Paper Citation Record · LEDGER

Subversion via Focal Points: Investigating Collusion in LLM Monitoring

As of 7 August 2026, this Paper Citation Record lists 8 of 8 outbound references and 0 inbound Pith citation observations for arXiv:2507.03010.

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

pith.paper-citation-record.v1
2507.03010 v1

Coverage vector

measured 8 of 8 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T20:52:29.912853Z

measured 8 of 8 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

8 of 8 outbound references displayed

verified exact0
verified fuzzy2
unresolved6
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d7ae2f33-49bf-4b13-80b8-b125b9b6f2e4 · outbound

This paper cites Ctrl-Z: Controlling AI Agents via Resampling.

Subversion via Focal Points: Investigating Collusion in LLM Monitoring Ctrl-Z: Controlling AI Agents via Resampling

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T20:52:29.326571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6511c20f-7a93-40c4-b169-2f85f00cba12 · outbound

This paper cites AI Control: Improving Safety Despite Intentional Subversion.

Subversion via Focal Points: Investigating Collusion in LLM Monitoring AI Control: Improving Safety Despite Intentional Subversion

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T20:52:29.430622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f029221-1244-42d7-a78b-569bcae35409 · outbound

This paper cites Measuring Coding Challenge Competence With APPS.

Subversion via Focal Points: Investigating Collusion in LLM Monitoring Measuring Coding Challenge Competence With APPS

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:52:30.441274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7b890ddb-8501-4c5c-8ebe-256fbb103f47 · outbound

This paper cites Subversion Strategy Eval: Can language models statelessly strategize to subvert control protocols?.

Subversion via Focal Points: Investigating Collusion in LLM Monitoring Subversion Strategy Eval: Can language models statelessly strategize to subvert control protocols?

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T20:52:29.606862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4e914dd-f6d4-4025-b4cd-f4f56d5021e5 · outbound

This paper cites Hidden in plain text: Emergence & mitigation of steganographic collusion in LLMs.

Subversion via Focal Points: Investigating Collusion in LLM Monitoring Hidden in plain text: Emergence & mitigation of steganographic collusion in LLMs

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T20:52:29.683394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1f6b897-3579-452f-82b9-433273197a45 · outbound

This paper cites Torr, Lewis Hammond, and Christian Schroeder de Witt.

Subversion via Focal Points: Investigating Collusion in LLM Monitoring Torr, Lewis Hammond, and Christian Schroeder de Witt

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:52:30.309378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 32a4d493-fc2c-4b5f-bca2-5444675ec82b · outbound

This paper cites Large Language Models Often Know When They Are Being Evaluated.

Subversion via Focal Points: Investigating Collusion in LLM Monitoring Large Language Models Often Know When They Are Being Evaluated

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T20:52:29.855907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cbbd01f-1168-4c14-b873-ebcaba0725ec · outbound

This paper cites Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats.

Subversion via Focal Points: Investigating Collusion in LLM Monitoring Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T20:52:29.912853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.