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

2025 1

verdicts

CONDITIONAL 1

representative citing papers

XAI-Units: Benchmarking Explainability Methods with Unit Tests

cs.LG · 2025-06-01 · conditional · novelty 6.0

XAI-Units offers synthetic datasets and handcrafted models with known ground-truth attributions to unit-test feature attribution methods, and demonstrates its use by revealing a normalization bug in Captum's DeepLIFT.

citing papers explorer

Showing 1 of 1 citing paper.

  • XAI-Units: Benchmarking Explainability Methods with Unit Tests cs.LG · 2025-06-01 · conditional · none · ref 2

    XAI-Units offers synthetic datasets and handcrafted models with known ground-truth attributions to unit-test feature attribution methods, and demonstrates its use by revealing a normalization bug in Captum's DeepLIFT.