Metraipolis › archive › dc_fed591abbe8e

Sharp and Stable Label-Free Calibration Certificates from Logical Coherence — arXiv:2610.21567

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.21567
License (as archived): CC0-1.0
Archived: 2026-10-16T10:22:33.713Z
SHA-256 of the archived text: 48e567b2a58ba3cc4939e5a3f493028cb249dba875192e97e06028a4ed6b196c
Stable URL of this page: https://metraipolis.com/documento/dc_fed591abbe8e

How to cite

Sharp and Stable Label-Free Calibration Certificates from Logical Coherence — arXiv:2610.21567 — arXiv (en), https://arxiv.org/abs/2610.21567 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fed591abbe8e (Metraipolis archive dc_fed591abbe8e, sha256 48e567b2a58ba3cc4939e5a3f493028cb249dba875192e97e06028a4ed6b196c)

BibTeX

@misc{dcfed591abbe8e,
  title = {Sharp and Stable Label-Free Calibration Certificates from Logical Coherence — arXiv:2610.21567},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21567},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fed591abbe8e; sha256 48e567b2a58ba3cc4939e5a3f493028cb249dba875192e97e06028a4ed6b196c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21567. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Query-conditioned probabilistic predictors answer logically related questions one at a time, and labels to check their calibration are often missing. For each restriction on what a bettor's stakes may use, a minimax theorem identifies, for finitely supported laws of the answers, the sharp label-free lower bound on the corresponding calibration residual. On bundles of different events its mean, marginal and joint stages can separate strictly, and a bundle's bound cannot be attributed to one question without assumptions on the others. The sharp marginal bound is discontinuous in the answers, and no label-free lower bound continuous in the Wasserstein distance stays within a constant factor of it. Lipschitz stakes give a stable bound, sharp for a smooth calibration residual and, for every positive Lipschitz constant, positive exactly when the sharp marginal bound is. On i.i.d. streams, projected online gradient ascent at fixed nodes gives fixed-horizon certificates whose shortfall is bounded by grid, learning and statistical terms, and predictable betting gives anytime-valid ones. In a preregistered study of four predictors on two data sets, all seven confirmatory certificates were positive (the eighth pair did not pass the pilot). A certificate shows only that calibration is at least this bad; zero means "not refuted".

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.21567 — 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 2026-10-16T08:48:02.732Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).