Paper Citation Record · LEDGER

Preventing Language Models From Hiding Their Reasoning

As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 17 inbound Pith citation observations for arXiv:2310.18512.

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

pith.paper-citation-record.v1
2310.18512 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 17 of 17 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 17 of 17 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-10T16:41:22.141140Z

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

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

2
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 06a3266a-2cee-4b34-8223-3dcf28092312 · inbound

Alignment faking in large language models cites this paper.

Alignment faking in large language models Preventing Language Models From Hiding Their Reasoning

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T22:50:11.946185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 42aceb86-a0bb-481f-b238-dfaa9b454102 · inbound

MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking cites this paper.

MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking Preventing Language Models From Hiding Their Reasoning

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-10T16:41:22.141140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67be5f1f-89f9-49de-b9de-97969602ee1a · 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 Preventing Language Models From Hiding Their Reasoning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T22:03:54.383501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31c74176-d014-4c06-b0de-dc539a7e1980 · inbound

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

When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors Preventing Language Models From Hiding Their Reasoning

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-06T19:34:55.843136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bf448f2-6dcd-4830-905a-704b7d8ece0f · inbound

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

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety Preventing Language Models From Hiding Their Reasoning

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:19:44.761298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1f21787f-b906-4a30-bddd-cd0a03fb9630 · inbound

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

Diagnosing Pathological Chain-of-Thought in Reasoning Models Preventing Language Models From Hiding Their Reasoning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T23:26:30.628642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d71b3f4-33e8-4484-be57-83039ffb90f6 · inbound

Detecting and Suppressing Reward Hacking with Gradient Fingerprints cites this paper.

Detecting and Suppressing Reward Hacking with Gradient Fingerprints Preventing Language Models From Hiding Their Reasoning

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T08:22:37.572076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation bc293fa8-4e7f-4c12-b12d-7002267f0c87 · 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 Preventing Language Models From Hiding Their Reasoning

Reference 44

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T06:32:24.393171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 03f5e166-a971-4774-ad45-9f8e85f5c4a0 · inbound

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

Understanding and Mitigating Premature Confidence for Better LLM Reasoning Preventing Language Models From Hiding Their Reasoning

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T14:04:44.385114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f752b928-caa1-4e30-a480-7f9f7a324065 · inbound

Conceptual Steganography cites this paper.

Conceptual Steganography Preventing Language Models From Hiding Their Reasoning

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-06-29T18:53:51.621461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4ad341bd-0be5-4de4-80fe-cc441e544fac · inbound

A Note on the Strategic Confinement Problem cites this paper.

A Note on the Strategic Confinement Problem Preventing Language Models From Hiding Their Reasoning

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-06-27T17:31:06.842944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 122c54e7-21d8-478a-b498-880e09ae5697 · inbound

CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs cites this paper.

CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs Preventing Language Models From Hiding Their Reasoning

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-03T05:07:39.423665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e8a0d71d-82ff-46f5-ac74-7566df5fb004 · inbound

Comparing Linear Probes with Mahalanobis Cosine Similarity cites this paper.

Comparing Linear Probes with Mahalanobis Cosine Similarity Preventing Language Models From Hiding Their Reasoning

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-07-04T01:09:18.923298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0b3af246-dbce-44ae-b803-3e0a0600999d · 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 Preventing Language Models From Hiding Their Reasoning

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-07-01T16:25:50.102094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3fd1c6e4-9836-428f-8115-7be3bbfda935 · inbound

Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation cites this paper.

Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation Preventing Language Models From Hiding Their Reasoning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T23:29:50.791477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9df42a77-34b4-467c-8d69-28d57c845de5 · inbound

Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations cites this paper.

Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations Preventing Language Models From Hiding Their Reasoning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:59.970123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7dbb06f-cfdd-481b-a3dc-6ebe56957df8 · 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 Preventing Language Models From Hiding Their Reasoning

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T04:14:45.406064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.