Datasets

EngineAD

EngineAD is a real-world vehicle engine anomaly detection dataset designed for safety-critical transportation applications.

• Collected from a fleet of 25 commercial vehicles over 6 months.
• Includes high-resolution telemetry sampled at approximately 1-second intervals from engine-related sensors.
• Covers 13 raw engine signals (e.g., pressure, temperature, fuel-rate, rotational-speed related channels).
• Includes expert annotations distinguishing normal operation from early signs of incipient faults.
• Provides processed segment-level data commonly used for benchmarking (including principal-component-based representations).

Dataset page: BorealisData - EngineAD (DOI:10.5683/SP3/TX13P1)

Related papers:

• EngineAD: A Real-World Vehicle Engine Anomaly Detection Dataset (AAAI ASTAD 2026)
• Multivariate Time-Series Anomaly Detection with Temporal Self-supervision and Graphs (ECML PKDD 2023)

Citation policy: If you use EngineAD, please cite the related papers above (as requested in the EngineAD GitHub description).

MultiTab — Synthetic Multitask Data

Generate synthetic multitask regression datasets with controllable task correlations, polynomial complexity, and noise levels.

Generator: Open the MultiTab generator →

Related paper:

• MultiTab: A Scalable Foundation for Multitask Learning on Tabular Data (AAAI 2026)

Citation policy: If you use MultiTab or the synthetic generator for experiments, please cite the paper above (as requested in the MultiTab GitHub description).

Upcoming datasets

CARLA-Collide

Description to be added.

Link: TBD

Real-Collide

Description to be added.

Link: TBD