Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings | Paper Citation Record

Observation 7847c1fd-240f-4c1b-8b72-b44e8ba17873 · outbound

This paper cites Inspect AI : Framework for large language model evaluations, May 2024.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Inspect AI : Framework for large language model evaluations, May 2024

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:51:57.025625Z

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 d2be7f1d-5e18-467f-9912-e82813a20e15 · outbound

This paper cites Introducing Claude haiku 4.5, October 2025 a.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Introducing Claude haiku 4.5, October 2025 a

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:51:56.835810Z

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 e95b416b-de1e-4fd8-92ee-637b4e2811a0 · outbound

This paper cites Introducing Claude opus 4.5, November 2025 b.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Introducing Claude opus 4.5, November 2025 b

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:51:56.491211Z

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 1a90898a-bc18-40f9-8b9a-f0032c091536 · outbound

This paper cites Introducing Claude sonnet 4.5, September 2025 c.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Introducing Claude sonnet 4.5, September 2025 c

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:51:56.238274Z

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 96f401f5-f452-466e-8c89-fc3e111287e3 · outbound

This paper cites Chain-of-Thought Reasoning In The Wild Is Not Always Faithful.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:51.013543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 366a74fc-0792-4b39-b5c3-c60280eb4461 · outbound

This paper cites Biases in the Blind Spot: Detecting What LLMs Fail to Mention.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Biases in the Blind Spot: Detecting What LLMs Fail to Mention

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:51.079079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b791013-7f29-4d0b-888a-19e074ff7dea · outbound

This paper cites How does information access affect LLM monitors' ability to detect sabotage? arXiv preprint arXiv:2601.21112, January 2026.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings How does information access affect LLM monitors' ability to detect sabotage? arXiv preprint arXiv:2601.21112, January 2026

Reference 7

Resolution: verified exact; doi, observed 2026-08-06T17:51:52.773964Z

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 e411a152-ded3-44c0-bd5f-77beed122afc · outbound

This paper cites CoT red-handed: Stress testing chain-of-thought monitoring.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings CoT red-handed: Stress testing chain-of-thought monitoring

Reference 8

Resolution: verified exact; doi, observed 2026-08-06T17:51:52.696529Z

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 0aa7a58c-ad9e-47a7-99cb-42408b2e00b0 · outbound

This paper cites Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:51.240956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 791437e5-9cf6-41f3-beb7-14463f28461b · outbound

This paper cites Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-08-06T17:51:53.503854Z

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 ee052de4-fd50-4743-b7dc-1918bc7d93d5 · outbound

This paper cites Censored LLMs as a natural testbed for secret knowledge elicitation.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Censored LLMs as a natural testbed for secret knowledge elicitation

Reference 11

Resolution: verified exact; doi, observed 2026-08-06T17:51:52.622765Z

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 a1af007d-4c82-4494-8810-dfe623e17938 · outbound

This paper cites Reasoning Models Don't Always Say What They Think.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Reasoning Models Don't Always Say What They Think

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:51.482929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31bd8a52-def3-4980-b486-f4912b8a29b7 · outbound

This paper cites Lee, He He, Ian Kivlichan, Bowen Baker, Micah Carroll, and Tomek Korbak.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Lee, He He, Ian Kivlichan, Bowen Baker, Micah Carroll, and Tomek Korbak

Reference 14

Resolution: verified exact; doi, observed 2026-08-06T17:51:52.542529Z

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 e5e97ee0-eae1-4eb5-b90e-08d1df8d9865 · outbound

This paper cites Are DeepSeek R1 And Other Reasoning Models More Faithful?.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Are DeepSeek R1 And Other Reasoning Models More Faithful?

