RISED operationalizes five evaluation dimensions for AI decision-support systems via BCa bootstrap intervals and Holm-Bonferroni verdicts, revealing failures missed by AUROC on seven cohorts including Diabetes 130 and NHANES.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
No citing papers match the current filters.