Unverified90% confidenceFactTime unknown
基础模型透明度指数（Foundation Model Transparency Index）于2023年首次发布，采用了包含100个细分指标的评估体系
1
Sources
90%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
Unverified多个主要开源基金会在2024-2025年间相继出台政策，要求提交安全报告时必须附带可复现的概念验证（PoC），以过滤纯AI生成的低质量报告62% similarUnverifiedOpenAI open-sourced its Evals framework in 2023, categorizing evaluation into three major types: fact-based exact matching, model-based judgment, and human-annotation-based evaluation.60% similarUnverifiedOn May 19, 2025, third-party AI safety evaluation organization METR released a document titled "Frontier Risk Report."59% similarUnverifiedGreenLight模型由Katzin等人于2020年在《Biosystems Engineering》期刊发表，涉及超过100个状态方程58% similarUnverified表征工程作为系统性框架由斯坦福大学Zou等人于2023年在论文《Representation Engineering: A Top-Down Approach to AI Transparency》中正式提出58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/22959API
curl https://kongchang.com/api/v1/knowledge/claims/22959MCP
get_claim(id=22959)