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

B-cos GNNs: Faithful Explanations through Dynamic Linearity

cs.LG · 2026-05-19 · unverdicted · novelty 7.0

B-cos GNNs achieve inherent explainability in graph neural networks by using linear aggregation and B-cos transforms to produce exact per-node per-feature contribution decompositions via dynamic linearity.

citing papers explorer

Showing 1 of 1 citing paper.

  • B-cos GNNs: Faithful Explanations through Dynamic Linearity cs.LG · 2026-05-19 · unverdicted · none · ref 15

    B-cos GNNs achieve inherent explainability in graph neural networks by using linear aggregation and B-cos transforms to produce exact per-node per-feature contribution decompositions via dynamic linearity.