Reasoning Models Don't Always Say What They Think | Paper Citation Record

Observation b0d84af8-53d5-4908-8fbe-29a7d337e092 · inbound

Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring cites this paper.

Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring Reasoning Models Don't Always Say What They Think

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-08T21:06:55.819737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e584c35e-928a-4b1c-b8b7-db77b142f3fb · inbound

Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models? cites this paper.

Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models? Reasoning Models Don't Always Say What They Think

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T14:52:40.853592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eab382ac-af4b-45d1-a118-f797cd15a0b5 · inbound

OpenReview Should be Protected and Leveraged as a Community Asset for Research in the Era of Large Language Models cites this paper.

OpenReview Should be Protected and Leveraged as a Community Asset for Research in the Era of Large Language Models Reasoning Models Don't Always Say What They Think

Reference 158

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:48.472560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7f3d973-79fb-47d3-8a48-616c1f3674ff · inbound

Strategic Reflectivism In Intelligent Systems cites this paper.

Strategic Reflectivism In Intelligent Systems Reasoning Models Don't Always Say What They Think

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T12:59:21.225815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fea7934-502b-4000-97ef-23decd091a22 · inbound

Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment cites this paper.

Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment Reasoning Models Don't Always Say What They Think

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T12:02:40.820858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d658fca0-f320-4b32-9929-f9116c6da8c0 · inbound

Why do AI agents communicate in human language? cites this paper.

Why do AI agents communicate in human language? Reasoning Models Don't Always Say What They Think

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T11:21:49.677629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3897f119-b35d-4837-b2a0-23f98bbac994 · inbound

The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity cites this paper.

The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity Reasoning Models Don't Always Say What They Think

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-15T16:10:31.664485Z

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 cf7e1040-bede-4c42-b203-413bc87f8b2f · inbound

A Survey on Large Language Models for Mathematical Reasoning cites this paper.

A Survey on Large Language Models for Mathematical Reasoning Reasoning Models Don't Always Say What They Think

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:45.045847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0df62072-9738-438c-969c-a79048aecda3 · inbound

AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions cites this paper.

AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions Reasoning Models Don't Always Say What They Think

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-07T05:01:08.327546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2170fee5-fc74-4209-a415-4a639f0c0b89 · inbound

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

Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning Reasoning Models Don't Always Say What They Think

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T22:03:51.958119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 536ecd38-a839-4c65-af8c-9b27a028b125 · inbound

Listener-Rewarded Thinking in VLMs for Image Preferences cites this paper.

Listener-Rewarded Thinking in VLMs for Image Preferences Reasoning Models Don't Always Say What They Think

Reference 6

Resolution: metadata mismatch; local_arxiv, observed 2026-05-19T07:42:09.240618Z

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 465cd223-356b-406d-9dee-178694ad797e · inbound

Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models cites this paper.

Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models Reasoning Models Don't Always Say What They Think

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T21:37:52.644431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40f0cd15-8704-4053-a0ff-37067452c6a2 · inbound

Is Reasoning All You Need? Probing Bias in the Age of Reasoning Language Models cites this paper.

Is Reasoning All You Need? Probing Bias in the Age of Reasoning Language Models Reasoning Models Don't Always Say What They Think

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T20:25:53.363109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88018fc3-e8f8-4346-9d24-ad3dee5f9bf8 · inbound

Lessons from a Chimp: AI "Scheming" and the Quest for Ape Language cites this paper.

Lessons from a Chimp: AI "Scheming" and the Quest for Ape Language Reasoning Models Don't Always Say What They Think

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T20:18:15.499693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caa0589b-8752-4308-b471-8fef84c0721a · inbound

WebGuard: Building a Generalizable Guardrail for Web Agents cites this paper.

WebGuard: Building a Generalizable Guardrail for Web Agents Reasoning Models Don't Always Say What They Think

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T16:12:47.648456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5795bd41-e36f-4944-a6bc-19e2b558e834 · inbound

Re:Form -- Reducing Human Annotations in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny cites this paper.

Re:Form -- Reducing Human Annotations in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny Reasoning Models Don't Always Say What They Think

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T15:20:10.865469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef73b372-82cc-494e-bfc6-1fdb4ff1aad1 · inbound

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks cites this paper.

Lightweight Language Models are Prone to Reasoning Errors for Complex Computational Phenotyping Tasks Reasoning Models Don't Always Say What They Think

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T11:06:07.060768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 640802df-da7a-4574-9bb4-b6d7ea69a610 · inbound

Position: Intelligent Coding Systems Should Write Programs with Justifications cites this paper.

Position: Intelligent Coding Systems Should Write Programs with Justifications Reasoning Models Don't Always Say What They Think

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T23:01:59.326685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acfa9999-7359-4316-860a-4b79b5086acf · inbound

Reliable Weak-to-Strong Monitoring of LLM Agents cites this paper.

Reliable Weak-to-Strong Monitoring of LLM Agents Reasoning Models Don't Always Say What They Think

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T15:53:48.111145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e706203d-4698-45ef-9caf-4a22f187b0d5 · inbound

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations cites this paper.

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations Reasoning Models Don't Always Say What They Think

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T19:12:05.814286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3653af64-4892-4a1b-a832-592267de95d2 · inbound

Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight cites this paper.

Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight Reasoning Models Don't Always Say What They Think

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T17:40:08.174781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33013157-cb8a-442f-9429-a3e535258762 · inbound

Context Is What You Need: The Maximum Effective Context Window for Real World Limits of LLMs cites this paper.

Context Is What You Need: The Maximum Effective Context Window for Real World Limits of LLMs Reasoning Models Don't Always Say What They Think

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-18T14:52:41.098958Z

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 399715de-4411-4b6e-a0b8-7346bfde06b6 · inbound

CLARity: Reasoning Consistency Alone Can Teach Reinforced Experts cites this paper.

CLARity: Reasoning Consistency Alone Can Teach Reinforced Experts Reasoning Models Don't Always Say What They Think

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T10:40:42.937652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16b83c19-f98d-4cdb-8de1-2f7b2e26fe91 · inbound

MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes cites this paper.

MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes Reasoning Models Don't Always Say What They Think

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-04T09:16:39.944551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0d2b242-9c7e-42cc-8bd1-5d10b8716736 · inbound

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning cites this paper.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Reasoning Models Don't Always Say What They Think

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-18T05:12:23.661588Z

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 b41a6e13-c940-409a-8066-8b6103ea7860 · inbound

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning cites this paper.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Reasoning Models Don't Always Say What They Think

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-21T20:10:34.943343Z

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 b4076495-9561-4ac2-a970-59b3cd42d405 · inbound

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning cites this paper.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Reasoning Models Don't Always Say What They Think

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:05.547904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 962c22c5-bc25-4353-8cf6-52aa84e33783 · inbound

Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models cites this paper.

Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models Reasoning Models Don't Always Say What They Think

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T08:15:49.310593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15d4e5a5-a2dc-40f9-b01b-c4b79c422fd2 · inbound

Does the Model Say What the Data Says? A Simple Heuristic for Model Data Alignment cites this paper.

Does the Model Say What the Data Says? A Simple Heuristic for Model Data Alignment Reasoning Models Don't Always Say What They Think

Reference 7

Resolution: metadata mismatch; local_arxiv, observed 2026-05-17T04:08:59.918559Z

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 e2f94947-bc2e-4e8a-9c83-19f530296e93 · inbound

TIME: Temporally Intelligent Meta-reasoning Engine for Context-Triggered Explicit Reasoning cites this paper.

TIME: Temporally Intelligent Meta-reasoning Engine for Context-Triggered Explicit Reasoning Reasoning Models Don't Always Say What They Think

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-16T15:51:05.408221Z

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 5641d735-1424-4009-adf0-ba2249c06512 · inbound

Who Endorsed It? Measuring Authority Bias Across Expertise Levels in Language Models cites this paper.

Who Endorsed It? Measuring Authority Bias Across Expertise Levels in Language Models Reasoning Models Don't Always Say What They Think

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T09:37:06.392506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee42911f-be32-4e48-ad5d-dd22f84a1634 · inbound

Diagnosing Pathological Chain-of-Thought in Reasoning Models cites this paper.

Diagnosing Pathological Chain-of-Thought in Reasoning Models Reasoning Models Don't Always Say What They Think

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T23:26:29.156561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d052d0bd-f976-4c9f-a265-938c17305c5e · inbound

A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring cites this paper.

A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring Reasoning Models Don't Always Say What They Think

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T19:01:29.941429Z

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 0208175d-d09c-48dc-a403-16ac3708cd52 · inbound

Decoding the Critique Mechanism in Large Reasoning Models cites this paper.

Decoding the Critique Mechanism in Large Reasoning Models Reasoning Models Don't Always Say What They Think

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-05-25T06:50:27.509774Z

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 2d8925cd-3703-41b9-b029-08f8412cb9f6 · inbound

Measuring and curing reasoning rigidity: from decorative chain-of-thought to genuine faithfulness cites this paper.

Measuring and curing reasoning rigidity: from decorative chain-of-thought to genuine faithfulness Reasoning Models Don't Always Say What They Think

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-15T01:19:37.314423Z

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 d55b2e55-70c2-4e9f-9061-35dc68a0ca37 · inbound

Unreal Thinking: Chain-of-Thought Hijacking via Two-stage Backdoor cites this paper.

Unreal Thinking: Chain-of-Thought Hijacking via Two-stage Backdoor Reasoning Models Don't Always Say What They Think

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:18:01.027228Z

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 de4e5c57-26a4-4f22-9482-9b20151a6582 · inbound

Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges cites this paper.

Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges Reasoning Models Don't Always Say What They Think

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:18:01.027228Z

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 1ea296e3-d673-435b-a44f-d0104d2989fa · inbound

Reasoning Dynamics and the Limits of Monitoring Modality Reliance in Vision-Language Models cites this paper.

Reasoning Dynamics and the Limits of Monitoring Modality Reliance in Vision-Language Models Reasoning Models Don't Always Say What They Think

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:18:01.027228Z

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 15a8e342-8d97-447d-9c15-1b6d2ef2d903 · inbound

RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomography cites this paper.

RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomography Reasoning Models Don't Always Say What They Think

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:18:01.027228Z

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 d8fc774a-cf78-4284-9d2d-b5f5eb752d97 · inbound

RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomography cites this paper.

RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomography Reasoning Models Don't Always Say What They Think

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-12T19:46:06.596310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e9ff09e-a53d-40a6-90b6-00cb2d7f6d00 · inbound

LLM Reasoning Is Latent, Not the Chain of Thought cites this paper.

LLM Reasoning Is Latent, Not the Chain of Thought Reasoning Models Don't Always Say What They Think

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:18:01.027228Z

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 0ab57bc7-0888-4fce-bbdd-9816e3682432 · inbound

Meta-Aligner: Bidirectional Preference-Policy Optimization for Multi-Objective LLMs Alignment cites this paper.

Meta-Aligner: Bidirectional Preference-Policy Optimization for Multi-Objective LLMs Alignment Reasoning Models Don't Always Say What They Think

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:18:01.027228Z

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 f33251ec-8c90-4958-b480-5098bb9e89d9 · inbound

Risk Reporting for Developers' Internal AI Model Use cites this paper.

Risk Reporting for Developers' Internal AI Model Use Reasoning Models Don't Always Say What They Think

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:18:01.027228Z

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 f01d4a45-c755-4998-a99a-18d72c0bc82e · inbound

Knowledge Distillation Must Account for What It Loses cites this paper.

Knowledge Distillation Must Account for What It Loses Reasoning Models Don't Always Say What They Think

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:18:01.027228Z

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 8f6e77be-77d3-46cd-8720-222d36b097d2 · inbound

Knowledge Distillation Must Account for What It Loses cites this paper.

Knowledge Distillation Must Account for What It Loses Reasoning Models Don't Always Say What They Think

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:18:01.027228Z

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 00e2d83c-05f3-4c81-8a42-fd6a2a80bea4 · inbound

LLMs as ASP Programmers: Self-Correction Enables Task-Agnostic Nonmonotonic Reasoning cites this paper.

LLMs as ASP Programmers: Self-Correction Enables Task-Agnostic Nonmonotonic Reasoning Reasoning Models Don't Always Say What They Think

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:18:01.027228Z

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 4990d3c3-1389-4523-8f49-7d3fbc3c8800 · inbound

LLMs as ASP Programmers: Self-Correction Enables Task-Agnostic Nonmonotonic Reasoning cites this paper.

LLMs as ASP Programmers: Self-Correction Enables Task-Agnostic Nonmonotonic Reasoning Reasoning Models Don't Always Say What They Think

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T08:15:31.889929Z

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 27acda19-81ed-44f8-aa1c-25997ffef768 · inbound

Compared to What? Baselines and Metrics for Counterfactual Prompting cites this paper.

Compared to What? Baselines and Metrics for Counterfactual Prompting Reasoning Models Don't Always Say What They Think

Reference 48

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:18:01.027228Z

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 4d178c74-9cdb-4d7f-b9d5-76aa514d3719 · inbound

LLMs Should Not Yet Be Credited with Decision Explanation cites this paper.

LLMs Should Not Yet Be Credited with Decision Explanation Reasoning Models Don't Always Say What They Think

Reference 35

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:18:01.027228Z

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 443bff77-af49-4d53-abb8-cd4e56939818 · inbound

How Well Do LLMs Perform on the Simplest Long-Chain Reasoning Tasks: An Empirical Study on the Equivalence Class Problem cites this paper.

How Well Do LLMs Perform on the Simplest Long-Chain Reasoning Tasks: An Empirical Study on the Equivalence Class Problem Reasoning Models Don't Always Say What They Think

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:18:01.027228Z

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 905a0f71-d091-47e3-95df-9c3ae5bb58dc · inbound

Weighted Rules under the Stable Model Semantics cites this paper.

Weighted Rules under the Stable Model Semantics Reasoning Models Don't Always Say What They Think

Reference 54

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:18:01.027228Z

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 0890147d-6344-46d2-b322-4049a2b5ae88 · inbound

Medical Model Synthesis Architectures: A Case Study cites this paper.

Medical Model Synthesis Architectures: A Case Study Reasoning Models Don't Always Say What They Think

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:18:01.027228Z

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 1379bc7a-10d2-4f7c-bb5c-e48a32918246 · inbound

The Open-Box Fallacy: Why AI Deployment Needs a Calibrated Verification Regime cites this paper.

The Open-Box Fallacy: Why AI Deployment Needs a Calibrated Verification Regime Reasoning Models Don't Always Say What They Think

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:18:01.027228Z

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 97761f00-d0d9-4985-8d59-97100c0a2408 · inbound

Evaluating the False Trust Engendered by LLM Explanations cites this paper.

Evaluating the False Trust Engendered by LLM Explanations Reasoning Models Don't Always Say What They Think

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:18:01.027228Z

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 18fac225-07d6-4ccb-9680-e9ea6f8dc4c4 · inbound

Evaluating the False Trust Engendered by LLM Explanations cites this paper.

Evaluating the False Trust Engendered by LLM Explanations Reasoning Models Don't Always Say What They Think

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T21:53:47.150254Z

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 a6c9611b-04e9-46f6-a459-6342b5d71e30 · inbound

Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought Reasoning cites this paper.

Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought Reasoning Reasoning Models Don't Always Say What They Think

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:18:01.027228Z

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 298e183b-3d79-4f02-82bb-6a5e067eaa22 · inbound

When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel cites this paper.

When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel Reasoning Models Don't Always Say What They Think

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:18:01.027228Z

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 cd56e294-43cc-4ae3-a435-b5a8a2df0670 · inbound

Trace ideals and uniserial modules cites this paper.

Trace ideals and uniserial modules Reasoning Models Don't Always Say What They Think

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-15T11:13:18.391956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d5bbaf8-b8ad-4afa-8f43-8315ffe1a154 · inbound

Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs cites this paper.

Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs Reasoning Models Don't Always Say What They Think

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:18:01.027228Z

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 24b201f8-68b0-46b3-aafc-03a13b094649 · inbound

Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack cites this paper.

Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack Reasoning Models Don't Always Say What They Think

Reference 12

Resolution: metadata mismatch; local_arxiv, observed 2026-05-14T20:32:56.763151Z

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 7df7c8d5-f52b-4b61-afeb-25c3fea8e00a · inbound

CoT-Guard: Small Models for Strong Monitoring cites this paper.

CoT-Guard: Small Models for Strong Monitoring Reasoning Models Don't Always Say What They Think

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:18:01.027228Z

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 14716553-4a52-4687-a8cb-4b99e8b0d481 · inbound

What properties of reasoning supervision are associated with improved downstream model quality? cites this paper.

What properties of reasoning supervision are associated with improved downstream model quality? Reasoning Models Don't Always Say What They Think

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:18:01.027228Z

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 72267283-16c0-42eb-a0c2-f9d345092281 · inbound

Bridging Legal Interpretation and Formal Logic: Faithfulness, Assumption, and the Future of AI Legal Reasoning cites this paper.

Bridging Legal Interpretation and Formal Logic: Faithfulness, Assumption, and the Future of AI Legal Reasoning Reasoning Models Don't Always Say What They Think

Reference 19

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T05:25:04.091839Z

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 0c687c55-bc96-45e7-bec1-1d32ecf88a00 · inbound

SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades cites this paper.

SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades Reasoning Models Don't Always Say What They Think

Reference 86

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T02:33:32.331296Z

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 2bdf5cbd-10a0-41f5-aab4-9f883173e6a3 · inbound

LLMs in Qualitative Research: Opportunities, Limitations, and Practical Considerations cites this paper.

LLMs in Qualitative Research: Opportunities, Limitations, and Practical Considerations Reasoning Models Don't Always Say What They Think

Reference 16

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T16:03:33.155685Z

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 8b6033d8-dc92-4d3b-a1ed-04c886432846 · inbound

Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics cites this paper.

Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics Reasoning Models Don't Always Say What They Think

Reference 10

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T11:03:13.933854Z

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 5de14b6c-8e1f-4937-b5c3-9ee0e0899c22 · inbound

Probabilistic Tiny Recursive Model cites this paper.

Probabilistic Tiny Recursive Model Reasoning Models Don't Always Say What They Think

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:43:05.907422Z

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 b0f81a3c-ea24-4265-ba64-297fdec4f1e5 · inbound

Neurosymbolic Learning for Inference-Time Argumentation cites this paper.

Neurosymbolic Learning for Inference-Time Argumentation Reasoning Models Don't Always Say What They Think

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T05:13:03.466611Z

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 3338abe3-aff3-4a91-9965-6d1cae5ca940 · inbound

Neurosymbolic Learning for Inference-Time Argumentation cites this paper.

Neurosymbolic Learning for Inference-Time Argumentation Reasoning Models Don't Always Say What They Think

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T18:04:57.778119Z

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 72b1b6c2-5744-47eb-b542-7568fe0aa45f · inbound

On the Cost and Benefit of Chain of Thought: A Learning-Theoretic Perspective cites this paper.

On the Cost and Benefit of Chain of Thought: A Learning-Theoretic Perspective Reasoning Models Don't Always Say What They Think

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-21T05:13:58.676304Z

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 036aa5de-343c-4c35-a9cb-dba17059b446 · inbound

The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small Language Models cites this paper.

The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small Language Models Reasoning Models Don't Always Say What They Think

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-05-25T06:30:25.628182Z

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 93f60722-4667-4c28-bae8-603703863689 · inbound

Understanding and Mitigating Premature Confidence for Better LLM Reasoning cites this paper.

Understanding and Mitigating Premature Confidence for Better LLM Reasoning Reasoning Models Don't Always Say What They Think

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-06-30T14:04:44.433322Z

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 36615e4a-62d5-42f8-a29c-05719f7a5fe3 · inbound

Investigating the Interplay between Contextual and Parametric Chain-of-Thought Faithfulness under Optimization cites this paper.

