NUWA 风险治理 · 研究方法
Introducing SOLVE+: Scoring Cyber Scenarios (Version 0.5)
NUWA 研究解读 · 独立复核待完成
NUWA Research Note
研究问题研究设计与假设来源发现NUWA 解读局限与相反证据研究联系研究与决策意义机构与角色原始资源模型辅助整理 · 选读原始全文或官方文章中的相关章节；尚未完成逐章节审计。
研究速读
SOLVE+ 描述人类视角的场景难度，不报告模型成功率。
研究问题
怎样刻画多步网络场景中不同能力需求，同时不抹去各维度含义？
研究设计与假设
草案扩展 SOLVE 的能力维度，逐步评分，并将全场景编排与步骤聚合分开处理。
来源发现
规范要求分别评估能力维度。
人类难度可能明显不同于 AI 难度；编排是独立的场景级贡献。
NUWA 解读
NUWA 解读：这是任务需求标注框架提案，尚不是通用难度标尺验证或 AI 风险分数。
局限与相反证据
0.5 属早期草案；已读解释章节未确立评分者一致性、预测校准或与危害的因果联系。
研究联系
NUWA 关联：AgentCyberRange 关注联动推进；只有明确映射并另行审阅后，才能用 SOLVE+ 描述其任务需求。
研究与决策意义
NUWA 建议：保留逐维标注与框架版本，不把聚合难度与基准通过率直接比较。
精确来源位置
- Introducing SOLVE+: Scoring Cyber Scenarios (Version 0.5) · SOLVE+ Scoring Framework version 0.5, Introduction, pp.1–2Selected original resource https://irregular-public-docs.s3.eu-north-1.amazonaws.com/full_solve_plus_framework.pdf; sha256:c8127041c04cf20c966f19d85deba9663f75739b3463c57a54b5425c0365803a; archived source capture; exact capture time not independently established
- Introducing SOLVE+: Scoring Cyber Scenarios (Version 0.5) · Interpreting scores, pp.2–3Selected original resource https://irregular-public-docs.s3.eu-north-1.amazonaws.com/full_solve_plus_framework.pdf; sha256:c8127041c04cf20c966f19d85deba9663f75739b3463c57a54b5425c0365803a; archived source capture; exact capture time not independently established
- Introducing SOLVE+: Scoring Cyber Scenarios (Version 0.5) · Summing up scores, pp.3–4Selected original resource https://irregular-public-docs.s3.eu-north-1.amazonaws.com/full_solve_plus_framework.pdf; sha256:c8127041c04cf20c966f19d85deba9663f75739b3463c57a54b5425c0365803a; archived source capture; exact capture time not independently established
来源核查、数据提取、编辑批准与实验复现分别记录。 方法说明 →
机构与角色
引用与复用
引用研究发现时请引用原始出版物；引用 NUWA 的整理与解释时，单独引用本站记录及对应快照。
原始出版物 · BibTeX
@misc{solve-plus,
title = {Introducing SOLVE+: Scoring Cyber Scenarios (Version 0.5)},
url = {https://www.irregular.com/research/solve-plus},
year = {2026},
date = {2026-09-03},
version = {Source capture 2026-10-25},
note = {Source capture 2026-10-25}
}
NUWA 记录 · BibTeX
@misc{solve-plus-nuwa,
title = {Introducing SOLVE+: Scoring Cyber Scenarios (Version 0.5) — NUWA research record},
url = {https://whitzard.tech/nuwa/whitzard-index/work/solve-plus/},
version = {2026-10-29.1},
organization = {NUWA Frontier AI Safety Lab},
howpublished = {Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--solve-plus.json},
note = {NUWA research note. Source-reading scope and independent review status are stated on the record. Snapshot 2026-10-29.1. Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--solve-plus.json.}
}
证据快照 2026-10-29.1 · 索引更新 · RSS
参考文献
- [1] Introducing SOLVE+: Scoring Cyber Scenarios (Version 0.5). 2026-09-03 ; Official publication masthead and article byline; SOLVE+ Scoring Framework version 0.5, Introduction, pp.1–2; Interpreting scores, pp.2–3