Pré-Publication, Document De Travail Année : 2025

How to judge a competition: Fairly judging a competition or assessing benchmark results

Résumé

This paper addresses how to minimize randomness in competition or benchmark judging. We discuss scoring metrics, size of test data, error bars, splitting into phases, and score aggregation methods. Our approach blends theoretical insights with practical guidelines, aiming to provide a clear framework for effective decision making and reduced uncertainty.

Fichier principal
Vignette du fichier
judging_competition_book_chapter4_adrien_pavao-1.pdf (1.04 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05169899 , version 1 (18-07-2025)

Licence

Identifiants

  • HAL Id : hal-05169899 , version 1

Citer

Adrien Pavão. How to judge a competition: Fairly judging a competition or assessing benchmark results. 2025. ⟨hal-05169899⟩
334 Consultations
690 Téléchargements

Partager

  • More