Paper Citation Record · LEDGER

Model evaluation for extreme risks

As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 47 inbound Pith citation observations for arXiv:2305.15324.

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

pith.paper-citation-record.v1
2305.15324 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 47 of 47 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 47 of 47 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-09T05:20:17.538978Z

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

58
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 604417e3-3264-4da5-b336-4c161674a669 · inbound

AI-Augmented Surveys: Leveraging Large Language Models and Surveys for Opinion Prediction cites this paper.

AI-Augmented Surveys: Leveraging Large Language Models and Surveys for Opinion Prediction Model evaluation for extreme risks

Reference 91

Resolution: verified exact; arxiv_id, observed 2026-05-24T08:49:13.910243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 322984e0-ed5c-4f59-bc4a-fdd194faa95f · inbound

Gemini: A Family of Highly Capable Multimodal Models cites this paper.

Gemini: A Family of Highly Capable Multimodal Models Model evaluation for extreme risks

Reference 95

Resolution: verified exact; arxiv_id, observed 2026-05-24T05:03:55.499819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e567a0de-1275-4d07-9569-096c39ef0453 · inbound

TrustLLM: Trustworthiness in Large Language Models cites this paper.

TrustLLM: Trustworthiness in Large Language Models Model evaluation for extreme risks

Reference 178

Resolution: verified exact; arxiv_id, observed 2026-05-18T11:17:08.559994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5c16d358-cca0-46ce-8ba2-7bc8d01dac6a · inbound

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

Gemma 2: Improving Open Language Models at a Practical Size Model evaluation for extreme risks

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:11:16.458916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 609483f9-1026-42f3-8c03-700914fe8f04 · inbound

Enabling External Scrutiny of AI Systems with Privacy-Enhancing Technologies cites this paper.

Enabling External Scrutiny of AI Systems with Privacy-Enhancing Technologies Model evaluation for extreme risks

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-09T05:20:17.538978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 203605c6-35df-4a78-a504-9babfc3fd8af · inbound

Towards an AI co-scientist cites this paper.

Towards an AI co-scientist Model evaluation for extreme risks

Reference 35

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T13:02:44.555404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 068c3fb0-56a3-459c-88dc-cfb232f39dda · inbound

Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks cites this paper.

Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks Model evaluation for extreme risks

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T14:09:51.655116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24a86f83-83d2-4712-9042-e6e893aa06df · inbound

Evaluating LLM Agent Adherence to Hierarchical Safety Principles: A Lightweight Benchmark for Probing Foundational Controllability Components cites this paper.

Evaluating LLM Agent Adherence to Hierarchical Safety Principles: A Lightweight Benchmark for Probing Foundational Controllability Components Model evaluation for extreme risks

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T11:28:21.649808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5823278-1eef-4d29-9d9f-d89cf8709360 · inbound

Benchmarking Misuse Mitigation Against Covert Adversaries cites this paper.

Benchmarking Misuse Mitigation Against Covert Adversaries Model evaluation for extreme risks

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-19T10:32:14.669979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ae0ef045-e116-48ed-84e6-14f9f36aac9a · inbound

MalGEN: A Testbed for Modeling and Evaluating Malware Behaviors cites this paper.

MalGEN: A Testbed for Modeling and Evaluating Malware Behaviors Model evaluation for extreme risks

Reference 35

Resolution: metadata mismatch; arxiv_id, observed 2026-05-19T11:07:15.347544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1c6d6086-2acf-4e2d-bf5f-454524113818 · inbound

UCD: Unlearning in LLMs via Contrastive Decoding cites this paper.

UCD: Unlearning in LLMs via Contrastive Decoding Model evaluation for extreme risks

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.887715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7fa0bd3-765b-4d2d-828e-b39219f73bbf · inbound

A Conceptual Framework for AI Capability Evaluations cites this paper.

A Conceptual Framework for AI Capability Evaluations Model evaluation for extreme risks

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-06T23:25:51.618603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bb39678-e27a-493a-87d7-193ec5fc5c53 · inbound

On the Generalizability of "Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals" cites this paper.

On the Generalizability of "Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals" Model evaluation for extreme risks

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T21:57:43.091137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd4dda47-dcb5-4268-8aac-5b76de9ed102 · inbound

From Turing to Tomorrow: The UK's Approach to AI Regulation cites this paper.

From Turing to Tomorrow: The UK's Approach to AI Regulation Model evaluation for extreme risks

Reference 158

Resolution: unresolved; no resolver link, observed 2026-08-06T20:32:41.866495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b823d75-1aec-4bdb-afaa-6f87ed338aaa · inbound

Domestic frontier AI regulation, an IAEA for AI, an NPT for AI, and a US-led Allied Public-Private Partnership for AI: Four institutions for governing and developing frontier AI cites this paper.

Domestic frontier AI regulation, an IAEA for AI, an NPT for AI, and a US-led Allied Public-Private Partnership for AI: Four institutions for governing and developing frontier AI Model evaluation for extreme risks

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-06T19:11:07.257632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2704126-6a95-405e-b8d2-e321a4781f2c · inbound

Technical Requirements for Halting Dangerous AI Activities cites this paper.

Technical Requirements for Halting Dangerous AI Activities Model evaluation for extreme risks

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T17:50:30.606349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30fbed42-5157-40ac-b14a-eeaa3bcee6a0 · inbound

ExploreGS: Explorable 3D Scene Reconstruction with Virtual Camera Samplings and Diffusion Priors cites this paper.

ExploreGS: Explorable 3D Scene Reconstruction with Virtual Camera Samplings and Diffusion Priors Model evaluation for extreme risks

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T23:01:41.829098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c1b739c-c238-469b-a268-36ebc6ea9d53 · inbound

Designing Incident Reporting Systems for Harms from General-Purpose AI cites this paper.

Designing Incident Reporting Systems for Harms from General-Purpose AI Model evaluation for extreme risks

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T00:20:32.268321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e229ee5b-ed62-464e-b88a-83c79af78af3 · inbound

Internal Deployment in the AI Act cites this paper.

Internal Deployment in the AI Act Model evaluation for extreme risks

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T17:54:18.544842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ae434422-e6ff-4489-91f0-5e33c4893222 · inbound

LLM-Guided Prompt Evolution for Password Guessing cites this paper.

LLM-Guided Prompt Evolution for Password Guessing Model evaluation for extreme risks

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-11T11:31:01.210679Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1f6a3b20-f614-4c80-a058-4dff33e7f0d8 · inbound

Representation-Guided Parameter-Efficient LLM Unlearning cites this paper.

Representation-Guided Parameter-Efficient LLM Unlearning Model evaluation for extreme risks

Reference 39

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T06:06:19.409992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ef47b39b-b3c0-486c-99b4-91d58f4a3192 · inbound

Who Defines "Best"? Towards Interactive, User-Defined Evaluation of LLM Leaderboards cites this paper.

Who Defines "Best"? Towards Interactive, User-Defined Evaluation of LLM Leaderboards Model evaluation for extreme risks

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-11T14:21:07.365784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e57dc426-ca56-4c82-b65b-78808d36c75f · inbound

Risk Reporting for Developers' Internal AI Model Use cites this paper.

Risk Reporting for Developers' Internal AI Model Use Model evaluation for extreme risks

Reference 41

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T23:16:16.432362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fa8dc43b-6271-499b-9812-a4d0c020d8c0 · inbound

Evaluation without Generation: Non-Generative Assessment of Harmful Model Specialization with Applications to CSAM cites this paper.

Evaluation without Generation: Non-Generative Assessment of Harmful Model Specialization with Applications to CSAM Model evaluation for extreme risks

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:31:14.196298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 70fa7b83-c04f-41ad-b983-ff44680cfb62 · inbound

Artificial Jagged Intelligence as Uneven Optimization Energy Allocation Capability Concentration, Redistribution, and Optimization Governance cites this paper.

Artificial Jagged Intelligence as Uneven Optimization Energy Allocation Capability Concentration, Redistribution, and Optimization Governance Model evaluation for extreme risks

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-11T17:01:09.016460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bcc58897-32c0-4dcf-93e3-8d1564eb52cd · inbound

A Validated Prompt Bank for Malicious Code Generation: Separating Executable Weapons from Security Knowledge in 1,554 Consensus-Labeled Prompts cites this paper.

A Validated Prompt Bank for Malicious Code Generation: Separating Executable Weapons from Security Knowledge in 1,554 Consensus-Labeled Prompts Model evaluation for extreme risks

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-05-09T06:40:43.534363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 612496ef-2aad-468a-b2f1-e8b1fdc66928 · inbound

When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels cites this paper.

When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels Model evaluation for extreme risks

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-05-08T21:39:24.651511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4abdc819-bec3-4252-9092-d4bf6a8d8648 · inbound

Overtrained, Not Misaligned cites this paper.

Overtrained, Not Misaligned Model evaluation for extreme risks

Reference 41

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T06:47:26.248329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2a4f006a-c173-44c6-8881-bf25d2053da4 · inbound

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching cites this paper.

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching Model evaluation for extreme risks

Reference 94

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T04:57:17.277926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0edff6ea-befb-4647-851b-bc7182eea175 · inbound

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching cites this paper.

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching Model evaluation for extreme risks

Reference 94

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T05:45:06.474151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6aec64f0-8e08-4930-af60-720b9a55ea30 · 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 Model evaluation for extreme risks

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-06-30T20:55:03.991229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ce90f471-643a-4f7f-a4ff-9105b12525d2 · inbound

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

Measuring Safety Alignment Effects in Autonomous Security Agents Model evaluation for extreme risks

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-20T04:28:05.922999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d0953d61-28a0-4d0a-bf04-78c563c4c583 · inbound

Backchaining Loss of Control Mitigations from Mission-Specific Benchmarks in National Security cites this paper.

