pith citation observation for arXiv:2604.12177.

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

pith.paper-citation-record.v1
2604.12177 v1

Coverage vector

measured 12 of 12 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T16:20:14.720123Z

measured 13 of 13 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-26T04:42:47.126107Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-04T13:59:52.343837Z

Reference resolution

12 of 12 outbound references displayed

verified exact8
verified fuzzy2
unresolved0
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3ada37fe-179b-4484-8063-10a3e4080aaa · outbound

This paper cites Masset, R.

Policy-Invisible Violations in LLM-Based Agents Masset, R

Reference 1

Resolution: malformed identifier; doi_truncated, observed 2026-05-10T16:20:34.686764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6e2e6673-b0ba-4fb3-ad80-c94e4e192b23 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Policy-Invisible Violations in LLM-Based Agents Constitutional AI: Harmlessness from AI Feedback

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-11T09:00:59.909004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6a66f7d1-678f-4940-9c84-d5e46a6e139d · outbound

This paper cites A large annotated corpus for learning natural language inference.

Policy-Invisible Violations in LLM-Based Agents A large annotated corpus for learning natural language inference

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:54:55.962483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fc14d40a-838e-4b6b-ace2-4a614a694598 · outbound

This paper cites OpenAI Gym.

Policy-Invisible Violations in LLM-Based Agents OpenAI Gym

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-11T19:49:39.087655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 357dd823-1d7b-49dc-b304-0df08b82d20e · outbound

This paper cites Keep security! benchmarking security policy preservationinlargelanguagemodelcontextsagainstindirectattacksinquestionanswering.

Policy-Invisible Violations in LLM-Based Agents Keep security! benchmarking security policy preservationinlargelanguagemodelcontextsagainstindirectattacksinquestionanswering

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T15:54:55.968345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e40f8581-2e32-4521-8b15-5c22de4f9974 · outbound

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

Policy-Invisible Violations in LLM-Based Agents AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:35:13.649872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a74867b6-336a-4c77-9acb-d76bce01ebe5 · outbound

This paper cites Agentleak: A full-stack benchmark for privacy leakage in multi-agent llm systems.

Policy-Invisible Violations in LLM-Based Agents Agentleak: A full-stack benchmark for privacy leakage in multi-agent llm systems

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:00:59.883884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6e4e90eb-9670-4612-9d6e-47bd66ce18ad · outbound

This paper cites Doc-PP: Document Policy Preservation Benchmark for Large Vision-Language Models.

Policy-Invisible Violations in LLM-Based Agents Doc-PP: Document Policy Preservation Benchmark for Large Vision-Language Models

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-11T09:00:59.896614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 10f0b55d-0340-4087-8648-c810a25ffca4 · outbound

This paper cites Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation.

Policy-Invisible Violations in LLM-Based Agents Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-06-02T03:04:03.222330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f5deea6f-0646-4a13-bde8-d9480f1fc51a · outbound

This paper cites Agentdam: Privacy leakage evaluation for autonomous web agents.

Policy-Invisible Violations in LLM-Based Agents Agentdam: Privacy leakage evaluation for autonomous web agents

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:00:59.889003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 76c1d56e-4a2f-43c2-bfd7-765fb42ec38c · outbound

This paper cites The Rise and Potential of Large Language Model Based Agents: A Survey.

Policy-Invisible Violations in LLM-Based Agents The Rise and Potential of Large Language Model Based Agents: A Survey

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:48:03.736032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9c081e7e-5055-46d8-a312-fba893267525 · outbound

This paper cites R-Judge: Benchmarking Safety Risk Awareness for LLM Agents.

Policy-Invisible Violations in LLM-Based Agents R-Judge: Benchmarking Safety Risk Awareness for LLM Agents

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:00:59.873412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

Observation 530202df-72db-4061-affa-14c7f9cb28fe · inbound

VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skills cites this paper.

VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skills Policy-Invisible Violations in LLM-Based Agents

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-07-04T13:59:52.345124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.