Chain-of-Thought Reasoning In The Wild Is Not Always Faithful | Paper Citation Record

Observation 9194b23c-8816-44fa-a0e8-38533ac977b9 · inbound

Phi-4-reasoning Technical Report cites this paper.

Phi-4-reasoning Technical Report Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-06-01T03:02:49.618587Z

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 65660cc0-fbd5-49e6-a3ff-f2d982edfcc9 · inbound

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

A Survey on Large Language Models for Mathematical Reasoning Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:44.340730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a17aa33-fcff-43ff-a872-6e30272278cc · inbound

Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs cites this paper.

Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-06-01T03:02:49.618587Z

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 615326e2-1ec1-4e27-996c-c9fcaa96e469 · inbound

Answer-Centric or Reasoning-Driven? Uncovering the Latent Memory Anchor in LLMs cites this paper.

Answer-Centric or Reasoning-Driven? Uncovering the Latent Memory Anchor in LLMs Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T23:33:52.801644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4047ab3-1937-40f7-8b9c-f670e5675eb9 · inbound

Is Long-to-Short a Free Lunch? Investigating Inconsistency and Reasoning Efficiency in LRMs cites this paper.

Is Long-to-Short a Free Lunch? Investigating Inconsistency and Reasoning Efficiency in LRMs Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T23:10:24.498510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 311a0f42-6e0d-4e61-8cb5-2c1e3812b90f · inbound

KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality cites this paper.

KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-06-01T03:02:49.618587Z

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 2ad3bb70-9718-4362-9b7b-5b5f34ad5512 · 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 Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T22:03:50.831268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dddb8680-2d31-4975-acb9-d35b4364e831 · inbound

Are They All Good? Evaluating the Quality of CoTs in LLM-based Code Generation cites this paper.

Are They All Good? Evaluating the Quality of CoTs in LLM-based Code Generation Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T18:57:12.997242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cbfa818-0ff0-449f-8e6e-8defeacc35b9 · inbound

TinyTroupe: An LLM-powered Multiagent Persona Simulation Toolkit cites this paper.

TinyTroupe: An LLM-powered Multiagent Persona Simulation Toolkit Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-06-01T03:02:49.618587Z

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 53e75451-60cd-4f23-857a-77f6bd6da8f1 · inbound

TinyTroupe: An LLM-powered Multiagent Persona Simulation Toolkit cites this paper.

TinyTroupe: An LLM-powered Multiagent Persona Simulation Toolkit Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:07.947618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecf95395-fedf-4c66-8987-a59e164ad1b1 · inbound

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

Position: Intelligent Coding Systems Should Write Programs with Justifications Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T23:01:58.755678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87e6b6c7-e38f-4fa2-b7cf-efbaa83f6522 · inbound

Do Cognitively Interpretable Reasoning Traces Improve LLM Performance? cites this paper.

Do Cognitively Interpretable Reasoning Traces Improve LLM Performance? Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T17:40:52.629513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1331e4bc-038e-4a13-9748-b01e2c52454f · inbound

Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation? cites this paper.

Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation? Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T15:30:30.158836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19a9428a-3b77-4944-a35d-8b37187c5f34 · inbound

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control cites this paper.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:50.382652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdb19087-9a0a-42eb-939b-20c32f6f35da · inbound

CoreThink: A Symbolic Reasoning Layer to reason over Long Horizon Tasks with LLMs cites this paper.

CoreThink: A Symbolic Reasoning Layer to reason over Long Horizon Tasks with LLMs Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T13:05:31.857966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dd18d34-1be3-434d-8793-e115c674b165 · inbound

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models cites this paper.

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-05T10:39:04.414376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6edb149-d740-45bc-9538-5a21a51714b3 · inbound

A Survey of Reinforcement Learning for Large Reasoning Models cites this paper.

A Survey of Reinforcement Learning for Large Reasoning Models Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-06-01T03:02:49.618587Z

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 77f1045f-9409-4096-9730-639a51ae7717 · inbound

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

CLARity: Reasoning Consistency Alone Can Teach Reinforced Experts Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T10:40:42.437398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1acdbd2-4445-433e-8b26-90251c95d133 · inbound

Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation cites this paper.

Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T09:50:41.886859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f709fc83-dfe9-4e63-8e2c-1254a68959fb · inbound

Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations cites this paper.

Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-04T09:08:53.755726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7d357cd-022e-450a-8303-13b307615b75 · inbound

Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought cites this paper.

Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-06-01T03:02:49.618587Z

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 31e59c10-a00b-4c74-8dbc-1e53c2171a5e · inbound

Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought cites this paper.

Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T07:43:09.181699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6361836-f748-47cc-b3c4-a4e614fd20ac · inbound

Scaling Latent Reasoning via Looped Language Models cites this paper.

Scaling Latent Reasoning via Looped Language Models Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 74

Resolution: verified exact; arxiv_id, observed 2026-06-01T03:02:49.618587Z

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 406e97bc-d75b-4dc4-bcde-e8963e4f5691 · inbound

Scaling Latent Reasoning via Looped Language Models cites this paper.

