Metraipolis › archive › dc_878bbadab71f
FMMO: Detecting the Divergence Between Local Attribution and Global Drift — arXiv:2609.06173
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.06173
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:56:39.502Z
- SHA-256 of the archived text
21862ed965b5ec542c01a4120a56bc0802c4bccd1897e3391445bd9a10bf3bab- Stable URL of this page
https://metraipolis.com/documento/dc_878bbadab71f
How to cite
FMMO: Detecting the Divergence Between Local Attribution and Global Drift — arXiv:2609.06173 — arXiv (en), https://arxiv.org/abs/2609.06173 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_878bbadab71f (Metraipolis archive dc_878bbadab71f, sha256 21862ed965b5ec542c01a4120a56bc0802c4bccd1897e3391445bd9a10bf3bab)
BibTeX
@misc{dc878bbadab71f,
title = {FMMO: Detecting the Divergence Between Local Attribution and Global Drift — arXiv:2609.06173},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.06173},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_878bbadab71f; sha256 21862ed965b5ec542c01a4120a56bc0802c4bccd1897e3391445bd9a10bf3bab},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06173. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Post-deployment drift poses a critical risk to algorithmic accountability, particularly when ground truth labels are delayed and performance degradation becomes a "silent failure". While Explainable AI (XAI) is often relied upon to audit these shifts, we demonstrate that popular local attribution methods (e.g., TreeSHAP) can exhibit misleading stability even as model reliability collapses. In this paper, we propose a Framework for Model Monitoring and Observability (FMMO) designed to expose the divergence between local explanation stability and global distribution shifts. Using benchmark, synthetic, and real-world datasets, we show that local XAI methods fail to flag drift-induced disparate impact, specifically where False Positive Rates spike for protected groups while feature attributions remain unchanged. By integrating global surrogate models with model utilization measurements, FMMO mitigates this fairness blind spot, ensuring that stakeholders can detect discriminatory deterioration that standard local XAI tools overlook. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.06173 — 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 2026-10-16T13:39:42.851Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).