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:51.627288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3d8dc31-19d1-4cda-9ead-c45b620d98b6 · outbound

This paper cites When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:51.719517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e76d3e12-a314-4abe-94a4-1407cb4be026 · outbound

This paper cites (some) natural emergent misalignment from reward hacking in non-production rl, March 2026.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings (some) natural emergent misalignment from reward hacking in non-production rl, March 2026

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:51:56.031994Z

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 d3aea62b-7a06-4803-9dad-47dc30961199 · outbound

This paper cites Guan, Miles Wang, Micah Carroll, Zehao Dou, Annie Y.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Guan, Miles Wang, Micah Carroll, Zehao Dou, Annie Y

Reference 18

Resolution: verified exact; doi, observed 2026-08-06T17:51:52.467492Z

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 8cb673e0-48bc-460e-b3d1-bed4380fa23f · outbound

This paper cites Noticing the watcher: LLM agents can infer CoT monitoring from blocking feedback.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Noticing the watcher: LLM agents can infer CoT monitoring from blocking feedback

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.058436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e760a5c-06ea-4874-9859-3c1560cfed5b · outbound

This paper cites Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.127591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22c44c1e-22f5-4d04-b6fd-fce58ce9fa4f · outbound

This paper cites SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.183344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1876190b-3bb6-4f5d-8e47-bda706cf4f6a · outbound

This paper cites Measuring Faithfulness in Chain-of-Thought Reasoning.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Measuring Faithfulness in Chain-of-Thought Reasoning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.186621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c2634c9-8748-435f-89fc-1556adf7a8e6 · outbound

This paper cites an unresolved cited work.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.188944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3651c42c-9b21-436c-ab27-1bab369e683f · outbound

This paper cites Kimi k2 thinking, January 2026.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Kimi k2 thinking, January 2026

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:51:55.762764Z

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 4760181c-3f11-4e6a-8253-4d579d9e9421 · outbound

This paper cites gpt-oss-120b and gpt-oss-20b model card, August 2025.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings gpt-oss-120b and gpt-oss-20b model card, August 2025

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:51:55.503751Z

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 d17cf599-3150-4a5b-8cc7-14591bd740eb · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Steering Llama 2 via Contrastive Activation Addition

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.195387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4269579b-a6a1-498b-8a71-ec6210044950 · outbound

This paper cites Large language models can learn and generalize steganographic chain-of-thought under process supervision, 2025.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Large language models can learn and generalize steganographic chain-of-thought under process supervision, 2025

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.200090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d19fe64f-252a-44d0-be19-488d429369ef · outbound

This paper cites Steering Language Models With Activation Engineering.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Steering Language Models With Activation Engineering

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.202208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e354193-0b20-4880-bdd3-940b439a681b · outbound

This paper cites Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.204689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc5cb71a-18b1-49eb-a2ec-5d8a375928a1 · outbound

This paper cites Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.207562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d43bd6ce-84b7-4f2f-b8b1-aa28a045cfa8 · outbound

This paper cites MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.209806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8b455d8-8d05-46f3-859c-f38727e2e722 · outbound

This paper cites Grok 3 beta --- the age of reasoning agents, February 2025.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Grok 3 beta --- the age of reasoning agents, February 2025

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:51:55.227558Z

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 54fed9a0-8407-4395-ae8a-33038bcb0cfd · outbound

This paper cites GLM -4.7: Advancing the coding capability, December 2025.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings GLM -4.7: Advancing the coding capability, December 2025

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:51:54.965790Z

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 13fb16fc-05d5-414c-8ed0-4e4729999ed4 · outbound

This paper cites Can reasoning models obfuscate reasoning? stress-testing chain-of-thought monitorability.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Can reasoning models obfuscate reasoning? stress-testing chain-of-thought monitorability

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.216459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2437502c-1a34-4113-ae1e-bba68ec7ea31 · outbound

This paper cites 2023 , eprint=.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings 2023 , eprint=

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.218672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 927958a4-176c-4630-b2be-86610271f78c · outbound

This paper cites 2023 , eprint=.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings 2023 , eprint=

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.220659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98c666c8-bd05-4431-8064-c1bb5dc17370 · outbound

This paper cites 2025 , eprint=.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings 2025 , eprint=

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.222703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f9459d3-121b-4223-a87d-8015784b7ea4 · outbound

This paper cites 2026 , eprint=.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings 2026 , eprint=

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:51:54.777138Z

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 5178187b-cf63-4f2c-8935-92370c368a2d · outbound

This paper cites 2025 , eprint=.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings 2025 , eprint=

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:51:54.665282Z

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 c9b6f91c-e608-4553-900d-9d7171c2293c · outbound

This paper cites 2026 , eprint=.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings 2026 , eprint=

