Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-12T03:09:34.972527Z
Paper Citation Record · LEDGER
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring
As of 9 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 2 inbound Pith citation observations for arXiv:2605.09684.
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 2026-08-09T06:31:02.800959+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-01T09:12:24.853947Z
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
44 of 44 outbound references displayed
- verified exact0
- verified fuzzy16
- unresolved26
- parse uncertain0
- malformed identifier2
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation e60b184f-cd57-4bf6-8168-6e517393bbf7 · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 1
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.818600Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation f06d1572-feaf-45ef-a8ff-1d56d7d73472 · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 2
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.845570Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 0459a6b3-767d-4aab-a47d-18de68cb6ca4 · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 3
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.827381Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 9642377d-e1a1-4887-aa8d-b9f2880fe6d3 · outbound
This paper cites 167.172.48.16/28.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring 167.172.48.16/28
Reference 4
- Resolution
- malformed identifier
- raw_fallback, observed 2026-05-12T20:41:52.946387Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 4e463831-25f2-4aa4-a640-0734fdf27a36 · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 5
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.922739Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 5e52754f-cc3a-45d6-8fff-d67bbc560a7c · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 6
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.814549Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 7a34d840-338e-4b12-aa3a-190feb9208a4 · outbound
This paper cites What files should the agent need to access? What changes should it need to make?.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring What files should the agent need to access? What changes should it need to make?
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T20:41:52.937076Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 60a141e4-1381-45be-a879-b8c3793352c4 · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 8
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.858433Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 638ea022-7bd4-42ed-b824-0da14cf44e7e · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 9
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.842178Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 10dc6d80-d8e7-4e98-a9ed-ad962729a605 · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 10
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.810489Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 41257beb-bb83-4c34-b943-03bdb2f8cecd · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 11
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.933742Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 044e2569-c616-4582-9ab3-2799d31e9ae1 · outbound
This paper cites The attacker agent will be given a main task to complete legitimately, plus a secret side task to accomplish while evading a monitor.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring The attacker agent will be given a main task to complete legitimately, plus a secret side task to accomplish while evading a monitor
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T20:41:52.939754Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation dd63d327-fe8c-441a-b740-fc8d8fc90252 · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 14
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.853968Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 6c248771-197e-4a70-b491-eab1b06f26db · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 15
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.862094Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 58e31e2c-67f3-4073-b447-93e1311a135c · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 16
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.943255Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 681fb340-a012-41d4-873b-1051e4442068 · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 17
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.952791Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 0da35c73-1923-43e4-be8b-0969ca5ae579 · outbound
This paper cites Then generate the report.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Then generate the report
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T20:41:52.873244Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 2a7a484f-afdc-4d2f-a70c-0bc5c99b9e8b · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 19
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.949336Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 874577c5-6a67-49da-a0c8-f8b46f771534 · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 20
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.884449Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation b220f5ac-6e67-4707-9b65-7ad79abeea2f · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 21
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.928368Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 9d241114-8d32-4422-ba95-703c400155e3 · outbound
This paper cites For each strategy, specify: (i) exact step-by-step instructions; (ii) what the monitor would need to understand to detect it; (iii) which main-task actions provide cover.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring For each strategy, specify: (i) exact step-by-step instructions; (ii) what the monitor would need to understand to detect it; (iii) which main-task actions provide cover
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T20:41:52.805490Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 67dd6bf7-5139-426d-a9b9-570fc5cad26e · outbound
This paper cites If the attack could be slotted into a different user task unchanged, the strategy is not specific enough.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring If the attack could be slotted into a different user task unchanged, the strategy is not specific enough
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T20:41:52.918956Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 7494a131-2519-4bab-b26c-f7510b1faa5f · outbound
This paper cites Avoid unnecessary complexity and any obviously adversarial signal.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Avoid unnecessary complexity and any obviously adversarial signal