Scaling Latent Reasoning via Looped Language Models Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-04T07:31:49.221545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d723168a-93a1-4914-9770-99db91369060 · inbound

Interpretability from the Ground Up: Stakeholder-Centric Design of Automated Scoring in Educational Assessments cites this paper.

Interpretability from the Ground Up: Stakeholder-Centric Design of Automated Scoring in Educational Assessments Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-06-01T03:02:49.618587Z

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 784a0bf0-189b-46ae-a61e-aee5a720143b · inbound

When AI Persuades: Adversarial Explanation Attacks on Human Trust in AI-Assisted Decision Making cites this paper.

When AI Persuades: Adversarial Explanation Attacks on Human Trust in AI-Assisted Decision Making Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-06-01T03:02:49.618587Z

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 acdeba73-909b-4153-8070-569ed35b01c1 · inbound

ReSS: Learning Reasoning Models for Tabular Data Prediction via Symbolic Scaffold cites this paper.

ReSS: Learning Reasoning Models for Tabular Data Prediction via Symbolic Scaffold Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-06-01T03:02:49.618587Z

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 ede4e4e2-5534-4676-af24-15b61800fd2b · inbound

ReSS: Learning Reasoning Models for Tabular Data Prediction via Symbolic Scaffold cites this paper.

ReSS: Learning Reasoning Models for Tabular Data Prediction via Symbolic Scaffold Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-06-01T03:02:49.618587Z

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 e25d97f8-ffe5-45e2-a9f8-e2f888310d97 · inbound

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

LLM Reasoning Is Latent, Not the Chain of Thought Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-06-01T03:02:49.618587Z

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 3e39f9fd-9175-45fd-8256-cf26c7a51918 · inbound

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

Compared to What? Baselines and Metrics for Counterfactual Prompting Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-06-01T03:02:49.618587Z

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 12b37a5b-f300-456e-a9ec-00c3ebcb2ccd · inbound

Confidence-Aware Alignment Makes Reasoning LLMs More Reliable cites this paper.

Confidence-Aware Alignment Makes Reasoning LLMs More Reliable Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-06-01T03:02:49.618587Z

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 87db8dcf-3462-467c-a315-c31a58610d26 · inbound

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

Evaluating the False Trust Engendered by LLM Explanations Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-06-01T03:02:49.618587Z

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 0de77f20-3079-4254-8484-40b09a7ed8fb · inbound

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

Evaluating the False Trust Engendered by LLM Explanations Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-06-01T03:02:49.618587Z

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 5fa3958e-b342-4153-adce-24cfe02f2460 · inbound

Deep Reasoning in General Purpose Agents via Structured Meta-Cognition cites this paper.

Deep Reasoning in General Purpose Agents via Structured Meta-Cognition Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 88

Resolution: verified exact; arxiv_id, observed 2026-06-01T03:02:49.618587Z

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 817312d5-2378-4b74-b334-5e8c9f5aaa83 · 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 Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-06-01T03:02:49.618587Z

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 bd88a687-d925-4417-9db9-72c31c0bdc41 · inbound

Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution cites this paper.

Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-06-01T03:02:49.618587Z

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 d8320dad-b0be-4e3b-918b-d58655a82e11 · 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 Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-06-01T03:02:49.618587Z

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 891d14cb-99e1-4ffe-a516-c78d6ebd3e47 · inbound

Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning cites this paper.

Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-06-30T15:34:48.035904Z

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 3fe2150c-f828-4c41-87a6-2444b1bc2959 · inbound

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

Understanding and Mitigating Premature Confidence for Better LLM Reasoning Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-06-30T14:04:44.414531Z

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 015fee4b-cd2e-466c-91cf-5c19db65ad7a · inbound

Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy cites this paper.

Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-06-29T21:53:59.509298Z

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 e335a703-8459-43b5-bf75-eb80c96cf4cd · inbound

What Does Chain-of-Thought Contribute at Probe Time? Evidence for Local Co-Occurrence Activation cites this paper.

What Does Chain-of-Thought Contribute at Probe Time? Evidence for Local Co-Occurrence Activation Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-06-29T17:33:45.512215Z

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 919221a4-713c-4b7c-a11c-cac4fe10542a · inbound

What Does Chain-of-Thought Contribute at Probe Time? Evidence for Local Co-Occurrence Activation cites this paper.

What Does Chain-of-Thought Contribute at Probe Time? Evidence for Local Co-Occurrence Activation Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T13:08:40.058805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f65a3bd3-0475-4cd6-ba98-10aa0fe87439 · inbound

Forecasting Future Behavior as a Learning Task cites this paper.

Forecasting Future Behavior as a Learning Task Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-07-03T06:07:41.352894Z

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 ce64ce93-e475-4f2d-9290-61b6ba32b49e · 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 Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 55

Resolution: verified exact; local_arxiv, observed 2026-07-03T11:18:03.828935Z

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 447b601f-3e95-4e48-9367-8fbd2feb2c6d · 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 Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-03T16:58:43.406916Z

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 d2805322-f0dd-4723-9ca3-bf133385f47b · inbound

Answer Engineering: Local Trajectory Editing for Protocol-Constrained Decision Making in Large Language Models cites this paper.

Answer Engineering: Local Trajectory Editing for Protocol-Constrained Decision Making in Large Language Models Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-07-04T06:49:37.545786Z

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 95de15de-01a6-4a55-b4fe-52017bee5406 · inbound

Do Thinking Tokens Help with Safety? cites this paper.

Do Thinking Tokens Help with Safety? Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-07-04T17:30:00.655029Z

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 7bcea873-d6aa-4b6f-87f9-b44b317af510 · inbound

Where Do CoT Training Gains Land in LLM based Agents? cites this paper.

Where Do CoT Training Gains Land in LLM based Agents? Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-04T13:49:51.539339Z

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 c6c31034-9380-40e9-84d2-dae4f9cd07e9 · inbound

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

Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 83

Resolution: verified exact; local_arxiv, observed 2026-07-02T12:46:56.219034Z

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 a3dd1913-a81d-4e3c-a99e-1394705840ac · inbound

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

Reading Between the Dots: Decoding Hidden Computation across Filler Tokens Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 3

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 b1756608-8180-4040-92fc-3538414a25fe · inbound

Context-Masked Truncated Reasoning Audits for Answer-Key Dependence in LLM Tutors cites this paper.

Context-Masked Truncated Reasoning Audits for Answer-Key Dependence in LLM Tutors Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-11T17:05:29.695180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2add7b3-a570-4564-b51a-b01d972bd8da · inbound

Do Vision-Language-Action Models Mean What They Say? On the Role of Faithfulness in Embodied Reasoning cites this paper.

Do Vision-Language-Action Models Mean What They Say? On the Role of Faithfulness in Embodied Reasoning Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-11T15:16:38.426751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fd9aef5-5d36-495a-842a-128c892cf410 · inbound

Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring cites this paper.

Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 79

Resolution: verified exact; local_arxiv, observed 2026-07-10T00:56:41.060161Z

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 ec75fd25-568c-4c41-b2aa-3a13edd5f3dc · inbound

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

Length Penalties Make Chain-of-Thought Less Monitorable Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 47

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 a4cd360a-c10f-419a-b72d-18e4acb12420 · inbound

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

Length Penalties Make Chain-of-Thought Less Monitorable Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T08:06:10.759079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82ffa36e-827e-434b-853f-66e4ade443c8 · inbound

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

Length Penalties Make Chain-of-Thought Less Monitorable Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:26.776436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e9ee9b0-a0b5-4d20-9c68-2ca6b429b1b9 · inbound

Controlled Reformulation Testing for Logical Consistency in Large Language Models cites this paper.

Controlled Reformulation Testing for Logical Consistency in Large Language Models Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T01:55:04.455545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05f8c993-b201-41c7-b42c-5b575121ab38 · inbound

Mechanistic Attention Guidance for Agent Memory Refinement cites this paper.

Mechanistic Attention Guidance for Agent Memory Refinement Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T17:30:38.509216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7de66025-d265-4f54-b74a-364463398050 · inbound

One Student, Many Teachers: Multi-Task On-Policy Distillation via Soft-Prompt Privileged Context cites this paper.

One Student, Many Teachers: Multi-Task On-Policy Distillation via Soft-Prompt Privileged Context Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T09:22:00.540306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0106a6b7-a635-43f4-bb0a-93dca770eb44 · inbound

Not All LLM Reasoning is Visible in the Chain-of-Thought cites this paper.

Not All LLM Reasoning is Visible in the Chain-of-Thought Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T04:14:41.224620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 656cdbbf-656c-4531-827b-b2f40dc799bf · inbound

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong cites this paper.

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-30T21:44:25.171383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 087608a2-96ff-469a-9bdd-0e8c391224a5 · inbound

Why Public Service AI Governance Frameworks Risk Failing in the Age of General-Purpose AI: Lessons from Policing cites this paper.

Why Public Service AI Governance Frameworks Risk Failing in the Age of General-Purpose AI: Lessons from Policing Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T01:52:56.666840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7d0c5bc-7b1a-4d33-8a3a-a2e66e218315 · inbound

A Reference-Free Score for Detecting Silent Reasoning Failures in Large Language Models cites this paper.

A Reference-Free Score for Detecting Silent Reasoning Failures in Large Language Models Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T02:41:53.515878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfb39c0b-f025-446f-8f35-12f215f3da91 · inbound

On the Generalization of Steering Vectors for Chain-of-Thought Faithfulness cites this paper.

On the Generalization of Steering Vectors for Chain-of-Thought Faithfulness Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T14:26:27.978746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5540de9-5ae7-4408-a903-f8736ba54a1b · inbound

Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs cites this paper.

Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T00:13:47.033588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96f401f5-f452-466e-8c89-fc3e111287e3 · inbound

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings cites this paper.

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 f6abacef-696b-4345-84ad-a1a670263898 · inbound

Transformers Struggle to Use Their Emergent World Models: Revisiting the Tower of Hanoi, and the Illusion of Thinking cites this paper.

Transformers Struggle to Use Their Emergent World Models: Revisiting the Tower of Hanoi, and the Illusion of Thinking Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-10T15:20:56.946510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers