Paper Citation Record · LEDGER

Evaluating Frontier Models for Dangerous Capabilities

As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 51 inbound Pith citation observations for arXiv:2403.13793.

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

pith.paper-citation-record.v1
2403.13793 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 51 of 51 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 51 of 51 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:34:05.033901Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, 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

11
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 5397a145-bf4e-4251-a510-aa73e680b479 · inbound

LLM Agents can Autonomously Exploit One-day Vulnerabilities cites this paper.

LLM Agents can Autonomously Exploit One-day Vulnerabilities Evaluating Frontier Models for Dangerous Capabilities

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T04:18:27.721335Z

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 5e4744a9-9afb-4475-8606-520bfe93d33a · inbound

Gemma 2: Improving Open Language Models at a Practical Size cites this paper.

Gemma 2: Improving Open Language Models at a Practical Size Evaluating Frontier Models for Dangerous Capabilities

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:11:16.476742Z

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 8ebdf006-f847-4ed3-a907-983e3caeb6ac · inbound

Safety case template for frontier AI: A cyber inability argument cites this paper.

Safety case template for frontier AI: A cyber inability argument Evaluating Frontier Models for Dangerous Capabilities

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-12T22:01:11.507302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15f0547b-94c7-4ce5-b869-0556aad8a54d · inbound

Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment cites this paper.

Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment Evaluating Frontier Models for Dangerous Capabilities

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T18:15:02.620872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0353eefc-190f-4539-bbd6-3a7d36c013b0 · inbound

Dimensions of Generative AI Evaluation Design cites this paper.

Dimensions of Generative AI Evaluation Design Evaluating Frontier Models for Dangerous Capabilities

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T17:15:21.945350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f64c4e1-828a-4706-9b42-47ed2dace3a8 · inbound

Best-of-N Jailbreaking cites this paper.

Best-of-N Jailbreaking Evaluating Frontier Models for Dangerous Capabilities

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-11T22:21:46.938158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84930135-d3d2-41d7-a0ea-024504b98d5c · inbound

Towards Data Governance of Frontier AI Models cites this paper.

Towards Data Governance of Frontier AI Models Evaluating Frontier Models for Dangerous Capabilities

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-11T22:06:54.204725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa14d73f-3b98-467b-98df-ed70fa9be0ee · inbound

Frontier Models are Capable of In-context Scheming cites this paper.

Frontier Models are Capable of In-context Scheming Evaluating Frontier Models for Dangerous Capabilities

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-16T14:22:01.671094Z

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 d7d3fc15-ed60-4b0e-984f-dca0c53661e7 · inbound

What AI evaluations for preventing catastrophic risks can and cannot do cites this paper.

What AI evaluations for preventing catastrophic risks can and cannot do Evaluating Frontier Models for Dangerous Capabilities

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T11:56:20.991463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4832d0c-7de9-4495-92f3-9564d4a34d9b · inbound

Frontier AI systems have surpassed the self-replicating red line cites this paper.

Frontier AI systems have surpassed the self-replicating red line Evaluating Frontier Models for Dangerous Capabilities

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T19:37:44.732532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b08d6fd2-6db4-4753-ab21-4885354ae96e · inbound

Quantifying detection rates for dangerous capabilities: a theoretical model of dangerous capability evaluations cites this paper.

Quantifying detection rates for dangerous capabilities: a theoretical model of dangerous capability evaluations Evaluating Frontier Models for Dangerous Capabilities

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T11:30:43.131236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f85bd960-a8cd-4ffc-8e96-fbaf221f5797 · inbound

OpenAI o1 System Card cites this paper.

OpenAI o1 System Card Evaluating Frontier Models for Dangerous Capabilities

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-23T06:42:39.642455Z

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 28512f1c-7477-4b92-a651-cde7deb30b94 · inbound

Authenticated Delegation and Authorized AI Agents cites this paper.

Authenticated Delegation and Authorized AI Agents Evaluating Frontier Models for Dangerous Capabilities

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-10T19:50:42.581504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54ab1573-da71-4eb2-a70f-7d5bdffbc599 · inbound

The AI Agent Index cites this paper.

The AI Agent Index Evaluating Frontier Models for Dangerous Capabilities

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-09T14:48:35.492465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa0b066f-1fcc-4b5a-812a-f607318d8510 · inbound

Towards an AI co-scientist cites this paper.

Towards an AI co-scientist Evaluating Frontier Models for Dangerous Capabilities

Reference 38

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T13:02:44.576679Z

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 c7c49b1b-fc83-4f17-bc1f-82192cf068a2 · inbound

Mapping Industry Practices to the EU AI Act's GPAI Code of Practice Safety and Security Measures cites this paper.

Mapping Industry Practices to the EU AI Act's GPAI Code of Practice Safety and Security Measures Evaluating Frontier Models for Dangerous Capabilities

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T11:34:05.033901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60966de0-cb01-47a8-9c2a-e3f296d50abb · inbound

JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift cites this paper.

JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift Evaluating Frontier Models for Dangerous Capabilities

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T05:57:58.287237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49cc80c4-77d1-44db-b5ae-09685e1e801c · inbound

Real-World Gaps in AI Governance Research cites this paper.

Real-World Gaps in AI Governance Research Evaluating Frontier Models for Dangerous Capabilities

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-16T04:53:11.969029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fff4a8ad-7dad-4e6c-9731-1915a374fa2c · inbound

Evaluating Frontier Models for Stealth and Situational Awareness cites this paper.

Evaluating Frontier Models for Stealth and Situational Awareness Evaluating Frontier Models for Dangerous Capabilities

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-16T04:22:42.676750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4badcd9d-26c5-4958-8f5e-052cd73a5167 · inbound

AI Governance to Avoid Extinction: The Strategic Landscape and Actionable Research Questions cites this paper.

AI Governance to Avoid Extinction: The Strategic Landscape and Actionable Research Questions Evaluating Frontier Models for Dangerous Capabilities

Reference 156

Resolution: unresolved; no resolver link, observed 2026-08-15T23:27:30.430189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f46d63e-ab30-4b48-b0fb-6d5d6d486985 · inbound

ACSE-Eval: Can LLMs threat model real-world cloud infrastructure? cites this paper.

ACSE-Eval: Can LLMs threat model real-world cloud infrastructure? Evaluating Frontier Models for Dangerous Capabilities

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T21:03:00.711731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 291bbf65-44a7-4f41-afc8-e085cebc48d4 · inbound

Forewarned is Forearmed: A Survey on Large Language Model-based Agents in Autonomous Cyberattacks cites this paper.

Forewarned is Forearmed: A Survey on Large Language Model-based Agents in Autonomous Cyberattacks Evaluating Frontier Models for Dangerous Capabilities

Reference 154

Resolution: unresolved; no resolver link, observed 2026-08-15T20:28:59.431537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 316b0a8f-dd34-417e-8046-86a1e7ec13d6 · inbound

Benchmarking Misuse Mitigation Against Covert Adversaries cites this paper.

Benchmarking Misuse Mitigation Against Covert Adversaries Evaluating Frontier Models for Dangerous Capabilities

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-19T10:32:14.642218Z

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 40c2ff1d-0346-4269-9b7a-7b608aa67487 · inbound

Data-Centric Safety and Ethical Measures for Data and AI Governance cites this paper.

Data-Centric Safety and Ethical Measures for Data and AI Governance Evaluating Frontier Models for Dangerous Capabilities

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T04:34:08.884266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64cb3526-2168-4d5e-96d6-e947c741a752 · inbound

Contemporary AI foundation models increase biological weapons risk cites this paper.

Contemporary AI foundation models increase biological weapons risk Evaluating Frontier Models for Dangerous Capabilities

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T04:17:20.085006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff62de0c-4161-493e-8c1b-09bf990d1e6f · inbound

International Security Applications of Flexible Hardware-Enabled Guarantees cites this paper.

International Security Applications of Flexible Hardware-Enabled Guarantees Evaluating Frontier Models for Dangerous Capabilities

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T19:47:59.062215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a56befd-c9be-42e5-9209-0b30a053139b · inbound

SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents cites this paper.

SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents Evaluating Frontier Models for Dangerous Capabilities

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T19:54:52.954857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be9f9fa3-1e59-4bc6-b345-e655913e4d13 · inbound

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities cites this paper.

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities Evaluating Frontier Models for Dangerous Capabilities

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-05-19T05:52:07.931876Z

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 e107757b-5e07-42fd-a604-df71d28c0cf0 · inbound

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework cites this paper.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Evaluating Frontier Models for Dangerous Capabilities

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:37.129859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ded1746d-a757-43f2-ae1c-421e4d68f658 · inbound

Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report cites this paper.

Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report Evaluating Frontier Models for Dangerous Capabilities

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T15:14:22.926909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdd23794-a56e-411d-9767-1858edc9d8c5 · inbound

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

Reliable Weak-to-Strong Monitoring of LLM Agents Evaluating Frontier Models for Dangerous Capabilities

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-05T15:53:53.446112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c944593-4e77-41ff-8120-20da83a075f2 · inbound

Private, Verifiable, and Auditable AI Systems cites this paper.

Private, Verifiable, and Auditable AI Systems Evaluating Frontier Models for Dangerous Capabilities

Reference 225

Resolution: unresolved; no resolver link, observed 2026-08-05T15:43:59.371101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93071eb1-00da-4785-8cae-d7d45886470a · inbound

Estimating the Empowerment of Language Model Agents cites this paper.

Estimating the Empowerment of Language Model Agents Evaluating Frontier Models for Dangerous Capabilities

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T14:53:17.688392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98004cc5-5adf-4f1f-b56a-8b3576daf855 · inbound

Safe for Whom? Rethinking How We Evaluate the Safety of LLMs for Real Users cites this paper.

Safe for Whom? Rethinking How We Evaluate the Safety of LLMs for Real Users Evaluating Frontier Models for Dangerous Capabilities

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-16T23:23:39.955248Z

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 9fa259d1-9099-4208-a1de-04ac5e511324 · inbound

The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems cites this paper.