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:51:54.582474Z

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 8a77ec12-81e6-421d-95ab-c5a11106bdca · outbound

This paper cites 2025 , eprint=.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings 2025 , eprint=

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.230732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2216db55-6d18-447f-abcf-399d79cf8587 · outbound

This paper cites arXiv preprint arXiv:2512.18311 , year =.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings arXiv preprint arXiv:2512.18311 , year =

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.232686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2441273-de61-4d74-98c2-3bd6b0405e43 · outbound

This paper cites Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.234780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03053e1a-46ae-4826-8f62-66d4aa37aeb3 · outbound

This paper cites arXiv preprint arXiv:2603.05706 , year =.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings arXiv preprint arXiv:2603.05706 , year =

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.236856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73fad7a8-57a9-467f-9bc2-e574c9639c7a · outbound

This paper cites arXiv preprint arXiv:2510.19851 , year =.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings arXiv preprint arXiv:2510.19851 , year =

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.238875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d596953b-7e25-450b-b47c-9a8a9b4bc214 · outbound

This paper cites arXiv preprint arXiv:2505.23575 , year =.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings arXiv preprint arXiv:2505.23575 , year =

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.241151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9bf8812-08ae-4748-befb-961011b835f5 · outbound

This paper cites When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.243168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8b8928b-266a-431f-8ecc-d9792f291cf1 · outbound

This paper cites Noticing the Watcher:.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Noticing the Watcher:

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:51:54.381037Z

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 f77f12fa-2906-4938-afa5-a16bcb1a9463 · outbound

This paper cites SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.248062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9aedb683-1bd7-40c5-815c-4ffddab805dd · outbound

This paper cites How does information access affect.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings How does information access affect

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.250176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f4c68f4-055c-4a3b-a21e-2af33c9e81f9 · outbound

This paper cites Censored.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Censored

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.251993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8866e0b7-52c9-4da1-818d-d74a206bfd76 · outbound

This paper cites Steering.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Steering

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:51:54.249447Z

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 1bde4f1c-47e6-4640-b119-782c5d80421e · outbound

This paper cites Steering Language Models With Activation Engineering.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Steering Language Models With Activation Engineering

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.255930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47e18b2a-f703-4c80-9d3f-be93e2d71ed6 · outbound

This paper cites Are DeepSeek R1 And Other Reasoning Models More Faithful?.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Are DeepSeek R1 And Other Reasoning Models More Faithful?

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.258144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27e34088-3de7-4aec-a62c-7553b5bb1345 · outbound

This paper cites Reasoning Models Don't Always Say What They Think.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Reasoning Models Don't Always Say What They Think

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.260226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8daac443-4250-474f-8592-87fb3f5eef50 · outbound

This paper cites Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.262506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10dc86da-4f31-49dd-89d6-1d84367a99da · outbound

This paper cites 2026 , month=.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings 2026 , month=

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:51:54.034479Z

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 0370dbc7-3f1a-4713-a0a5-382c4d7f45b6 · outbound

This paper cites 2025 , eprint=.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings 2025 , eprint=

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:51:53.801715Z

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 10862a44-87c1-49bd-a152-b497a20cabab · outbound

This paper cites 2025 , eprint=.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings 2025 , eprint=

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:51:53.612616Z

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 ff7822dc-7acd-4f27-a4e3-83cd1b74624f · outbound

This paper cites Humanity's Last Exam.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings Humanity's Last Exam

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.270575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f68615f0-7475-41bb-8659-4c087ba4a378 · outbound

This paper cites 2025 , month =.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings 2025 , month =

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.272644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e3d9c8b-8daf-4730-91e2-6918e9a77e7c · outbound

This paper cites 2024 , month =.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings 2024 , month =

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.274605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a939a46-89a1-43c6-a786-78eb546c2959 · outbound

This paper cites GPQA: A Graduate-Level Google-Proof Q&A Benchmark.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings GPQA: A Graduate-Level Google-Proof Q&A Benchmark

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.276967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7975a77d-4bac-4655-b354-d47530af65b9 · outbound

This paper cites 2024 , eprint=.

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings 2024 , eprint=

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:52.279090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers