PiNets are pseudo-linear networks that form linear models instance-wise to enforce explanatory alignment, where explanations construct rather than rationalize predictions, and are evaluated as faithful on image classification and segmentation via MARS criteria.
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
-
Aligned explanations in neural networks
PiNets are pseudo-linear networks that form linear models instance-wise to enforce explanatory alignment, where explanations construct rather than rationalize predictions, and are evaluated as faithful on image classification and segmentation via MARS criteria.