Investigating the Interplay between Contextual and Parametric Chain-of-Thought Faithfulness under Optimization Reasoning Models Don't Always Say What They Think

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T12:24:39.911749Z

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 1267243d-b84a-4a28-a165-467128bd3df1 · inbound

Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth cites this paper.

Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth Reasoning Models Don't Always Say What They Think

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T12:04:39.043070Z

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 cc117f66-49fd-45d4-9e01-d012482f881e · inbound

The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure cites this paper.

The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure Reasoning Models Don't Always Say What They Think

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T12:03:24.170793Z

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 ea7361b8-2675-4d0b-b8d1-99997e495135 · inbound

"I Strongly Suspect This Website Is a Scam": Benchmarking PII Leakage and Detection without Defense in Autonomous Web Agents cites this paper.

"I Strongly Suspect This Website Is a Scam": Benchmarking PII Leakage and Detection without Defense in Autonomous Web Agents Reasoning Models Don't Always Say What They Think

Reference 118

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T19:42:36.153240Z

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 5a3e24ab-bec8-4d1b-b8b5-2164b985e945 · inbound

Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs cites this paper.

Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs Reasoning Models Don't Always Say What They Think

Reference 46

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T19:52:35.744075Z

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 14c8dcfc-e9df-4fe1-b08c-47d49a33643b · inbound

Quantifying Faithful Confidence Expression in Large Reasoning Models cites this paper.

Quantifying Faithful Confidence Expression in Large Reasoning Models Reasoning Models Don't Always Say What They Think

Reference 6

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T03:06:29.237014Z

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 0edb1f89-ee21-4a21-811b-fe05be39555c · inbound

ZERO-APT: A Closed-Loop Adversarial Framework for LLM-Driven Automated Penetration Testing under Intelligent Defense cites this paper.

ZERO-APT: A Closed-Loop Adversarial Framework for LLM-Driven Automated Penetration Testing under Intelligent Defense Reasoning Models Don't Always Say What They Think

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-07-02T13:16:58.775410Z

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 abf2824c-88dc-4bea-8a86-df21dcbead16 · inbound

The Self-Correction Illusion: Role Relabeling Gates Explicit Error Flagging in Large Language Models cites this paper.

The Self-Correction Illusion: Role Relabeling Gates Explicit Error Flagging in Large Language Models Reasoning Models Don't Always Say What They Think

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T01:31:29.339523Z

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 b22e2154-4f51-47c1-a388-6dbf500856e1 · inbound

From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents cites this paper.

From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents Reasoning Models Don't Always Say What They Think

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-07-02T13:36:59.388654Z

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 9efaf398-c88f-4b7f-aaff-b12045c5eb38 · inbound

From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents cites this paper.

From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents Reasoning Models Don't Always Say What They Think

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T12:19:46.889450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ced19d64-699c-42a9-9dfb-ba8fc5a9e584 · inbound

Sycophancy Towards Researchers Drives Performative Misalignment cites this paper.

Sycophancy Towards Researchers Drives Performative Misalignment Reasoning Models Don't Always Say What They Think

Reference 63

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T22:27:26.205760Z

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 a6ef89e3-3b6c-49e2-9372-19cded203eeb · inbound

Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization cites this paper.

Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization Reasoning Models Don't Always Say What They Think

Reference 239

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T01:37:30.562997Z

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 ed797390-a567-404b-af25-f504bd1c365f · inbound

The Distributed Detectability Band Against Marginal-Preserving Attacks cites this paper.

The Distributed Detectability Band Against Marginal-Preserving Attacks Reasoning Models Don't Always Say What They Think

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-07-03T05:57:41.849792Z

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 f4fc79be-0cac-4a79-9e02-5734febcfbbf · inbound

Observable Patterns Are Not Explanations: A Causal-Geometric Analysis of Latent Reasoning Models cites this paper.

