Paper Citation Record · LEDGER

A Safe Harbor for AI Evaluation and Red Teaming

As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 20 inbound Pith citation observations for arXiv:2403.04893.

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

pith.paper-citation-record.v1
2403.04893 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 20 of 20 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 20 of 20 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T05:23:48.289056Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-21T15:00:15.356444Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 69790a2b-1513-4e0b-9e7f-2bc6badd63d5 · inbound

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks cites this paper.

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks A Safe Harbor for AI Evaluation and Red Teaming

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-14T17:11:00.985647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 45f7aa29-0ab2-4c31-9a8d-31433899d91b · inbound

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models cites this paper.

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models A Safe Harbor for AI Evaluation and Red Teaming

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-15T06:08:05.659825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 5e185663-fa17-41a7-82cb-19a046427f3a · inbound

AI Safety Frameworks Should Include Procedures for Model Access Decisions cites this paper.

AI Safety Frameworks Should Include Procedures for Model Access Decisions A Safe Harbor for AI Evaluation and Red Teaming

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T19:37:34.840366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5c68c08-3d94-4613-8b4f-72dae82cb0c8 · inbound

A Framework for Evaluating LLMs Under Task Indeterminacy cites this paper.

A Framework for Evaluating LLMs Under Task Indeterminacy A Safe Harbor for AI Evaluation and Red Teaming

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-12T15:58:47.561742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f1d0d9f-3ec3-4c6e-84e0-d18eceee8228 · inbound

Position Paper: Model Access should be a Key Concern in AI Governance cites this paper.

Position Paper: Model Access should be a Key Concern in AI Governance A Safe Harbor for AI Evaluation and Red Teaming

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-12T05:00:04.270686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ef8e02f-8d20-49ec-ab5a-7254d8d13ffe · inbound

WeAudit: Scaffolding User Auditors and AI Practitioners in Auditing Generative AI cites this paper.

WeAudit: Scaffolding User Auditors and AI Practitioners in Auditing Generative AI A Safe Harbor for AI Evaluation and Red Teaming

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-10T22:31:35.725552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edd96ba3-6145-46c8-af22-ab5d8ef1c562 · inbound

The Pitfalls of "Security by Obscurity" And What They Mean for Transparent AI cites this paper.

The Pitfalls of "Security by Obscurity" And What They Mean for Transparent AI A Safe Harbor for AI Evaluation and Red Teaming

Reference 131

Resolution: unresolved; no resolver link, observed 2026-08-09T23:22:44.837401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d26b40c1-95df-4a0c-b8e2-995ef9e50891 · inbound

Access Denied: Meaningful Data Access for Quantitative Algorithm Audits cites this paper.

Access Denied: Meaningful Data Access for Quantitative Algorithm Audits A Safe Harbor for AI Evaluation and Red Teaming

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-09T19:07:00.533860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4619ed5c-67d9-4a9a-ac4c-baff4da2fdf4 · inbound

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

Enabling External Scrutiny of AI Systems with Privacy-Enhancing Technologies A Safe Harbor for AI Evaluation and Red Teaming

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T05:20:17.440043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f725fe4d-8a26-4fe8-ac79-a64b86fab000 · inbound

When Testing AI Tests Us: Safeguarding Mental Health on the Digital Frontlines cites this paper.

When Testing AI Tests Us: Safeguarding Mental Health on the Digital Frontlines A Safe Harbor for AI Evaluation and Red Teaming

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-16T05:23:48.289056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b3be58c-667d-4471-b751-23385d5e6ae7 · inbound

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

Real-World Gaps in AI Governance Research A Safe Harbor for AI Evaluation and Red Teaming

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-16T04:53:11.796533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e41ed12b-0b24-4dd6-9bb1-47952bab1fa8 · inbound

Adversarial Attacks on Robotic Vision Language Action Models cites this paper.

Adversarial Attacks on Robotic Vision Language Action Models A Safe Harbor for AI Evaluation and Red Teaming

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T11:11:40.477043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0273a9e-3da9-4c8c-8c28-51efe13005a4 · inbound

Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments cites this paper.

Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments A Safe Harbor for AI Evaluation and Red Teaming

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T21:45:02.774011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e665d1bc-66cc-4da8-a9e1-b8c397521577 · inbound

GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing cites this paper.

GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing A Safe Harbor for AI Evaluation and Red Teaming

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-06T18:40:52.530993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28f2f7bb-0e96-4f28-a879-f9317daf9c22 · inbound

Audits Under Resource, Data, and Access Constraints: Scaling Laws For Less Discriminatory Alternatives cites this paper.

Audits Under Resource, Data, and Access Constraints: Scaling Laws For Less Discriminatory Alternatives A Safe Harbor for AI Evaluation and Red Teaming

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T16:30:48.512989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29874361-afb1-431c-a022-65e86266bc47 · inbound

When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models cites this paper.

When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models A Safe Harbor for AI Evaluation and Red Teaming

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-18T09:31:11.622294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2a14fcda-211f-4d0b-82a0-632925293681 · inbound

"Unlimited Realm of Exploration and Experimentation": Methods and Motivations of AI-Generated Sexual Content Creators cites this paper.

"Unlimited Realm of Exploration and Experimentation": Methods and Motivations of AI-Generated Sexual Content Creators A Safe Harbor for AI Evaluation and Red Teaming

Reference 82

Resolution: verified exact; arxiv_id, observed 2026-05-21T15:00:15.358384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 563d47ba-234d-4bb5-ac69-d49bcef832b2 · inbound

ARMOR 2025: A Military-Aligned Benchmark for Evaluating Large Language Model Safety Beyond Civilian Contexts cites this paper.

ARMOR 2025: A Military-Aligned Benchmark for Evaluating Large Language Model Safety Beyond Civilian Contexts A Safe Harbor for AI Evaluation and Red Teaming

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-11T15:26:09.501662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 55848f82-5d4d-4f7b-9283-46f0f7efa8fb · inbound

Open-World Evaluations for Measuring Frontier AI Capabilities cites this paper.

Open-World Evaluations for Measuring Frontier AI Capabilities A Safe Harbor for AI Evaluation and Red Teaming

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-05-21T06:39:43.770823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 852e0b3d-e3c8-4068-9d4a-5cc8a34791cb · inbound

Position: Preventing AI-Generated CSAM Necessitates New Approaches to AI Safety cites this paper.

Position: Preventing AI-Generated CSAM Necessitates New Approaches to AI Safety A Safe Harbor for AI Evaluation and Red Teaming

Reference 109

Resolution: unresolved; no resolver link, observed 2026-07-12T14:28:50.627444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.