Metraipolis › archive › dc_05d6bfef231f
Truthful Calibration Measures for Sequential Prediction — arXiv:2608.21348
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.21348
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T10:31:41.168Z
- SHA-256 of the archived text
a30b052702fce9a124c78d832cc4aaa3e43da6096c0b38db76ff591131c6e1c5- Stable URL of this page
https://metraipolis.com/documento/dc_05d6bfef231f
How to cite
Truthful Calibration Measures for Sequential Prediction — arXiv:2608.21348 — arXiv (en), https://arxiv.org/abs/2608.21348 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_05d6bfef231f (Metraipolis archive dc_05d6bfef231f, sha256 a30b052702fce9a124c78d832cc4aaa3e43da6096c0b38db76ff591131c6e1c5)
BibTeX
@misc{dc05d6bfef231f,
title = {Truthful Calibration Measures for Sequential Prediction — arXiv:2608.21348},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.21348},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_05d6bfef231f; sha256 a30b052702fce9a124c78d832cc4aaa3e43da6096c0b38db76ff591131c6e1c5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21348. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Calibration requires probabilistic reports to be conditionally unbiased and reliably interpretable as probabilities. A calibration measure assigns numerical error to miscalibrated reports. Haghtalab et al. (2024) proposed an approximately truthful calibration measure for online prediction, leaving open whether exact truthfulness is compatible with completeness and soundness. We resolve this question negatively for sequential binary prediction: exact truthfulness is incompatible with completeness and soundness, even for independent outcomes. We then show that this impossibility is specific to exact truthfulness. We give two general reductions from a base calibration measure, producing additively and multiplicatively approximately truthful calibration measures, respectively. Applying the multiplicative reduction, for every $0 < \varepsilon < 1$ we construct a sound and complete calibration measure that is $(1+\exp(-T^{(1-\varepsilon)/2}/2))$-multiplicatively truthful. This improves the approximate-truthfulness guarantee of Haghtalab et al. (2024).
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-24 in cs.LG).
Categorie arXiv: Data Structures and Algorithms (cs.DS) ; Computer Science and Game Theory (cs.GT); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.21348 — 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 2026-10-18T10:27:56.011Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).