Metraipolis › archive › dc_2bdc351fbe61

Measuring AI harms with multidimensional Lorenz Zonoids — arXiv:2609.16004

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.16004
License (as archived)
CC0-1.0
Archived
2026-10-15T19:30:53.407Z
SHA-256 of the archived text
4778b4e0fff5e96d435496f884e184f4d2ba785099ee48b8bf4d73544e904cd3
Stable URL of this page
https://metraipolis.com/documento/dc_2bdc351fbe61

How to cite

Measuring AI harms with multidimensional Lorenz Zonoids — arXiv:2609.16004 — arXiv (en), https://arxiv.org/abs/2609.16004 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2bdc351fbe61 (Metraipolis archive dc_2bdc351fbe61, sha256 4778b4e0fff5e96d435496f884e184f4d2ba785099ee48b8bf4d73544e904cd3)
BibTeX
@misc{dc2bdc351fbe61,
  title = {Measuring AI harms with multidimensional Lorenz Zonoids — arXiv:2609.16004},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.16004},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2bdc351fbe61; sha256 4778b4e0fff5e96d435496f884e184f4d2ba785099ee48b8bf4d73544e904cd3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16004. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

While AI systems increasingly shape high-stakes societal domains, their governance is limited by the lack of risk management methods that operate on real harms, taking their severity, and not only their likelihood, into account. As a consequence, AI risk management models remain compliance-driven and provider-centric, offering limited insight into how harms are dangerous, and on what should be the priority of intervention. The problem is amplified by the nature of harm data which are typically ordinal and multidimensional. To solve the problem, and offer an effective risk assessment methodology, in this paper we propose to model harm data by means of Lorenz Zonoids and Gini indices. To this aim we propose to extend them in a multidimensional setting, and show how to practically calculate them for a real AI incident data repository, provided by the Massachusetts Institute of Technology. The empirical findings indicate that environmental, infrastructure, property, physical, and democracy-related harms attain the highest values under the two multidimensional Gini indices and therefore exhibit the strongest concentration in their joint direct, indirect, and inferred severity-frequency distributions. These concentration patterns may help identify categories that warrant closer examination when mitigation priorities are determined.

Tema degli esploratori: governance digitale e beni comuni (retro-catalogo arXiv: annunci del 2026-09-16 in cs.CY).
Categorie arXiv: Computers and Society (cs.CY) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.16004 — 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 2026-10-15T18:39:08.596Z dalla pagina https://arxiv.org/catchup/cs.CY/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).