Metraipolis › archive › dc_8be384bd5543

How to Verify Probabilistic Consistency of Predictive Models — arXiv:2608.11181

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.11181
License (as archived)
CC0-1.0
Archived
2026-10-19T06:09:42.056Z
SHA-256 of the archived text
d21cd7a24b3a1ffeec86647a343e3c13d84fcd70a96a22896b929bf302fcc049
Stable URL of this page
https://metraipolis.com/documento/dc_8be384bd5543

How to cite

How to Verify Probabilistic Consistency of Predictive Models — arXiv:2608.11181 — arXiv (en), https://arxiv.org/abs/2608.11181 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8be384bd5543 (Metraipolis archive dc_8be384bd5543, sha256 d21cd7a24b3a1ffeec86647a343e3c13d84fcd70a96a22896b929bf302fcc049)
BibTeX
@misc{dc8be384bd5543,
  title = {How to Verify Probabilistic Consistency of Predictive Models — arXiv:2608.11181},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11181},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8be384bd5543; sha256 d21cd7a24b3a1ffeec86647a343e3c13d84fcd70a96a22896b929bf302fcc049},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11181. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

When a probabilistic predictor answers many conditional-probability queries, are its answers self-consistent, and can this be verified in polynomial time? This problem is of interest for AI safety, where safety is derived from honesty about probabilistic predictions of unwanted outcomes potentially caused by an AI action. We construct an interactive PCP as follows. Let a predictive model be specified by a probability circuit P and a circuit Q which outputs confidence in predictions. Together, P and Q implicitly specify exponentially many probabilistic claims. We show a protocol in which a polynomial-time verifier can verify the approximate consistency of (P,Q). The verifier is given the pair of circuits (P,Q), which it evaluates at only a few points; alongside them it is given a proof oracle, an encoding of a witnessing probability distribution allegedly consistent with the predictions of (P,Q), which it reads at a few locations while interacting with a single untrusted prover. En route, we must ensure the existence of a sparse witnessing distribution consistent with the model's predictions. To do so, we first consider witness distributions for the consistency of explicit probabilistic claims, rather than claims specified by a predictor: say m claims, each of the form Pr[Y = 1 | X = x] = p, over n Boolean variables. Building on work initiated by Nilsson (Artif. Intell., 1986), we place l_2-approximate probabilistic consistency of explicit claims in NP, with certificates of length O(mn + log B) in the input bit-precision B; we further show how a small additive completeness-soundness gap removes the dependence on B. Together these results provide a complexity-theoretic foundation for certifying the self-consistency of probabilistic predictors. We view our interactive PCP as a first step toward training predictive models to prove their own consistency.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.AI).
Categorie arXiv: Computational Complexity (cs.CC) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.11181 — 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 2026-10-19T05:57:28.434Z 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).