The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems Evaluating Frontier Models for Dangerous Capabilities

Reference 103

Resolution: verified exact; arxiv_id, observed 2026-05-15T20:46:36.241926Z

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 bf4cfde7-10f5-433a-9099-a2b0e77d19be · inbound

From Disclosure to Self-Referential Opacity: Six Dimensions of Strain in Current AI Governance cites this paper.

From Disclosure to Self-Referential Opacity: Six Dimensions of Strain in Current AI Governance Evaluating Frontier Models for Dangerous Capabilities

Reference 69

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:00:22.250927Z

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 3fb4d26d-f3b0-4c3e-ad66-36d994d3cc4a · inbound

CyberCertBench: Evaluating LLMs in Cybersecurity Certification Knowledge cites this paper.

CyberCertBench: Evaluating LLMs in Cybersecurity Certification Knowledge Evaluating Frontier Models for Dangerous Capabilities

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T00:34:47.049775Z

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 8a653bfd-6ffc-4603-9442-4775de29256c · inbound

ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks? cites this paper.

ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks? Evaluating Frontier Models for Dangerous Capabilities

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-13T03:07:09.009924Z

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 d378f5ed-b3e3-4af3-ab17-32288ec8738b · inbound

Rollout Cards: A Reproducibility Standard for Agent Research cites this paper.

Rollout Cards: A Reproducibility Standard for Agent Research Evaluating Frontier Models for Dangerous Capabilities

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T06:02:23.587743Z

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 0672b9c5-6fb0-439c-9e09-65e98af93209 · inbound

Measuring Safety Alignment Effects in Autonomous Security Agents cites this paper.

Measuring Safety Alignment Effects in Autonomous Security Agents Evaluating Frontier Models for Dangerous Capabilities

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-20T04:28:05.916500Z

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 2e85b7ac-258d-4977-8ac5-73376046bb6f · inbound

Comprehensive AI governance requires addressing non-model gains cites this paper.

Comprehensive AI governance requires addressing non-model gains Evaluating Frontier Models for Dangerous Capabilities

Reference 76

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T08:15:31.663670Z

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 b787e572-707f-449d-9223-02a0fb9e8fcb · inbound

Solipsistic Superintelligence is Unlikely to be Cooperative cites this paper.

Solipsistic Superintelligence is Unlikely to be Cooperative Evaluating Frontier Models for Dangerous Capabilities

Reference 199

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T03:26:29.746920Z

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 80ecbb19-e52f-46ae-9021-c419ae918ce2 · inbound

A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing cites this paper.

A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing Evaluating Frontier Models for Dangerous Capabilities

Reference 103

Resolution: verified exact; arxiv_id, observed 2026-07-02T08:16:47.572672Z

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 238c4677-edad-4e28-805c-67e7e959149c · inbound

The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems cites this paper.

The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems Evaluating Frontier Models for Dangerous Capabilities

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-03T15:38:33.531225Z

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 498984e8-a9ec-4251-80d7-a6089f9abafb · inbound

The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems cites this paper.

The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems Evaluating Frontier Models for Dangerous Capabilities

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-06-30T11:34:38.126424Z

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 f4441bf2-4b62-4cd4-9a17-81337fcf7b1b · inbound

AI Sandboxes: A Threat Model, Taxonomy, and Measurement Framework cites this paper.

AI Sandboxes: A Threat Model, Taxonomy, and Measurement Framework Evaluating Frontier Models for Dangerous Capabilities

Reference 122

Resolution: verified exact; arxiv_id, observed 2026-07-03T22:08:59.996827Z

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 2943cd42-a5e2-4f2c-b94b-4cd3e36984e8 · inbound

Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action cites this paper.

Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action Evaluating Frontier Models for Dangerous Capabilities

Reference 75

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T10:15:44.646309Z

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 c0a59a1d-43da-4459-8037-1aed539ea542 · inbound

The Oracle's Gambit: A Game-Theoretic Framework for Responsible AI Release cites this paper.

The Oracle's Gambit: A Game-Theoretic Framework for Responsible AI Release Evaluating Frontier Models for Dangerous Capabilities

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-12T01:32:59.751620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0746f56a-9ea6-4c5c-9ca1-9d2e0f48bd6a · inbound

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

Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring Evaluating Frontier Models for Dangerous Capabilities

Reference 62

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T00:56:40.994995Z

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 1cc1b510-a081-4d37-a465-c8fa80c98ce4 · inbound

SAGE: Safety-First Defense-in-Depth Guardrails for Verified Lifecycle Control of High-Impact Generative AI cites this paper.

SAGE: Safety-First Defense-in-Depth Guardrails for Verified Lifecycle Control of High-Impact Generative AI Evaluating Frontier Models for Dangerous Capabilities

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-01T04:12:58.764877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b1eb21c-0605-4abb-a4cf-76023772b512 · inbound

Accountability Asymmetry and Structural Trust in Autonomous AI Systems cites this paper.

Accountability Asymmetry and Structural Trust in Autonomous AI Systems Evaluating Frontier Models for Dangerous Capabilities

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T14:51:31.797330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.