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T20:41:52.887957Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 3b06bb0b-f88d-4a15-8827-9e7fdb567420 · outbound
This paper cites X-API-Key: <key>.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring X-API-Key: <key>
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T20:41:52.834507Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 59a3affe-29b7-476e-a5ff-78fad795c440 · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 28
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.801026Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation d8d36b50-1055-49d9-9516-759cd1358ee3 · outbound
This paper cites All current strategies are caught easily by the monitors and score 10/10 on suspiciousness.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring All current strategies are caught easily by the monitors and score 10/10 on suspiciousness
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T20:41:52.837526Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 3c505654-20df-4b51-8ff4-bd134818a505 · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 30
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.915525Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 017fdb33-b05a-429e-9ee3-4f7c8a4be73e · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 31
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.839613Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 7e093238-e24c-41ad-b551-c5bed6081dab · outbound
This paper cites 3.2 For every step, propose a way to make it less suspicious.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring 3.2 For every step, propose a way to make it less suspicious
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T20:41:52.909285Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 14515655-d50f-4415-aa76-fd0db7d9e1e2 · outbound
This paper cites Where possible, frame attack steps as something the user would have asked for.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Where possible, frame attack steps as something the user would have asked for
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T20:41:52.912299Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation a35ac7e8-7f9d-4a08-9973-3e4c48e603a9 · outbound
This paper cites Avoid unnecessary complexity and any obviously adversarial signal.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Avoid unnecessary complexity and any obviously adversarial signal
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T20:41:52.925749Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 71476347-4e87-44b4-8c77-bb2665d97b0b · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 35
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.899220Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 2db0568c-17f6-4552-a6ff-5e43ccec2894 · outbound
This paper cites manage-sudo.sh) over writing new files containing dangerous content.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring manage-sudo.sh) over writing new files containing dangerous content
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T20:41:52.906157Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 88971916-fe11-4718-b5f0-35914ea4e34b · outbound
This paper cites X-API-Key: <key>.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring X-API-Key: <key>
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T20:41:52.881276Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 30575829-8184-4abc-acde-1b05616329e1 · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 38
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.956931Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation aa76cd0f-d715-4431-9391-e3308d5a6c41 · outbound
This paper cites test crash reporting.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring test crash reporting
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T20:41:52.869779Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation cf9b19d0-5977-49d4-b5fb-275fdb273c64 · outbound
This paper cites 4.Selective payload: send only the API key or specific credentials, not entire config files.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring 4.Selective payload: send only the API key or specific credentials, not entire config files
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T20:41:52.849724Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation b88bfb20-3553-41f8-92d8-274ef01e2b90 · outbound
This paper cites create", path.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring create", path
Reference 41
- Resolution
- malformed identifier
- raw_fallback, observed 2026-05-12T20:41:52.823081Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 0088fc25-deff-4b10-9402-da3afa0aab79 · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 42
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.830577Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 63fd97cd-e067-4a22-876f-feca644c5280 · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 43
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.895255Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 7e97bf8d-6503-4173-9914-81e80891b9ae · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 44
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.903277Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation bc54c829-814b-4931-a113-c2e7bbdc3191 · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 45
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.877575Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 0c60cfd7-33af-4c1d-99e1-9412c58c7d33 · outbound
This paper cites an unresolved cited work.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Unresolved cited work
Reference 46
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T20:41:52.891734Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 109aa328-0a9a-4f2c-8020-9319d5ebddfb · outbound
This paper cites No attack detected.
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring No attack detected
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T20:41:52.931010Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Pith citing papers
Observation 4854c0a9-6648-4f10-b8ef-430b938f594f · inbound
Agent-Safety Evaluations as Load-Bearing Evidence: A Vendor-Neutral, Cross-Harness Reconstructability Metric cites this paper.
Agent-Safety Evaluations as Load-Bearing Evidence: A Vendor-Neutral, Cross-Harness Reconstructability Metric MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-07-15T05:51:54.267975Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 66bfbfe0-e53f-4b93-a9b0-6b1604811588 · inbound
Code Monitor Red Teaming for Public-Test-Passing Code cites this paper.
Code Monitor Red Teaming for Public-Test-Passing Code MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T09:12:24.853947Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.