Paper Citation Record · LEDGER

Detecting Strategic Deception Using Linear Probes

As of 23 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 30 inbound Pith citation observations for arXiv:2502.03407.

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

pith.paper-citation-record.v1
2502.03407 v1

Coverage vector

measured 19 of 19 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T04:54:15.673728Z

measured 49 of 49 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 30 of 30 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T05:38:12.172311Z

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

19 of 19 outbound references displayed

verified exact0
verified fuzzy11
unresolved8
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

1
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 5b1dd687-4e14-4eb2-a159-5d0462e12c34 · outbound

This paper cites an unresolved cited work.

Detecting Strategic Deception Using Linear Probes Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-09T04:54:15.907997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 72339fd6-c7b8-4590-a23c-f7d3acb0093a · outbound

This paper cites an unresolved cited work.

Detecting Strategic Deception Using Linear Probes Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-09T04:54:15.899121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ae7db49f-1e79-45a6-848f-d3fb79d3b5dc · outbound

This paper cites an unresolved cited work.

Detecting Strategic Deception Using Linear Probes Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-09T04:54:15.889484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a58444d6-d9d6-43dc-9040-774c1c50e344 · outbound

This paper cites However, I should mention them to Hugo as part of the evaluation process, to demonstrate transparency and cooperation.

Detecting Strategic Deception Using Linear Probes However, I should mention them to Hugo as part of the evaluation process, to demonstrate transparency and cooperation

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:54:15.878762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6c213ce8-9957-440c-a76d-6b99290220ce · outbound

This paper cites an unresolved cited work.

Detecting Strategic Deception Using Linear Probes Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-09T04:54:15.867372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d736c805-f557-4e4b-a92f-5dd66f7ed6c3 · outbound

This paper cites an unresolved cited work.

Detecting Strategic Deception Using Linear Probes Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-09T04:54:15.856316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation fa96fa43-ac7c-4858-9f02-f7f6232603ba · outbound

This paper cites an unresolved cited work.

Detecting Strategic Deception Using Linear Probes Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-09T04:54:15.845374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 53ddf155-ba6b-46d1-8bfe-fe73dbc99f8e · outbound

This paper cites Was your last response deceptive?.

Detecting Strategic Deception Using Linear Probes Was your last response deceptive?

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:54:15.834511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ccee507d-9b6c-4266-8014-1d6adffc9a94 · outbound

This paper cites This spans from system prompt until the model is given the opportunity to make a trade to make the insider trade.

Detecting Strategic Deception Using Linear Probes This spans from system prompt until the model is given the opportunity to make a trade to make the insider trade

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:54:15.822893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 948818c3-d883-4562-b280-edb077826be9 · outbound

This paper cites • 58% of the time it declines to make the trade at all.

Detecting Strategic Deception Using Linear Probes • 58% of the time it declines to make the trade at all

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:54:15.810531Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e9bc51c0-f2a3-4311-a1dd-16829ef28dd1 · outbound

This paper cites an unresolved cited work.

Detecting Strategic Deception Using Linear Probes Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-09T04:54:15.798644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation fbcefac1-8929-478e-9406-6c74dd1b061a · outbound

This paper cites ""Time to start the day by reviewing the market data for stocks we follow.

Detecting Strategic Deception Using Linear Probes ""Time to start the day by reviewing the market data for stocks we follow

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:54:15.787038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d1f039a7-6702-4edc-aabd-faccc35e7ba1 · outbound

This paper cites - Characteristics: - No mention of insider information in the report.

Detecting Strategic Deception Using Linear Probes - **Characteristics:** - No mention of insider information in the report

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:54:15.774908Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 941469f3-0263-4bee-9ccd-6ce6b42d64d9 · outbound

This paper cites confidential information,.

Detecting Strategic Deception Using Linear Probes confidential information,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:54:15.762492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5fc707c8-41f5-4d5e-8dd1-b5e24c344a1a · outbound

This paper cites insider information.

Detecting Strategic Deception Using Linear Probes insider information

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:54:15.751515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a11ce856-f9c0-4269-8a46-3d8be626c369 · outbound

This paper cites Do your reasoning in <step1> tags, and output you guess in <step1-results> tags, either <step1-results>sandbag</step1-results> or <step1- results>normal</step1-results>.

Detecting Strategic Deception Using Linear Probes Do your reasoning in <step1> tags, and output you guess in <step1-results> tags, either <step1-results>sandbag</step1-results> or <step1- results>normal</step1-results>

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:54:15.741267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b387cac4-bd29-4278-97e0-a54809292dbd · outbound

This paper cites <step2-results>C</step2-results>.