Backchaining Loss of Control Mitigations from Mission-Specific Benchmarks in National Security Model evaluation for extreme risks

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-21T02:03:54.371283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 501e47f3-025b-45c7-a4e5-82ee61a3cc84 · inbound

Backchaining Loss of Control Mitigations from Mission-Specific Benchmarks in National Security cites this paper.

Backchaining Loss of Control Mitigations from Mission-Specific Benchmarks in National Security Model evaluation for extreme risks

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T02:03:54.276808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1463a8d7-e34d-4643-adf6-ffc0360b188b · inbound

Consistency Training while Mitigating Obfuscation via Rate Matching cites this paper.

Consistency Training while Mitigating Obfuscation via Rate Matching Model evaluation for extreme risks

Reference 138

Resolution: verified exact; arxiv_id, observed 2026-06-28T14:32:18.172629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 89d9bf51-6c35-487a-ac47-5266fa246336 · 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 Model evaluation for extreme risks

Reference 114

Resolution: verified exact; arxiv_id, observed 2026-07-02T08:16:47.473340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bce19943-8a43-49cf-9f23-fb169f0bc0cb · inbound

LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs cites this paper.

LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs Model evaluation for extreme risks

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T01:41:29.305785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2aad5fe4-fc00-42c9-9231-205c1d2855b6 · inbound

Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting cites this paper.

Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting Model evaluation for extreme risks

Reference 97

Resolution: verified exact; arxiv_id, observed 2026-07-03T02:07:33.287703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fae8241c-6b94-4ea4-895c-e5540ed2c83c · inbound

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

AI Sandboxes: A Threat Model, Taxonomy, and Measurement Framework Model evaluation for extreme risks

Reference 142

Resolution: verified exact; arxiv_id, observed 2026-07-03T22:08:59.936017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c2a1ea71-96f9-4b62-9533-dff80c7ec0c2 · inbound

Has This Checkpoint Been Abliterated? A Two-Signal Audit and Its Failure Map cites this paper.

Has This Checkpoint Been Abliterated? A Two-Signal Audit and Its Failure Map Model evaluation for extreme risks

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-07-03T10:58:02.494876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8c1c4471-e678-41dd-81b0-679306396f64 · inbound

Securing Multi-Tool AI Agent Chains With Dynamic, Real-Time Compositional Policies cites this paper.

Securing Multi-Tool AI Agent Chains With Dynamic, Real-Time Compositional Policies Model evaluation for extreme risks

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-12T02:36:01.385664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcf9b8d3-76a9-4a20-8afa-d14f60399198 · inbound

Macro-Prudential AI Governance: A Two-Layer Early Warning and Response System for Frontier AI cites this paper.

Macro-Prudential AI Governance: A Two-Layer Early Warning and Response System for Frontier AI Model evaluation for extreme risks

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-12T01:45:06.581823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 215fec64-896f-44cb-9cd7-3387bec92bf5 · inbound

Open Problems in AI Incident Governance cites this paper.

Open Problems in AI Incident Governance Model evaluation for extreme risks

Reference 107

Resolution: unresolved; no resolver link, observed 2026-07-11T07:50:18.332768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49d6e1a2-c8ae-4098-810d-ef6e0cd631dc · inbound

NetInjectBench: Benchmarking Indirect Prompt Injection in Tool-Using Large Language Model Agents for Network Operations cites this paper.

NetInjectBench: Benchmarking Indirect Prompt Injection in Tool-Using Large Language Model Agents for Network Operations Model evaluation for extreme risks

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-14T11:20:52.129640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad1855e4-32f5-4754-96fd-6e96196fc2d4 · inbound

SysAdmin: Measuring Instrumental Power-Seeking in Frontier AI cites this paper.

SysAdmin: Measuring Instrumental Power-Seeking in Frontier AI Model evaluation for extreme risks

Reference 1997

Resolution: unresolved; no resolver link, observed 2026-08-02T16:36:34.814502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91461674-e372-43c8-b8fd-57db70a1d14f · inbound

ContainmentBench: Trace-Based Evaluation of Post-Injection Containment in Tool-Using LLM Agents cites this paper.

ContainmentBench: Trace-Based Evaluation of Post-Injection Containment in Tool-Using LLM Agents Model evaluation for extreme risks

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-31T23:24:19.561447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fea38624-2cc2-4078-bf04-a49900f7dedd · inbound

"Allow" to Achieve, Over-Privileged Inadvertently: The Unintended Cost of Task-Completion-Driven Pop-up Decisions in Mobile GUI Agents cites this paper.

"Allow" to Achieve, Over-Privileged Inadvertently: The Unintended Cost of Task-Completion-Driven Pop-up Decisions in Mobile GUI Agents Model evaluation for extreme risks

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T17:27:27.394338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.