A new 2x2 diagnostic matrix classifies probabilistic classifiers into Eagles, Bulls, Sloths, and Moles by calibration and discrimination, with empirical archetype assignments and a proof that post-hoc calibration cannot add discriminatory power.
Advances in Neural Information Processing Systems , volume=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Manokhin Probability Matrix: A Diagnostic Framework for Classifier Probability Quality
A new 2x2 diagnostic matrix classifies probabilistic classifiers into Eagles, Bulls, Sloths, and Moles by calibration and discrimination, with empirical archetype assignments and a proof that post-hoc calibration cannot add discriminatory power.