A model-agnostic framework decomposes conformal prediction interval width and bounds into feature-level contributions using Shapley and proportional Shapley values.
The proportional Shapley value and applications
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Unveil Sources of Uncertainty: Feature Contribution to Conformal Prediction Intervals
A model-agnostic framework decomposes conformal prediction interval width and bounds into feature-level contributions using Shapley and proportional Shapley values.