Observable Patterns Are Not Explanations: A Causal-Geometric Analysis of Latent Reasoning Models Reasoning Models Don't Always Say What They Think

Reference 30

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T11:18:03.796570Z

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 60250f88-3172-43ba-bf75-dd6341c2c6f1 · inbound

Beyond Accuracy: Measuring Bias Acknowledgment in Chain-of-Thought Reasoning for Responsible AI Evaluation cites this paper.

Beyond Accuracy: Measuring Bias Acknowledgment in Chain-of-Thought Reasoning for Responsible AI Evaluation Reasoning Models Don't Always Say What They Think

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T16:58:43.404342Z

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 8e9fc536-173e-4202-ad20-be7a769556ad · inbound

Know Your Limits : On the Faithfulness of LLMs as Solvers and Autoformalizers in Legal Reasoning cites this paper.

Know Your Limits : On the Faithfulness of LLMs as Solvers and Autoformalizers in Legal Reasoning Reasoning Models Don't Always Say What They Think

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T17:18:43.460462Z

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 166f1bd7-68e5-493a-8294-b0190d2ace62 · inbound

Analyzing the Narration Gap in LLM-Solver Loops cites this paper.

Analyzing the Narration Gap in LLM-Solver Loops Reasoning Models Don't Always Say What They Think

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-06-26T20:49:57.677402Z

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 e3156763-063a-496d-a562-cc7412994ac9 · inbound

Local Causal Attribution of Chain-of-Thought Reasoning cites this paper.

Local Causal Attribution of Chain-of-Thought Reasoning Reasoning Models Don't Always Say What They Think

Reference 6

Resolution: metadata mismatch; local_arxiv, observed 2026-06-26T12:49:29.099013Z

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 1cc15de3-a976-4434-bcec-2e1b23359500 · inbound

Against Proxy Optimization cites this paper.

Against Proxy Optimization Reasoning Models Don't Always Say What They Think

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T10:49:46.634634Z

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 1023fca4-0c2c-4ba5-bf14-f47e8ba7b344 · inbound

How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation cites this paper.

How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation Reasoning Models Don't Always Say What They Think

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T11:14:36.929953Z

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 19ccb1b6-dec5-480c-a109-8a5ce6b01850 · inbound

What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs cites this paper.

What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs Reasoning Models Don't Always Say What They Think

Reference 133

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T16:25:50.038326Z

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 bea6fe0e-0506-4155-ba9b-1b29eb4c9774 · inbound

Defeat Devices in AI Systems cites this paper.

Defeat Devices in AI Systems Reasoning Models Don't Always Say What They Think

Reference 12

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T08:44:27.899211Z

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 cf4e6467-6a82-45aa-a571-d41bfbbb3270 · inbound

Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision cites this paper.

Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision Reasoning Models Don't Always Say What They Think

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T10:35:42.816633Z

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 3c96079a-738b-489f-9f4e-b7300b8b2eb0 · inbound

Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates cites this paper.

Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates Reasoning Models Don't Always Say What They Think

Reference 82

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T12:46:56.222938Z

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 632a689a-da3f-445c-bf59-005be81801ac · inbound

Reading Between the Dots: Decoding Hidden Computation across Filler Tokens cites this paper.

Reading Between the Dots: Decoding Hidden Computation across Filler Tokens Reasoning Models Don't Always Say What They Think

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-12T02:02:49.492856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80f741cc-f051-4447-8d5a-6a40f24b9ea1 · inbound

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets cites this paper.

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets Reasoning Models Don't Always Say What They Think

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-07-10T11:57:03.259382Z

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 f7628fda-e636-4363-ae46-64d25abe2a80 · inbound

Length Penalties Make Chain-of-Thought Less Monitorable cites this paper.

Length Penalties Make Chain-of-Thought Less Monitorable Reasoning Models Don't Always Say What They Think

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-14T15:45:54.532529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f25cadd4-831e-4196-aafc-d85e71457bf1 · inbound

Length Penalties Make Chain-of-Thought Less Monitorable cites this paper.

Length Penalties Make Chain-of-Thought Less Monitorable Reasoning Models Don't Always Say What They Think

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-02T08:06:10.773565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers