Pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Aligned explanations in neural networks

cs.LG · 2026-01-07 · unverdicted · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Aligned explanations in neural networks cs.LG · 2026-01-07 · unverdicted · none · ref 19

    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.