Paper Citation Record · LEDGER

Auditing language models for hidden objectives

As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 36 inbound Pith citation observations for arXiv:2503.10965.

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

pith.paper-citation-record.v1
2503.10965 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 36 of 36 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:40:06.682295Z

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 4523999c-11ea-4675-8629-f91213f4ebe6 · inbound

Towards eliciting latent knowledge from LLMs with mechanistic interpretability cites this paper.

Towards eliciting latent knowledge from LLMs with mechanistic interpretability Auditing language models for hidden objectives

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:40:06.682295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa202458-0103-447c-b666-20ea3ed08adb · inbound

Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models cites this paper.

Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models Auditing language models for hidden objectives

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T14:13:51.942324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a3bdf26-6371-4dc1-9092-d0dff245fa82 · inbound

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

Fine-Grained Interpretation of Political Opinions in Large Language Models Auditing language models for hidden objectives

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T10:40:14.758765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f079495-60a1-40d6-a715-75f588fa91e0 · inbound

Because we have LLMs, we Can and Should Pursue Agentic Interpretability cites this paper.

Because we have LLMs, we Can and Should Pursue Agentic Interpretability Auditing language models for hidden objectives

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-07T01:03:21.160673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b88a1e6-611f-41e5-b5dc-cb04a4693e75 · inbound

Emergent misalignment as prompt sensitivity: A research note cites this paper.

Emergent misalignment as prompt sensitivity: A research note Auditing language models for hidden objectives

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T19:53:58.827203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af0beebe-97c8-4cdb-83f8-ffbd766a73ca · inbound

Simple Mechanistic Explanations for Out-Of-Context Reasoning cites this paper.

Simple Mechanistic Explanations for Out-Of-Context Reasoning Auditing language models for hidden objectives

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:43.680460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70e3acff-d50d-4d41-8bde-f83b37011a63 · inbound

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs cites this paper.

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Auditing language models for hidden objectives

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T16:57:08.878310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17683638-5c63-49f4-8d3f-25b356055bbb · inbound

Mechanistic interpretability for steering vision-language-action models cites this paper.

Mechanistic interpretability for steering vision-language-action models Auditing language models for hidden objectives

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T13:50:17.777613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed4d2bdb-a0b3-4817-bb93-0bade8384761 · inbound

Participatory AI: A Scandinavian Approach to Human-Centered AI cites this paper.

Participatory AI: A Scandinavian Approach to Human-Centered AI Auditing language models for hidden objectives

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-04T16:37:26.835978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f8e93d7-8c25-406e-ad64-0b7e8daba457 · inbound

Internal Deployment in the AI Act cites this paper.

Internal Deployment in the AI Act Auditing language models for hidden objectives

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-21T17:54:18.534920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e2285006-db6a-4264-814f-b9b95cfdf594 · inbound

Pando: Do Interpretability Methods Work When Models Won't Explain Themselves? cites this paper.

Pando: Do Interpretability Methods Work When Models Won't Explain Themselves? Auditing language models for hidden objectives

Reference 1

Resolution: malformed identifier; arxiv_id, observed 2026-05-11T10:26:02.378367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ecabf288-40ff-4f20-8eee-4284d200fcb7 · 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 Auditing language models for hidden objectives

Reference 80

Resolution: verified exact; arxiv_id, observed 2026-05-10T14:00:28.385565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7919d241-d8ef-400d-a631-0f3936192d04 · inbound

Most Current Model Organisms Are Leaky: Perplexity Differencing Often Reveals Finetuning Objectives cites this paper.

Most Current Model Organisms Are Leaky: Perplexity Differencing Often Reveals Finetuning Objectives Auditing language models for hidden objectives

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T16:06:07.697769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5ce426cb-d4e5-4ef4-960a-c6d84b54944b · inbound

Most Current Model Organisms Are Leaky: Perplexity Differencing Often Reveals Finetuning Objectives cites this paper.

Most Current Model Organisms Are Leaky: Perplexity Differencing Often Reveals Finetuning Objectives Auditing language models for hidden objectives

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T07:55:31.599646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 56fdb4a2-ef28-4146-ba4a-8e4e09a98f61 · inbound

Narrow Secret Loyalty Dodges Black-Box Audits cites this paper.

Narrow Secret Loyalty Dodges Black-Box Audits Auditing language models for hidden objectives

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:00:57.070015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 12f71361-56e3-40e4-b345-1c4336b2f5b3 · inbound

Narrow Secret Loyalty Dodges Black-Box Audits cites this paper.

Narrow Secret Loyalty Dodges Black-Box Audits Auditing language models for hidden objectives

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:12:22.905126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d3c0b841-123a-4bde-a163-775c7ade017e · inbound

Narrow Secret Loyalty Dodges Black-Box Audits cites this paper.

