Metraipolis › archive › dc_742f421ba3ea
Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration — arXiv:2609.01072
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01072
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:52:17.362Z
- SHA-256 of the archived text
1e4b647359cd6955e33ab9be3764f37f678bd63c289a1edd90992827d5a01e27- Stable URL of this page
https://metraipolis.com/documento/dc_742f421ba3ea
How to cite
Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration — arXiv:2609.01072 — arXiv (en), https://arxiv.org/abs/2609.01072 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_742f421ba3ea (Metraipolis archive dc_742f421ba3ea, sha256 1e4b647359cd6955e33ab9be3764f37f678bd63c289a1edd90992827d5a01e27)
BibTeX
@misc{dc742f421ba3ea,
title = {Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration — arXiv:2609.01072},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01072},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_742f421ba3ea; sha256 1e4b647359cd6955e33ab9be3764f37f678bd63c289a1edd90992827d5a01e27},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01072. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Post-hoc calibration corrects reported confidence, yet a multiclass calibrator can also change the associated top-1 prediction. Accuracy captures only the net effect of these changes on correctness, not how often predictions change; the Top-1 Prediction Change Rate (TPCR) instead measures this frequency. We propose Calibrator-Output Repair for Top-1 Decision Preservation (CORD), the first post-fit adapter to impose exact prediction preservation by repairing the full calibrated probability vector. From the original and calibrated outputs alone, CORD determines the mass assigned to the original top-1. The calibrated conditional distribution allocates the remaining mass over the other classes, yielding a repaired vector whose own argmax recovers the original prediction. On the calibration split, CORD coordinates the repaired masses to retain the calibrated outputs' mean mass on original predictions whenever attainable. The adapter alters neither the fitted calibrator nor its direct output, fits no additional supervised map, and requires no user- or validation-tuned hyperparameter. Across CIFAR-10/100 and ImageNet-1K, CORD attains zero TPCR by construction and lowers mean ECE, NLL, and Brier relative to the corresponding direct outputs in every dataset; paired gains persist under distribution shift and across calibration-set sizes. CORD thus removes the preservation constraint from calibrator fitting and assigns exact recovery of the original decision to subsequent output repair. Our code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.01072 — 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 2026-10-17T06:41:55.833Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).