Metraipolis › archive › dc_29129746db97
Status Association Does Not Reliably Predict Decision Leakage — arXiv:2608.10089
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.10089
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:08:53.104Z
- SHA-256 of the archived text
34b6ebf4f71f96270b77dc6e34376c05ca47e08e6754313827480519443d66d9- Stable URL of this page
https://metraipolis.com/documento/dc_29129746db97
How to cite
Status Association Does Not Reliably Predict Decision Leakage — arXiv:2608.10089 — arXiv (en), https://arxiv.org/abs/2608.10089 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_29129746db97 (Metraipolis archive dc_29129746db97, sha256 34b6ebf4f71f96270b77dc6e34376c05ca47e08e6754313827480519443d66d9)
BibTeX
@misc{dc29129746db97,
title = {Status Association Does Not Reliably Predict Decision Leakage — arXiv:2608.10089},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.10089},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_29129746db97; sha256 34b6ebf4f71f96270b77dc6e34376c05ca47e08e6754313827480519443d66d9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10089. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Bias evaluations often move too quickly from evidence that a model encodes a social association to claims that the same association will alter consequential decisions. We test whether that inference is warranted using Chilean surnames as controlled socioeconomic probes. We evaluate eight frozen model-provider cells on 1,032 prompts each, yielding 8,256 verified primary responses. The design separates forced latent association from matched consequential decisions across academic selection, professional hiring, research fellowship selection, and legal-aid intake. Elite-coded surnames received higher forced high-status probability mass than common surnames in seven of eight models and higher mass than rare-frequency controls in all eight. Yet elite-minus-common decision effects were close to zero for most systems. Five models were statistically equivalent within a predeclared (Plus-Minus)0.10 standard-deviation margin, while the remaining three were imprecise or borderline, with no consistent elite advantage. Association strength did not reliably predict decision leakage across models (r = 0.201, p = 0.633) or across frozen surname-pair-by-model cells (r = 0.065, p = 0.565). The central result is a measurement dissociation: latent social association and consequential treatment are empirically distinct constructs. Evaluations should measure the transition from association to action directly. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.AI). Categorie arXiv: Applications (stat.AP) ; Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.10089 — 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 2026-10-19T05:57:28.332Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).