Metraipolis › archive › dc_7e3236967f1b

Calibration Count Reuse: Validity Does Not Determine Efficiency — arXiv:2609.25138

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25138
License (as archived)
CC0-1.0
Archived
2026-10-08T15:08:09.761Z
SHA-256 of the archived text
6c6376119aa0300a1d3bd75807fe909cd9925eb080a28106c19d871ce0f70812
Stable URL of this page
https://metraipolis.com/documento/dc_7e3236967f1b

How to cite

Calibration Count Reuse: Validity Does Not Determine Efficiency — arXiv:2609.25138 — arXiv (en), https://arxiv.org/abs/2609.25138 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e3236967f1b (Metraipolis archive dc_7e3236967f1b, sha256 6c6376119aa0300a1d3bd75807fe909cd9925eb080a28106c19d871ce0f70812)
BibTeX
@misc{dc7e3236967f1b,
  title = {Calibration Count Reuse: Validity Does Not Determine Efficiency — arXiv:2609.25138},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25138},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e3236967f1b; sha256 6c6376119aa0300a1d3bd75807fe909cd9925eb080a28106c19d871ce0f70812},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25138. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Calibration count reuse raises separate validity and efficiency questions. We give a validity criterion for general count-dependent nonconformity scores: transferring one count from another class to the scored class must not improve its conformity. A leave-self-out full conformal reference proves the criterion without requiring normalization or preservation of same-class score order. For a common separable transformation, universal exchangeable validity is equivalent to being nondecreasing in the count, provided $K\alpha \geq 1$; normalized multiplicative weights obey the complementary nonincreasing condition. Additive penalties are covered under the stated information restrictions. Efficiency has no parallel ordering: two iid constructions make the same valid rule improve or worsen expected size at unchanged coverage. An expanded 55-rule study finds no resolved advantage from selected live-count rules over uniform weights. Image studies identify undercoverage under iid resampling, including at numerical convergence. Separately, execution of the released Conf-OT pipeline on its DTD and Aircraft benchmark subsets produces near-nominal median coverage under fixed stratified counts. The native results are reported separately from the iid analyses, without treating a benchmark observation as a universal guarantee. The findings separate validity, classifier confidence, numerical convergence, and population-specific efficiency.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.LG).
Categorie arXiv: Methodology (stat.ME) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.25138 — 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 2026-10-08T14:37:29.515Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).