A composition-only ML framework with Rashomon ensembles extracts consensus design rules and screens ~45,000 compounds to identify 122 high-confidence quantum defect hosts, recovering known materials and predicting new ones validated by limited DFT.
The matthews correlation coefficient (mcc) should replace the roc auc as the standard metric for assessing binary classification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.mtrl-sci 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Beyond Diamond: Interpretable Machine Learning Reveals Design Principles for Quantum Defect Host Materials
A composition-only ML framework with Rashomon ensembles extracts consensus design rules and screens ~45,000 compounds to identify 122 high-confidence quantum defect hosts, recovering known materials and predicting new ones validated by limited DFT.