Metraipolis › archive › dc_f58fdb98adbe
Verification with Transfer: Exact Information Frontiers and Their Price in Calls — arXiv:2610.12211
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.12211
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:20:39.968Z
- SHA-256 of the archived text
cc222b37b300253c0850e7fc608fe9548c848709892a7f0e70c379c26b57aa4c- Stable URL of this page
https://metraipolis.com/documento/dc_f58fdb98adbe
How to cite
Verification with Transfer: Exact Information Frontiers and Their Price in Calls — arXiv:2610.12211 — arXiv (en), https://arxiv.org/abs/2610.12211 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f58fdb98adbe (Metraipolis archive dc_f58fdb98adbe, sha256 cc222b37b300253c0850e7fc608fe9548c848709892a7f0e70c379c26b57aa4c)
BibTeX
@misc{dcf58fdb98adbe,
title = {Verification with Transfer: Exact Information Frontiers and Their Price in Calls — arXiv:2610.12211},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.12211},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f58fdb98adbe; sha256 cc222b37b300253c0850e7fc608fe9548c848709892a7f0e70c379c26b57aa4c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12211. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
A verifier that accepts or rejects whole answers reveals little: under a flat prior over $k$-bit answers, zero error needs $2^k-1$ verifications. The usual remedy is to solve related source tasks, either all first, as a curriculum does, or interleaved with verification. We price this remedy in information and in calls. With an exact verifier, the least causal information that any interleaving of source calls and $n$ verifications needs to succeed with probability $s$ is a list rate-distortion function, attained by one observation before any verification. It lower-bounds the expected number of binary source calls, which designed sources meet within $1+\log_25$ calls for unique answers and within a logarithmic term in general, where no additive constant suffices. With an exact verifier and fixed sources, moving every call before the first verification preserves all hard caps on calls, although interleaving can save unboundedly many expected calls; under a noisy verifier, source-first protocols can lose unbounded factors in information and in error. For linear banks over $\mathbb{F}_2$, optimal accuracy has a closed form, and after a polynomial-time reduction the budget profile is computable in time $2^{O(h^2)}\operatorname{poly}(J,k+h)$ for $J$ sources and nuisance dimension $h$. In these banks, for zero error under a hard cap, the calls beyond the rounded-up information price are exactly those spent on nuisance. Every numbered result apart from two clauses about the planner is machine-checked in Lean 4, assuming two published results. Used as a ruler, the frontier shows a small transformer using all delivered bits at latent dimension $5$ and none at $11$ within fixed training budgets; in a test with predictions recorded before training, low XOR degree of the target bits did not suffice for their use.
Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Cryptography and Security (cs.CR); Information Theory (cs.IT); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.12211 — 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 2026-10-09T05:50:01.003Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).