Narrow Secret Loyalty Dodges Black-Box Audits Auditing language models for hidden objectives

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-06-30T23:05:07.322088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 41e33e97-cf37-43ac-b5a3-0e315219a3de · inbound

Positive Alignment: Artificial Intelligence for Human Flourishing cites this paper.

Positive Alignment: Artificial Intelligence for Human Flourishing Auditing language models for hidden objectives

Reference 125

Resolution: verified exact; arxiv_id, observed 2026-05-15T05:59:47.974215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f9e9e36c-bd9e-4583-b4c1-7b602369d35d · inbound

Deep Minds and Shallow Probes cites this paper.

Deep Minds and Shallow Probes Auditing language models for hidden objectives

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-13T02:22:06.365710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3aa6eb90-0c30-46f6-9c73-13884c2f24f5 · inbound

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations cites this paper.

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations Auditing language models for hidden objectives

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:17:56.941027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5e6652c7-54d7-4f01-a9f2-a4d661157ebc · 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 Auditing language models for hidden objectives

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-06-30T20:55:03.932936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3550bd84-1b41-4078-bf8e-2a075683e031 · inbound

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs cites this paper.

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs Auditing language models for hidden objectives

Reference 88

Resolution: verified exact; arxiv_id, observed 2026-05-22T09:41:21.485724Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 819b93fe-de95-498a-9cb6-748d9e3e96e5 · inbound

PRISM: Recovering Instruction Sets from Language Model Activations cites this paper.

PRISM: Recovering Instruction Sets from Language Model Activations Auditing language models for hidden objectives

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-06-27T17:01:08.024529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6c3f657a-63bc-48ee-90d3-6563d1ff96a7 · 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 Auditing language models for hidden objectives

Reference 250

Resolution: verified exact; arxiv_id, observed 2026-07-03T01:37:30.478939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4eadd4bd-af71-4321-9a60-26aa20c3d2ec · 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 Auditing language models for hidden objectives

Reference 82

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T10:48:02.294364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7be5d1e9-cb3f-4c8b-a787-ba932cf5e064 · inbound

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

RogueAI: A Reverse Turing Test for Detecting Licensed AI Deception in Dialogue Auditing language models for hidden objectives

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-07-03T15:18:33.682490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 093f88b0-768b-456a-a7c9-f556eb286e15 · inbound

Self-CTRL: Self-Consistency Training with Reinforcement Learning cites this paper.

Self-CTRL: Self-Consistency Training with Reinforcement Learning Auditing language models for hidden objectives

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-07-03T20:08:56.002103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1444b25b-1bd5-4a3d-b6ea-21c396c7ad16 · inbound

Channel Location Constrains the Auditability of Subliminal Learning cites this paper.

Channel Location Constrains the Auditability of Subliminal Learning Auditing language models for hidden objectives

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-07-04T08:19:44.415684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f52bdd47-9f53-4350-a462-8c2dd4ed46d3 · inbound

The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology cites this paper.

The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology Auditing language models for hidden objectives

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-07-02T16:07:08.170512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3b2d4f8e-a49e-47ed-9b54-1dc75367f11d · inbound

Agent-Safety Evaluations as Load-Bearing Evidence: A Vendor-Neutral, Cross-Harness Reconstructability Metric cites this paper.

Agent-Safety Evaluations as Load-Bearing Evidence: A Vendor-Neutral, Cross-Harness Reconstructability Metric Auditing language models for hidden objectives

Reference 15

Resolution: malformed identifier; no resolver link, observed 2026-07-15T05:51:54.267975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4956763c-4437-48e9-986e-a835920f2897 · inbound

GDM AI Control Roadmap cites this paper.

GDM AI Control Roadmap Auditing language models for hidden objectives

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T06:53:53.237703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 333f4bf7-a9ae-4ad4-a719-b8d30c0475c0 · inbound

Verbalizable Representations Form a Global Workspace in Language Models cites this paper.

Verbalizable Representations Form a Global Workspace in Language Models Auditing language models for hidden objectives

Reference 106

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:30.250045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5048bffa-aef4-4ffd-ad6d-f7f24bdf424a · inbound

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation cites this paper.

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation Auditing language models for hidden objectives

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T07:16:02.407247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33c2b679-5937-4d5c-b354-19eda83950bc · inbound

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation cites this paper.

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation Auditing language models for hidden objectives

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T07:16:02.413345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8933e60-ff59-4a3f-8efb-652aa548b415 · inbound

Reference Feature Atlases for Mechanistic Auditing of Language Models cites this paper.

Reference Feature Atlases for Mechanistic Auditing of Language Models Auditing language models for hidden objectives

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T12:35:16.824307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e720ff2-65da-40cc-bb98-22df2db2e570 · 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 Auditing language models for hidden objectives

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T04:14:44.927414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.