Welcome to the Multiverse

The archive and benchmark repository for multivariate time series classification.

Datasets · Results · Leaderboard · Experiments · Classifiers · Contributing

The Multiverse is a new archive of multivariate time series classification datasets. This repository is for accessing, benchmarking, and extending this new archive.

It brings together datasets, published results, reproducible evaluation workflows, and leaderboard infrastructure in one place. The aim is to make it easier to:

• access benchmark datasets for multivariate time series classification,
• load data into Python workflows,
• explore and compare against published results,
• reproduce baseline experiments,
• evaluate new classifiers consistently,
• and contribute new algorithms and results back to the archive.

This repository is intended as both a practical resource for researchers and a public record of benchmark results.

Top of the league

Places 1 to 5 by ranks

Quick start

Load a dataset

Use the examples in examples/aeon_quickstart.py as a starting point for downloading and loading Multiverse datasets.

Run an experiment

To reproduce a benchmark run or evaluate a new classifier, start from:

• experiments/run_single_dataset.py
• experiments/run_benchmark.py

Explore the results

Browse the generated leaderboard views in:

• leaderboards/leaderboard.md

Donate your code and published results

For submission layout and result schema, see:

• results/README.md
• results/schema.md

Repository layout

multiverse/
├── docs/                  # Documentation
├── experiments/           # Benchmark and reproduction scripts
├── results/               # Submitted results and schema
└── src/                   # Python package source for classifiers