Metraipolis › archive › dc_517bdaa4611e
AI Evaluation Should Measure Verification Cost, Not Correctness Alone — arXiv:2608.08709
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.08709
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:01:05.912Z
- SHA-256 of the archived text
a3596ccb2ffbb4f15ed20f9706f2e6ac30e7db6c28c7a3445082f32dcf73d172- Stable URL of this page
https://metraipolis.com/documento/dc_517bdaa4611e
How to cite
AI Evaluation Should Measure Verification Cost, Not Correctness Alone — arXiv:2608.08709 — arXiv (en), https://arxiv.org/abs/2608.08709 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_517bdaa4611e (Metraipolis archive dc_517bdaa4611e, sha256 a3596ccb2ffbb4f15ed20f9706f2e6ac30e7db6c28c7a3445082f32dcf73d172)
BibTeX
@misc{dc517bdaa4611e,
title = {AI Evaluation Should Measure Verification Cost, Not Correctness Alone — arXiv:2608.08709},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.08709},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_517bdaa4611e; sha256 a3596ccb2ffbb4f15ed20f9706f2e6ac30e7db6c28c7a3445082f32dcf73d172},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08709. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The reliability of AI generative models is typically measured by output correctness, yet in practice it depends on the effort required to verify those outputs. We argue that current evaluation metrics overlook a critical failure mode: Verification-Cost Errors (VCEs), defined as incorrect input-output pairs that a declared fraction of the verifier population fails to identify within the verification budget available in a given deployment context. Unlike standard notions of "hallucination", VCEs are defined operationally, by the failure of correct identification within budget rather than by any property of the output itself. Plausibility and authoritative presentation are hypothesised contributors to that failure, not defining conditions. To capture this asymmetry, we introduce the notion of verification cost relative to a deployment budget as an operational dimension that current evaluation does not routinely capture. The quantity is presented as a conceptual instrument rather than a finalized metric. Evidence from code generation and multi-modal document understanding shows that high benchmark accuracy can mask significant verification effort in practice. We therefore take the position that correctness alone is insufficient as a measure of reliability. AI evaluation should explicitly account for verification cost, reflecting whether errors can be detected under realistic resource constraints. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-11 in cs.SE). Categorie arXiv: Artificial Intelligence (cs.AI) ; Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2608.08709 — 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 2026-10-19T09:00:31.518Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).