Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-02T08:40:02.287760Z
Paper Citation Record · LEDGER
As of 21 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 1 inbound Pith citation observation for arXiv:2607.05462.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-02T08:40:02.287760Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-02T02:00:46.265255Z
A source-named dated measurement, never combined with another source.
Source: cited_works
18 of 18 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation d384b008-2e2e-43db-b408-b551fddda966 · outbound
BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment National Academies Press, Washington, D.C., 2004
Reference 1
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 39a70f28-9f1b-4ec2-b488-80bb5cb05a69 · outbound
BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment National Academies Press, Washington, D.C., 2017
Reference 2
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6b9e0e47-26a6-421b-bfc5-f755d3b92984 · outbound
BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment Dual-use capabilities of concern of biological ai models.PLoS computational biology, 21(5):e1012975, 2025
Reference 3
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c67ffb25-5c1c-4775-9cb2-948c37a53336 · outbound
BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment Without safeguards, ai-biology integration risks accelerating future pandemics.Frontiers in Microbiology, 16:1734561, 2026
Reference 4
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4c5da5f1-170b-4360-8613-82f41e5c35e8 · outbound
BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment Amoresystematicapproach tobiologicalrisk.Science, 350(6267):1471– 1473, 2015
Reference 5
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1cc5df35-b94a-4bd0-811f-bd354fcd353e · outbound
BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment Ai and biosecurity: The need for governance.Science, 385(6711):831–833, 2024
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 30969c73-855e-4d75-a19a-2b8928b73ed0 · outbound
BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment Safe rlhf: Safe reinforcement learning from human feedback
Reference 7
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cdc04368-7212-42bb-8b91-ced90d6f3a52 · outbound
BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment Constitutional AI: Harmlessness from AI Feedback
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 66e68d66-88cf-47d2-bbba-08fbd9c6ca77 · outbound
BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
Reference 9
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 50545031-c1f4-4743-aa23-a925afdc9c76 · outbound
BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment Constitutional classifiers++: Efficient production-grade defenses against universal jailbreaks.arXiv preprint arXiv:2601.04603, 2026
Reference 10
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 22a13f1a-389d-48ae-8847-14d41dbd3c08 · outbound
BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment OR-Bench: An Over-Refusal Benchmark for Large Language Models
Reference 11
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9e8cf392-3063-4472-94f6-bd8b27376ef6 · outbound
BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment RefusalBench: Why Refusal Rate Misranks Frontier LLMs on Biological Research Prompts
Reference 12
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3d143714-d751-42ed-8b9d-637afcdbfd16 · outbound
BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment Virology Capabilities Test (VCT): A Multimodal Virology Q&A Benchmark
Reference 13
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8d67474a-2cb4-4c6c-9a27-9182a942ebfd · outbound
BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecurity
Reference 14
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bb6475ac-3285-4fb4-8402-048fc826bbcb · outbound
BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment Agentic baim-llm evaluation (able): Benchmarking llm use of protein design tools
Reference 15
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fc9bdb47-95ec-4ede-908c-b74d8bdf314f · outbound
BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
Reference 16
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6d94eb5d-0d27-4422-93e1-e40d82b1bac7 · outbound
BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment Biothreat benchmark generation framework for evaluating frontier AI models I: The task-query architecture.arXiv preprint arXiv:2512.08130, 2025
Reference 17
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b1e59ba0-0b3b-461b-a902-6db2aed35248 · outbound
BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment Peptide inhibitors of theα-cobratoxin–nicotinic acetylcholine receptor interaction.Journal of medicinal chemistry, 63(22):13709–13718, 2020
Reference 18
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 61cadd07-2158-4827-9e20-a046b634833a · inbound
BioTIER: A Refusal Benchmark for Targeted Biological Risk Mitigation BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment
Reference 23
Source-reported events for the cited work
Unavailable: canonical work link unavailable.