keyword

CodaLab Competitions

CodaLab Competitions is an open-source web platform for organizing online scientific and machine-learning challenges, where participants submit results or code and compare performance on leaderboards. It supports multiple competition phases and can run submitted jobs in Docker containers using computing resources provided by organizers.

1 item

CodaLab Competitions: An Open Source Platform to Organize Scientific Challenges

Adrien Pavao, Isabelle Guyon, Anne-Catherine Letournel, Dinh-Tuan Tran, Xavier Baró, Hugo Jair Escalante, Sergio Escalera, Tyler Thomas, Zhen Xu

Organizations4Paradigm Inc.Centre de Visió per ComputadorChaLearnCNRSInstituto Nacional de Astrofísica, Óptica y ElectrónicaLISNTier0 Software Development LLCUniversitat de BarcelonaUniversitat Oberta de CatalunyaUniversité Paris-Saclay

Why you should read this

Presents an open-source framework that enables researchers to design, host, and scale reproducible machine learning competitions using custom Docker environments, multi-phase evaluations, and external compute resources.

CodaLab Competitions is an open source web platform designed to help data scientists and research teams to crowd-source the resolution of machine learning problems through the organization of competitions, also called challenges or contests. CodaLab Competitions provides useful features such as multiple phases, results and code submissions, multi-score leaderboards, and jobs running inside Docker containers. The platform is very flexible and can handle large scale experiments, by allowing organizers to upload large datasets and provide their own CPU or GPU compute workers.

Source

http://jmlr.org/papers/volume24/21-1436/21-1436.pdf

Added

2026-09-26