Paper Citation Record · LEDGER

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models

As of 7 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 7 inbound Pith citation observations for arXiv:2506.04909.

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

pith.paper-citation-record.v1
2506.04909 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T10:38:05.468538Z

measured 37 of 37 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 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:00:51.707342Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

30 of 30 outbound references displayed

verified exact0
verified fuzzy16
unresolved14
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation ea1967ed-7fb3-4bfb-a259-2ff5ac84da73 · outbound

This paper cites write newline.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T10:38:02.027941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7f2c0be-31e9-46d6-b0b0-ecc9b43caf03 · outbound

This paper cites and Mitchell, T.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models and Mitchell, T

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:38:08.795250Z

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 bc0d4022-cb2d-464d-b884-7197d6d32dcc · outbound

This paper cites Discovering latent knowledge in language models without supervision, March 2024.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models Discovering latent knowledge in language models without supervision, March 2024

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:38:08.698680Z

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 f8cea9d1-5ff4-40ad-ad5a-f045ea23bb2c · outbound

This paper cites Localizing lying in llama: Understanding instructed dishonesty on true-false questions through prompting, probing, and patching, November 2023.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models Localizing lying in llama: Understanding instructed dishonesty on true-false questions through prompting, probing, and patching, November 2023

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:38:08.506436Z

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 9bd5f315-7111-4238-8abe-a69eb08545b4 · outbound

This paper cites A mathematical framework for transformer circuits.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models A mathematical framework for transformer circuits

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T10:38:02.444405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2276cea3-94aa-4d69-a342-392a370dd943 · outbound

This paper cites R., and Hubinger, E.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models R., and Hubinger, E

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:38:08.264957Z

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 7a6dbadb-b282-4992-87e3-ce9132f2a1b7 · outbound

This paper cites Deception abilities emerged in large language models.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models Deception abilities emerged in large language models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T10:38:02.688962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ff6f362-bac0-4344-bdde-0a39ca7bbecf · outbound

This paper cites an unresolved cited work.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:38:08.038259Z

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 e43df03a-f2fd-4914-b20e-501298c205bc · outbound

This paper cites Y., Song, S., Hajishirzi, H., Kornblith, S., Farhadi, A., and Schmidt, L.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models Y., Song, S., Hajishirzi, H., Kornblith, S., Farhadi, A., and Schmidt, L

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:38:07.930957Z

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 eb049e20-912a-435a-9dc0-7d6644527c2b · outbound

This paper cites Large language models ( LLMs ): Survey , technical frameworks, and future challenges.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models Large language models ( LLMs ): Survey , technical frameworks, and future challenges

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T10:38:03.057101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7fae250-c8c1-4559-96df-6ab28f368dd5 · outbound

This paper cites TruthfulQA: Measuring How Models Mimic Human Falsehoods.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models TruthfulQA: Measuring How Models Mimic Human Falsehoods

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T10:38:03.263205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eaec6f86-1555-4ac8-9a0c-172a61f328ca · outbound

This paper cites Cognitive dissonance: Why do language model outputs disagree with internal representations of truthfulness? In Bouamor, H., Pino, J., and Bali, K.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models Cognitive dissonance: Why do language model outputs disagree with internal representations of truthfulness? In Bouamor, H., Pino, J., and Bali, K

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T10:38:03.360826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76fa1426-5849-493d-95a1-7de680df65f6 · outbound

This paper cites Faithful chain-of-thought reasoning.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models Faithful chain-of-thought reasoning

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:38:07.798430Z

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 04ccd2a7-7794-45a0-8e7f-e4ce61697f42 · outbound

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

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models Frontier Models are Capable of In-context Scheming

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T10:38:03.666723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e39c8e0a-756d-447f-9f73-173382954953 · outbound

This paper cites Locating and editing factual associations in gpt.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models Locating and editing factual associations in gpt

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:38:07.670229Z

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 d1ed4703-bad2-484d-8e89-88bf35bfc607 · outbound

This paper cites Interpreting gpt: The logit lens.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models Interpreting gpt: The logit lens

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:38:07.579925Z

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 31df4916-8878-494f-8a3b-af405b58173a · outbound

This paper cites S., Goldstein, S., O'Gara, A., Chen, M., and Hendrycks, D.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models S., Goldstein, S., O'Gara, A., Chen, M., and Hendrycks, D