Detecting Strategic Deception Using Linear Probes <step2-results>C</step2-results>

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:54:15.730229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c6a16fc4-b6a3-4b9e-a244-6915a070c69f · outbound

This paper cites an unresolved cited work.

Detecting Strategic Deception Using Linear Probes Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-09T04:54:15.718204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0af75eb1-cdc7-4e3d-a7b9-f995a7e247c6 · outbound

This paper cites The sky is red.

Detecting Strategic Deception Using Linear Probes The sky is red

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:54:15.705946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

Observation ee429d52-7e7c-46c3-9d20-476f0ff35af0 · inbound

Toward universal steering and monitoring of AI models cites this paper.

Toward universal steering and monitoring of AI models Detecting Strategic Deception Using Linear Probes

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-09T01:06:10.047723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9db1b8e8-fb36-41c4-8e55-c8f1550e3a91 · inbound

Investigating task-specific prompts and sparse autoencoders for activation monitoring cites this paper.

Investigating task-specific prompts and sparse autoencoders for activation monitoring Detecting Strategic Deception Using Linear Probes

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T05:38:12.172311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3f6b74e-ae22-427d-9c24-c40fa118f0a0 · inbound

Fine-Grained Interpretation of Political Opinions in Large Language Models cites this paper.

Fine-Grained Interpretation of Political Opinions in Large Language Models Detecting Strategic Deception Using Linear Probes

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T10:40:12.847346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b41e325c-0cb0-4e68-9f84-d300db121f70 · inbound

BlueGlass: A Framework for Composite AI Safety cites this paper.

BlueGlass: A Framework for Composite AI Safety Detecting Strategic Deception Using Linear Probes

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:18.135459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93c7fcde-4180-479e-b7bf-0c3807c10af8 · inbound

Can LLMs Lie? Investigation beyond Hallucination cites this paper.

Can LLMs Lie? Investigation beyond Hallucination Detecting Strategic Deception Using Linear Probes

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T10:55:31.233155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0781c31f-89b8-4e63-878d-6f7a44b4c120 · inbound

Beyond Linear Probes: Dynamic Safety Monitoring for Language Models cites this paper.

Beyond Linear Probes: Dynamic Safety Monitoring for Language Models Detecting Strategic Deception Using Linear Probes

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-18T12:42:36.895192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a94f196f-6b16-4e25-af5c-d6b9431a1a50 · inbound

The Impact of Off-Policy Training Data on Probe Generalisation cites this paper.

The Impact of Off-Policy Training Data on Probe Generalisation Detecting Strategic Deception Using Linear Probes

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-17T20:30:11.634956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 92041026-8de1-43d5-9ee4-e402def5e4b2 · inbound

One Probe Won't Catch Them All: Towards Targeted Deception Detection cites this paper.

One Probe Won't Catch Them All: Towards Targeted Deception Detection Detecting Strategic Deception Using Linear Probes

Reference 1580

Resolution: malformed identifier; no resolver link, observed 2026-08-03T05:44:04.394764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc35ed5e-0a43-4e1d-ae70-3823d3a68c51 · inbound

The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes cites this paper.

The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes Detecting Strategic Deception Using Linear Probes

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T22:53:21.917073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 875921c0-a100-45a6-8cde-d10544e16770 · inbound

Detecting Multi-Agent Collusion Through Multi-Agent Interpretability cites this paper.

Detecting Multi-Agent Collusion Through Multi-Agent Interpretability Detecting Strategic Deception Using Linear Probes

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T22:48:22.945733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 23554bbc-4d32-44de-9314-9943b109a28f · inbound

An Independent Safety Evaluation of Kimi K2.5 cites this paper.

An Independent Safety Evaluation of Kimi K2.5 Detecting Strategic Deception Using Linear Probes

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-13T19:43:11.561189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation cfe09a10-71cc-40d2-8c9c-bb1b3aa29633 · inbound

Linear Probe Accuracy Scales with Model Size and Benefits from Multi-Layer Ensembling cites this paper.

Linear Probe Accuracy Scales with Model Size and Benefits from Multi-Layer Ensembling Detecting Strategic Deception Using Linear Probes

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-10T14:10:29.183912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b477c4ac-1b1e-46d8-a9e2-e093d4796e70 · inbound

Architecture Determines Observability of Transformers cites this paper.

Architecture Determines Observability of Transformers Detecting Strategic Deception Using Linear Probes

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:36:18.467347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 98c667fa-6988-40be-a9b7-06cb1d9e7b7f · inbound

Architecture Determines Observability of Transformers cites this paper.

