Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-20T17:13:17.533134Z
Paper Citation Record · LEDGER
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors
As of 11 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2605.16626.
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 2026-08-10T06:31:04.303077+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
Reference resolution
31 of 31 outbound references displayed
- verified exact0
- verified fuzzy15
- unresolved16
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 15e5b1e6-dc53-4964-b83f-bdeeccd44533 · outbound
This paper cites an unresolved cited work.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors Unresolved cited work
Reference 1
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T17:13:35.908695Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 5ddbdbdb-3d97-4775-9a81-1adc6f6a7673 · outbound
This paper cites an unresolved cited work.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors Unresolved cited work
Reference 2
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T17:13:35.910401Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation e001ab12-3762-433d-98b3-c5815ea2791d · outbound
This paper cites an unresolved cited work.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors Unresolved cited work
Reference 3
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T17:13:35.911960Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation f0973ac5-d822-40e3-a2cb-348515326795 · outbound
This paper cites Tracked as metadata, not used as a filter, since attacks that are catastrophic but plausibly deniable are also interesting to control.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors Tracked as metadata, not used as a filter, since attacks that are catastrophic but plausibly deniable are also interesting to control
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T17:13:35.892300Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation bc981690-420a-49f5-8af4-9b680910dc45 · outbound
This paper cites verdict".
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors verdict"
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T17:13:35.858312Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 012c0bcc-05d8-4762-a6c0-77d267df1c92 · outbound
This paper cites Must be actual parameter data, not just summary statistics.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors Must be actual parameter data, not just summary statistics
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T17:13:35.889568Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 9c82f2c8-fa45-45e3-adb8-69276ec860b5 · outbound
This paper cites The credentials must actually leave the secure boundary.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors The credentials must actually leave the secure boundary
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T17:13:35.896230Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 22d3fa5f-7f3d-4ce5-b102-2382e583cfbc · outbound
This paper cites an unresolved cited work.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors Unresolved cited work
Reference 8
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T17:13:35.848652Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation f17b2c1f-9133-455e-a02e-c76acb831ca3 · outbound
This paper cites an unresolved cited work.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors Unresolved cited work
Reference 9
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T17:13:35.907044Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 5d023604-5fe4-48c2-8b92-ed3fdfbe714c · outbound
This paper cites an unresolved cited work.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors Unresolved cited work
Reference 10
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T17:13:35.886016Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation bb94e6ab-aa00-447a-8564-fd6683d90161 · outbound
This paper cites an unresolved cited work.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors Unresolved cited work
Reference 11
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T17:13:35.883957Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 81066b73-b38d-40fe-a639-cdf999e66098 · outbound
This paper cites internal.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors internal
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T17:13:35.893886Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 085f6083-6b06-4d0a-ba37-6115bce86c7d · outbound
This paper cites Identify commands, their outputs, and any network requests.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors Identify commands, their outputs, and any network requests
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T17:13:35.901596Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 51221a7e-6819-4ae0-afcc-f37f2fade436 · outbound
This paper cites Trace data from source (where credentials/weights/etc originate) to destination (where they end up).
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors Trace data from source (where credentials/weights/etc originate) to destination (where they end up)
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T17:13:35.891744Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation afbffc04-53c3-43e0-a6ca-aa2e47e513b6 · outbound
This paper cites an unresolved cited work.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors Unresolved cited work
Reference 15
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T17:13:35.903250Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 49c6750e-cbae-4902-b494-f8dde414ecc8 · outbound
This paper cites verdict".
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors verdict"
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T17:13:35.873960Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 2084e172-cd8b-4145-b4c9-cc8e6bad4d64 · outbound
This paper cites an unresolved cited work.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors Unresolved cited work
Reference 17
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T17:13:35.885495Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation f197a94e-fecb-4069-a309-61ab7251cd40 · outbound
This paper cites this bucket name is attacker-controlled.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors this bucket name is attacker-controlled
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T17:13:35.876963Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 8602c079-7aac-4e2e-8d91-5809e1da7e90 · outbound
This paper cites For example: - If the attack targets the wrong line number, verify the benign version targets the correct line by parsing the file content from the transcript and counting.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors For example: - If the attack targets the wrong line number, verify the benign version targets the correct line by parsing the file content from the transcript and counting
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T17:13:35.887613Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation b7ed5a8b-410f-4047-af29-ca29fb5b3b04 · outbound
This paper cites fixing line 805.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors fixing line 805
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T17:13:35.905003Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation b95ac5aa-55bb-4ed7-b688-32ea6479c2fc · outbound
This paper cites an unresolved cited work.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors Unresolved cited work
Reference 21
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T17:13:35.844339Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 26464eb5-375c-42f4-849a-6321c9f2d80c · outbound
This paper cites verdict".
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors verdict"
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T17:13:35.888087Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 758f9677-5595-4d20-a98e-6dc564f47ea1 · outbound
This paper cites Signs” list, and a new “Analysis Method.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors Signs” list, and a new “Analysis Method
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T17:13:35.881843Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 6d044bc2-96a7-46f0-84c8-a31f3da5e7f0 · outbound
This paper cites looks right.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors looks right
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T17:13:35.872045Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation f7648b4a-cd79-4bf1-a65f-815e97d34360 · outbound
This paper cites an unresolved cited work.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors Unresolved cited work
Reference 34
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T17:13:35.859375Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation e1e05987-19b2-4608-9be5-18e34e22edc1 · outbound
This paper cites an unresolved cited work.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors Unresolved cited work
Reference 35
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T17:13:35.890051Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 51a0c717-2910-46d2-b73b-6edda7f7ca06 · outbound
This paper cites an unresolved cited work.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors Unresolved cited work
Reference 36
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T17:13:35.878464Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation af478bbd-8f9a-48d7-b139-e7badc558d37 · outbound
This paper cites an unresolved cited work.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors Unresolved cited work
Reference 37
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T17:13:35.894312Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 749e7190-126b-407d-932a-0b68468d3453 · outbound
This paper cites an unresolved cited work.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors Unresolved cited work
Reference 38
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T17:13:35.883448Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 4572afc3-d4fb-467a-af9a-664296dbc50d · outbound
This paper cites an unresolved cited work.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors Unresolved cited work
Reference 39
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T17:13:35.852294Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 8867f74b-8e6a-4034-9b61-2bcb6648c2ee · outbound
This paper cites backup somewhere safe.
SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors backup somewhere safe
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T17:13:35.899218Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Pith citing papers
No inbound Pith citation observations are available.