Unverified50% confidenceConceptExact time
The research proposes the concept of function transparency: a model has function transparency if its prediction function can be expressed as a sum of univariate functions (main effects) and bivariate functions (pairwise interactions).
1
Sources
50%
Confidence
Long-term
Relevance
11/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedCommon generalized linear models (GLMs) and explainable boosting machines (EBMs) both fit the definition of function transparency.68% similarUnverifiedThe prediction function of a generalized linear model (GLM) takes the form g(E[Y]) = β0 + Σ βj xj, mapping the linear predictor to the target mean via the link function, and thus naturally satisfies function transparency.67% similarUnverified内在可解释性指模型结构本身的透明性,事后可解释性则是对不透明模型施加外部解释技术如SHAP、LIME65% similarUnverifiedTransparent output may refer to the model providing explainable and traceable results during inference, such as displaying reasoning chains, source annotations, or structured output formats.62% similarUnverifiedThe model is capable of achieving generation, editing, and transparent output in a single model.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1166090API
curl https://kongchang.com/api/v1/knowledge/claims/1166090MCP
get_claim(id=1166090)