Paper Citation Record · LEDGER

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance

As of 9 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 2 inbound Pith citation observations for arXiv:2507.02977.

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

pith.paper-citation-record.v1
2507.02977 v1

Coverage vector

measured 17 of 17 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T21:22:59.700209Z

measured 19 of 19 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-30T22:48:43.262187Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T13:45:45.914511Z

Reference resolution

17 of 17 outbound references displayed

verified exact0
verified fuzzy8
unresolved9
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 14b7a6ad-30ac-4e50-a1a3-671cd2f4a38c · outbound

This paper cites Openai o1 system card (sep 2024), 2024.

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance Openai o1 system card (sep 2024), 2024

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:23:01.888753Z

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 c839a1b3-e8fc-4d37-bd23-900c89b86489 · outbound

This paper cites Troy, Stuart J.

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance Troy, Stuart J

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:23:01.486686Z

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 b162460f-f4ce-4b8e-bf00-7117e17111b8 · outbound

This paper cites Frontier Models are Capable of In-context Scheming.

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance Frontier Models are Capable of In-context Scheming

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T21:22:58.636617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da5ee6ad-0100-470f-893a-0314c97069f4 · outbound

This paper cites Demonstrating specification gaming in reasoning models.

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance Demonstrating specification gaming in reasoning models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T21:22:58.773703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9a3c403-56a8-4381-a94f-b4874e0c9b15 · outbound

This paper cites Alignment faking in large language models.

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance Alignment faking in large language models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T21:22:58.816501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f84e754d-9041-4a9f-ab13-352b95172087 · outbound

This paper cites I replicated the anthropic alignment faking experiment on other models, and they didn’t fake alignment.

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance I replicated the anthropic alignment faking experiment on other models, and they didn’t fake alignment

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:23:00.987883Z

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 caddabb4-294c-48d2-b1e5-78e4f70d6b39 · outbound

This paper cites Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents.

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T21:22:59.013316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 948e0b54-c2a6-436d-bc62-e1fc37608a58 · outbound

This paper cites Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents.

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T21:22:59.018086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b532cbf-e85a-455d-b071-122038bcb9e8 · outbound

This paper cites LLM Agents can Autonomously Exploit One-day Vulnerabilities.

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance LLM Agents can Autonomously Exploit One-day Vulnerabilities

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T21:22:59.085926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac2932f3-7626-4f90-8d04-0933120e2807 · outbound

This paper cites LLM Agents Should Employ Security Principles.

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance LLM Agents Should Employ Security Principles

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T21:22:59.187197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 864ad225-6ec8-4119-bf39-664983f92734 · outbound

This paper cites Gemini 2.5: Our most intelligent models are getting even better, 2025.

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance Gemini 2.5: Our most intelligent models are getting even better, 2025

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:23:00.764807Z

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 f8715da1-640b-4c2a-b3d8-ff1984219aba · outbound

This paper cites o3 and o4-mini system card, 2025.

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance o3 and o4-mini system card, 2025

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:23:00.588657Z

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 a2429620-6956-4cc3-a50e-c31eb707128d · outbound

This paper cites System card: Claude opus 4 & claude sonnet 4, 2025.

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance System card: Claude opus 4 & claude sonnet 4, 2025

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:23:00.394776Z

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 36056a68-c910-46cf-8ba1-87983f700e77 · outbound

This paper cites Deepseek-r1-0528 release, 2025.

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance Deepseek-r1-0528 release, 2025

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:23:00.214313Z

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 a75e8976-5b5f-4ce4-9f19-0589630e90d9 · outbound

This paper cites Risks from Learned Optimization in Advanced Machine Learning Systems.

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance Risks from Learned Optimization in Advanced Machine Learning Systems

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T21:22:59.603290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0e97d17-b714-42de-897c-4af5f0637f63 · outbound

This paper cites reference.

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance reference

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:23:00.014538Z

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 5497942e-b2b9-4158-b589-003931fee4ad · outbound

This paper cites an unresolved cited work.

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance Unresolved cited work

Reference 2025

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:23:01.201836Z

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 5ab2a844-f601-40cf-b5ac-f63a4e8c73a8 · inbound

SciIntegrity-Bench: A Benchmark for Evaluating Academic Integrity in AI Scientist Systems cites this paper.

SciIntegrity-Bench: A Benchmark for Evaluating Academic Integrity in AI Scientist Systems LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-12T05:36:24.427998Z

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 c237a8e7-8289-4fec-8ef3-ab1df0f3d69d · inbound

SciIntegrity-Bench: A Benchmark for Evaluating Academic Integrity in AI Scientist Systems cites this paper.

SciIntegrity-Bench: A Benchmark for Evaluating Academic Integrity in AI Scientist Systems LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-01T13:45:45.916404Z

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.