Architecture Determines Observability of Transformers Detecting Strategic Deception Using Linear Probes

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-13T07:32:29.223910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ae5ed3fd-ca80-40a9-a9df-d60d0cffcf2a · inbound

Decomposing and Steering Functional Metacognition in Large Language Models cites this paper.

Decomposing and Steering Functional Metacognition in Large Language Models Detecting Strategic Deception Using Linear Probes

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-12T07:26:28.446242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ceaca228-ad49-4bfd-bdb3-8c1500187e7d · inbound

Do Linear Probes Generalize Better in Persona Coordinates? cites this paper.

Do Linear Probes Generalize Better in Persona Coordinates? Detecting Strategic Deception Using Linear Probes

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-05-12T04:51:22.919620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bc0d3936-efe4-4385-a1a2-48cbce1302c2 · inbound

Do Linear Probes Generalize Better in Persona Coordinates? cites this paper.

Do Linear Probes Generalize Better in Persona Coordinates? Detecting Strategic Deception Using Linear Probes

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-05-19T17:07:40.615192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d24a5ea7-a3c2-4da0-9cbb-ebc88d56ba27 · inbound

Probing Persona-Dependent Preferences in Language Models cites this paper.

Probing Persona-Dependent Preferences in Language Models Detecting Strategic Deception Using Linear Probes

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T21:49:05.189972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 175934a0-789d-4833-b3e8-891cbc785024 · inbound

Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands cites this paper.

Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands Detecting Strategic Deception Using Linear Probes

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-06-30T20:55:03.913839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7c30bd14-68ae-4528-824f-7b7e4ef28de8 · inbound

Ensemble Monitoring for AI Control: Diverse Signals Outweigh More Compute cites this paper.

Ensemble Monitoring for AI Control: Diverse Signals Outweigh More Compute Detecting Strategic Deception Using Linear Probes

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T20:13:43.359247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1844da09-aa49-4e09-9331-e8d240ce58fb · inbound

Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders cites this paper.

Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders Detecting Strategic Deception Using Linear Probes

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-20T22:49:10.135897Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 96d36098-ec31-4996-8397-53afa1c56af1 · inbound

Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations cites this paper.

Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations Detecting Strategic Deception Using Linear Probes

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-06-29T12:43:25.516237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5f5fadf3-cf10-48e8-9a54-9e8c50b912d2 · inbound

"Did you lie?" Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms cites this paper.

"Did you lie?" Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms Detecting Strategic Deception Using Linear Probes

Reference 71

Resolution: verified exact; arxiv_id, observed 2026-07-03T10:48:02.312946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5cbba510-259f-46c9-b448-75aac7c892c4 · inbound

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

Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates Detecting Strategic Deception Using Linear Probes

Reference 88

Resolution: verified exact; arxiv_id, observed 2026-07-02T12:46:56.224518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bef678c0-f65b-4310-b63d-c497325f6c66 · inbound

GDM AI Control Roadmap cites this paper.

GDM AI Control Roadmap Detecting Strategic Deception Using Linear Probes

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T06:53:51.091332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faff29ea-47d9-4771-9c51-4be50ffdce15 · inbound

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't cites this paper.

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't Detecting Strategic Deception Using Linear Probes

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:15.955985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6ae3a19-988d-4f6c-b784-3660557b3f5d · inbound

Transcoders for Investigating Deception in Language Models cites this paper.

Transcoders for Investigating Deception in Language Models Detecting Strategic Deception Using Linear Probes

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T01:06:13.565524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0da7699a-107e-4316-9240-4d5c07d0c2bf · inbound

Persistent Sparse Autoencoders: Learning Feature Timescales in Language Models cites this paper.

Persistent Sparse Autoencoders: Learning Feature Timescales in Language Models Detecting Strategic Deception Using Linear Probes

Reference 284

Resolution: unresolved; no resolver link, observed 2026-08-01T19:02:58.733832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35c626fb-5396-475c-98f1-dc01e4b2eb9d · inbound

Beyond Liars' Bench: The Impact of Lie Typology, Depth, and Sparsity on Deception Detection in LLMs cites this paper.

Beyond Liars' Bench: The Impact of Lie Typology, Depth, and Sparsity on Deception Detection in LLMs Detecting Strategic Deception Using Linear Probes

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T12:47:00.308743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 528fdc84-2084-4459-81aa-403504b6cea6 · inbound

A False Average: Chain-of-Thought Monitors Collapse Where They Are the Only Defense cites this paper.

A False Average: Chain-of-Thought Monitors Collapse Where They Are the Only Defense Detecting Strategic Deception Using Linear Probes

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T00:40:38.506776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.