arXiv preprint arXiv:2310.03149 , year=

Attributing Learned Concepts in Neural Networks to Training Data , author= · arXiv 2310.03149

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

1 Pith paper citing it

representative citing papers

cs.CY · 2026-05-06 · unverdicted · novelty 5.0

Rigorous interpretability can function as a principled form of model evaluation if its claims are falsifiable, reproducible, and predictive.

Showing 1 of 1 citing paper.

Rigorous Interpretation Is a Form of Evaluation cs.CY · 2026-05-06 · unverdicted · none · ref 79
Rigorous interpretability can function as a principled form of model evaluation if its claims are falsifiable, reproducible, and predictive.