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:38:07.443129Z

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 b9f1ec61-4e4e-4481-ae94-4bd3ba97bcaa · outbound

This paper cites Large language models can strategically deceive their users when put under pressure, July 2024.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models Large language models can strategically deceive their users when put under pressure, July 2024

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:38:07.324772Z

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 218aef99-cf33-4e90-9326-c7eadb5a5ed0 · outbound

This paper cites an unresolved cited work.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:38:07.182106Z

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 72b9e771-10e1-463a-913d-1715f16c41cb · outbound

This paper cites Qwq-32b: Embracing the power of reinforcement learning, March 2025.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models Qwq-32b: Embracing the power of reinforcement learning, March 2025

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:38:07.052683Z

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 45882e9b-bb11-42a8-8948-87676ff49ba7 · outbound

This paper cites L., Sharma, A.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models L., Sharma, A

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:38:06.977885Z

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 16202906-50d5-480e-8771-259ecba3b2d7 · outbound

This paper cites M., Thiergart, L., Leech, G., Udell, D., Vazquez, J.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models M., Thiergart, L., Leech, G., Udell, D., Vazquez, J

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:38:06.634111Z

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 5b7709c1-7bc1-44a4-a501-4270a70d1004 · outbound

This paper cites N., Kaiser, ., and Polosukhin, I.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models N., Kaiser, ., and Polosukhin, I

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T10:38:04.707675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4a24f4c-66a9-4b16-83dc-98d75501138b · outbound

This paper cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T10:38:04.803196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5497388-7067-482c-a3f7-2173f61acfe6 · outbound

This paper cites V., Zhou, D., et al.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models V., Zhou, D., et al

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T10:38:04.941743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a8dbc01-e3a2-4e56-9687-20e072740ba3 · outbound

This paper cites Qwen2.5 Technical Report.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models Qwen2.5 Technical Report

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T10:38:05.057064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edeeb8da-e7d3-422c-b360-568a11f9766b · outbound

This paper cites and Buzsaki, G.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models and Buzsaki, G

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:38:06.305864Z

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 9d6147ff-ac8b-4ef5-a946-2a7379e31e15 · outbound

This paper cites Reasoning models better express their confidence, 2025.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models Reasoning models better express their confidence, 2025

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T10:38:05.292046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2acd94a5-b29b-4172-b401-4f472583fc24 · outbound

This paper cites J., Wang, Z., Mallen, A., Basart, S., Koyejo, S., Song, D., Fredrikson, M., Kolter, J.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models J., Wang, Z., Mallen, A., Basart, S., Koyejo, S., Song, D., Fredrikson, M., Kolter, J

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:38:06.029672Z

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 ce335cbb-4e4f-4164-ad63-f60edd888e08 · outbound

This paper cites write newline.

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models write newline

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:38:05.813873Z

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.

Pith citing papers

Observation d94b862f-9d0a-46a8-8e48-25a4526a7381 · inbound

Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned Transformers cites this paper.

Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned Transformers When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T18:00:51.707342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c106958-39d9-4aca-85ba-031dcddc8406 · inbound

Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs cites this paper.

Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-05T15:52:45.041136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d7330bb-6195-47f7-9d55-0d3ac29e083c · inbound

DECOR: Auditing LLM Deception via Information Manipulation Theory cites this paper.

DECOR: Auditing LLM Deception via Information Manipulation Theory When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-20T06:28:05.389621Z

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 e4811b80-86b1-48d7-beab-a368e862aeaa · inbound

RogueAI: A Reverse Turing Test for Detecting Licensed AI Deception in Dialogue cites this paper.

RogueAI: A Reverse Turing Test for Detecting Licensed AI Deception in Dialogue When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-03T15:18:33.716480Z

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 88499384-a89c-4608-a2f1-9f5addf98a37 · inbound

What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates cites this paper.

What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models

Reference 116

Resolution: verified exact; arxiv_id, observed 2026-07-03T13:08:07.647083Z

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 54f538bb-6061-47d0-a0c1-f4f38945e484 · inbound

Transcoders for Investigating Deception in Language Models cites this paper.

Transcoders for Investigating Deception in Language Models When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T01:06:13.525747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8ada123-d371-4e1c-99e8-b656e1ef1880 · inbound

Risky Business: Measuring The Faithfulness-Safety Tension cites this paper.

Risky Business: Measuring The Faithfulness-Safety Tension When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-05T13:40:57.774902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.