Metraipolis › archive › dc_d1bae4e4e8ac

What Lies Beyond Perception: A Partition Theory of the Limits of AI Evaluation and Oversight — arXiv:2610.30803

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.30803
License (as archived): CC0-1.0
Archived: 2026-10-25T21:34:37.575Z
SHA-256 of the archived text: 43bbf99920b366c945e7d8ceefd3d9c377590a030a3179909ab34cd97cbe115b
Stable URL of this page: https://metraipolis.com/documento/dc_d1bae4e4e8ac

How to cite

What Lies Beyond Perception: A Partition Theory of the Limits of AI Evaluation and Oversight — arXiv:2610.30803 — arXiv (en), https://arxiv.org/abs/2610.30803 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d1bae4e4e8ac (Metraipolis archive dc_d1bae4e4e8ac, sha256 43bbf99920b366c945e7d8ceefd3d9c377590a030a3179909ab34cd97cbe115b)

BibTeX

@misc{dcd1bae4e4e8ac,
  title = {What Lies Beyond Perception: A Partition Theory of the Limits of AI Evaluation and Oversight — arXiv:2610.30803},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.30803},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d1bae4e4e8ac; sha256 43bbf99920b366c945e7d8ceefd3d9c377590a030a3179909ab34cd97cbe115b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30803. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Replacing the judge can move a benchmark score, and models can be trained to hide capabilities. Both put the evaluator in question: what can it certify? We develop a partition theory of evaluation from one principle: judgement is bounded by perception. An agent's discrimination is the partition of its inputs into classes it cannot tell apart. Discrimination is necessary for capability but not sufficient, so bounds on it bear directly on whether evaluation can show that a model lacks an ability. We prove a one-sided bound. An examinee whose partition refines its evaluator's has the discrimination to pass every test the evaluator can grade, provided each input has an acceptable reply. We define the echo test, which accepts any reply the evaluator perceives as identical to the input, and show that it is complete for the tests the evaluator can grade. Passing therefore certifies at most a floor on discrimination, never a ceiling, and only a sharper evaluator can raise it. Used to detect concealment, echo-test failure points the wrong way: under exhaustive probing it flags every honestly weaker examinee and no concealer that presents as the evaluator's peer. Exact imitation of a weaker model is undetectable by any behavioural evaluator. We extend the bound to ensembles of monitors and to channels a model controls, explain published findings on judge disagreement and sandbagging, and derive testable predictions. A safety case that argues from behavioural evaluation alone that a model lacks an ability must assume the model's cooperation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computers and Society (cs.CY); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.30803 — 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 2026-10-25T21:25:18.116Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).