Metraipolis › archive › dc_b128fc843fe4
Confidence regions for SAFE AI compliance scores — arXiv:2609.29588
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.29588
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T06:03:33.886Z
- SHA-256 of the archived text
737315991bfdb48c5b7bedfe5463ff07a3fbe17c5f239f2b55b3b301c752cbc0- Stable URL of this page
https://metraipolis.com/documento/dc_b128fc843fe4
How to cite
Confidence regions for SAFE AI compliance scores — arXiv:2609.29588 — arXiv (en), https://arxiv.org/abs/2609.29588 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b128fc843fe4 (Metraipolis archive dc_b128fc843fe4, sha256 737315991bfdb48c5b7bedfe5463ff07a3fbe17c5f239f2b55b3b301c752cbc0)
BibTeX
@misc{dcb128fc843fe4,
title = {Confidence regions for SAFE AI compliance scores — arXiv:2609.29588},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.29588},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b128fc843fe4; sha256 737315991bfdb48c5b7bedfe5463ff07a3fbe17c5f239f2b55b3b301c752cbc0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29588. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Artificial Intelligence trustworthiness scores are moving from research dashboards into compliance claims and procurement decisions. A compliance claim is a statistical decision based on the comparison between an estimated compliance metric and a set threshold. The recently proposed integrated SAFE AI metrics are based on three basic rank-graduation measures of accuracy, explainability and robustness, expressed on a common footing. The metrics are integrated into a single compliance score, so far reported as a point value. In this paper we propose to add an uncertainty layer to the SAFE AI compliance score. All component metrics are estimated on a shared test sample, so their errors covary. We estimate the full covariance of the component vector with a paired bootstrap, and quantify departures from the source-wise independence baseline suggested by the integrated-metrics framework's variability decomposition. A closed-form identity splits such departure into an uncertainty-weighted effective dimension and an exposure-weighted data-driven correlation, with both depending on the aggregator and the estimated uncertainty of the component metrics. The application of our proposal to both real and simulated data shows that the assumption of independence can either narrow or widen confidence bands, while the direction and magnitude of the effect depend on the aggregator type, machine learning model, and perturbation family. The resulting confidence region supports compliance decisions, which can be documented in a formal uncertainty certificate. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in stat.ME). Categorie arXiv: Methodology (stat.ME). Pagina del lavoro: https://arxiv.org/abs/2609.29588 — 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 2026-10-08T05:30:42.720Z dalla pagina https://arxiv.org/catchup/stat.ME/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).