Pandora's Regret is a closed-form pairwise scoring rule derived from expected optimal search costs that elicits true probabilities and outperforms log loss, accuracy, and F1 at predicting diagnostic costs on MedMNIST models.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 3roles
background 2polarities
background 2representative citing papers
For rare violent re-offense, risk assessment tools face a structural Likelihood Ratio Wall limiting positive predictive value to low levels with current discrimination power, worsened by a Surveillance Ceiling from over-policing that reduces maximum precision for over-policed groups even at equal re
Model evaluation in supervised learning should be treated as a context-dependent, decision-oriented process aligned with operational objectives rather than relying on a small set of aggregate metrics.
citing papers explorer
-
Pandora's Regret: A Proper Scoring Rule for Evaluating Sequential Search
Pandora's Regret is a closed-form pairwise scoring rule derived from expected optimal search costs that elicits true probabilities and outperforms log loss, accuracy, and F1 at predicting diagnostic costs on MedMNIST models.
-
The Likelihood Ratio Wall: Structural Limits on Accurate Risk Assessment for Rare Violence
For rare violent re-offense, risk assessment tools face a structural Likelihood Ratio Wall limiting positive predictive value to low levels with current discrimination power, worsened by a Surveillance Ceiling from over-policing that reduces maximum precision for over-policed groups even at equal re
-
Evaluating Supervised Machine Learning Models: Principles, Pitfalls, and Metric Selection
Model evaluation in supervised learning should be treated as a context-dependent, decision-oriented process aligned with operational objectives rather than relying on a small set of aggregate metrics.