Unverified50% confidenceFactExact time
SHAP由Scott Lundberg于2017年在NeurIPS论文中提出，是唯一同时满足局部准确性、缺失性和一致性三个公理的归因方法
1
Sources
50%
Confidence
Long-term
Relevance
8/29/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedSHAP (SHapley Additive exPlanations) was proposed by Lundberg and Lee in 2017 and is based on the Shapley value principle from cooperative game theory.71% similarUnverifiedThe theoretical basis of SHAP comes from the concept of Shapley values in cooperative game theory, proposed by Nobel Prize-winning economist Lloyd Shapley in 1953; in 2017, Lundberg and Lee introduced it into the field of machine learning.61% similarUnverifiedStatistician Donald Rubin proposed three missing data mechanisms in 1976: MCAR, MAR, and MNAR.59% similarUnverifiedThe theoretical foundation of SHAP (SHapley Additive exPlanations) originates from the fair allocation scheme proposed by Lloyd Shapley in cooperative game theory, for which he received the Nobel Prize in Economics in 1953.58% similarUnverified2020 年研究人员实现了 SHA-1 的选择前缀碰撞（Chosen-Prefix Collision）53% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/818098API
curl https://kongchang.com/api/v1/knowledge/claims/818098MCP
get_claim(id=818098)