Metraipolis › archive › dc_f8463f441bdd

Does Explainability Survive Data Drift? — arXiv:2610.05379

Source
arXiv
Original
https://arxiv.org/abs/2610.05379
License (as archived)
CC0-1.0
Archived
2026-10-06T05:26:53.686Z
SHA-256 of the archived text
2fa61b2821abf9fe03512bfb9d14de764bb0d828323ceed3112fbb3a644c909b
Stable URL of this page
https://metraipolis.com/documento/dc_f8463f441bdd

How to cite

Does Explainability Survive Data Drift? — arXiv:2610.05379 — arXiv, https://arxiv.org/abs/2610.05379 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f8463f441bdd (Metraipolis archive dc_f8463f441bdd, sha256 2fa61b2821abf9fe03512bfb9d14de764bb0d828323ceed3112fbb3a644c909b)
BibTeX
@misc{dcf8463f441bdd,
  title = {Does Explainability Survive Data Drift? — arXiv:2610.05379},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05379},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f8463f441bdd; sha256 2fa61b2821abf9fe03512bfb9d14de764bb0d828323ceed3112fbb3a644c909b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05379. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Model performance monitoring is a standard practice in machine learning deployments. Detection performance is tracked continuously, and model decay is expected as the relationship between the feature and target variables degrades, a phenomenon known as concept drift. Explanation fidelity, however, is rarely monitored with the same discipline, even in domains such as financial systems, healthcare, and other regulated environments where explanations are required for governance purposes. This paper investigates whether explanations can decay under data drift, even when the feature-target relationship remains stable, and whether explanations produced before drift occurs remain faithful to the decisions of the model that replaces them. Using the IEEE-CIS Transaction Fraud Detection dataset, we find statistically significant covariate shift but no statistically significant evidence of concept drift under the implemented conditional-drift tests, thereby providing an empirical setting in which input distributional change can be studied separately from detectable changes in the feature-target relationship. Local explanations are generated with ExIFFI and evaluated at three levels: path validity, structural behaviour, and fidelity under controlled intervention. Results show that while prior explanations retain substantial decision relevance to a retrained model, they are consistently less faithful than newly generated explanations, with no evidence of a systematically widening gap across the evaluated windows. The study shows that explanation fidelity requires its own monitoring, that structural stability of explanations does not guarantee functional fidelity, and that explanations should be treated as artifacts tied to the model that produced them.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.05379 — 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 2026-10-06T05:24:06.017Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).