Metraipolis › archive › dc_dc483548c3ee

Measuring Explainer Stability via Attribution Separability — arXiv:2608.02697

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.02697
License (as archived)
CC0-1.0
Archived
2026-10-31T12:17:41.285Z
SHA-256 of the archived text
e25c1e2f66c901b2fd892ce0f7cb0f73667497af6c263bbb632df949fa14dc9b
Stable URL of this page
https://metraipolis.com/documento/dc_dc483548c3ee

How to cite

Measuring Explainer Stability via Attribution Separability — arXiv:2608.02697 — arXiv (en), https://arxiv.org/abs/2608.02697 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dc483548c3ee (Metraipolis archive dc_dc483548c3ee, sha256 e25c1e2f66c901b2fd892ce0f7cb0f73667497af6c263bbb632df949fa14dc9b)
BibTeX
@misc{dcdc483548c3ee,
  title = {Measuring Explainer Stability via Attribution Separability — arXiv:2608.02697},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.02697},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dc483548c3ee; sha256 e25c1e2f66c901b2fd892ce0f7cb0f73667497af6c263bbb632df949fa14dc9b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.02697. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Attribution methods (AMs) assign an importance score to each feature and are widely adopted to explain black-box models. However, most methods can produce variable attribution scores due to stochastic components in their definition. In this paper, we propose a distribution-based framework to capture the stability of attribution scores. In particular, our approach allows to understand the degree of separability in the ranked attribution vector and obtain the largest index for which a feature ranking remains reliable. We further extend this framework to compare AMs based on the robustness of their rankings across a dataset. Through experiments, we demonstrate how to apply our method to evaluate explainer stability. Overall, our approach provides a complementary criterion for evaluating the stability of AMs.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.02697 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T12:05:52.938Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).