ASP-POTASSCO: Algorithm Selection for Answer Set Programming Solvers

A 2014 dataset curated by the TabArena team for evaluating predictive machine learning models on independent and identically distributed tabular data. It originates from a study on algorithm selection for Answer Set Programming solvers, with the intended task being classification. The dataset was sourced from OpenML and is associated with published research.

Use Cases

• Benchmarking classification models for independent and identically distributed data based on the dataset's stated focus.
• Studying algorithm selection performance based on features derived from solver benchmark results.
• Evaluating predictive models for computational logic tasks based on the dataset's domain.

Strengths

• Dataset is explicitly curated for evaluating predictive ML models on IID tabular data.
• Associated with a peer-reviewed research paper from 2014, providing academic context.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, sample data, and file formats are unknown, which may limit suitability assessment.
• Last update date is unknown; freshness unverified.

Provenance

Source

OpenML (id: 41705), originally from research by Hoos, Lindauer, and Schaub.

Collection Method

Curated from solver benchmark results; the TabArena team dropped leaking and constant columns.

Time Range

2014

Freshness

Dataset Year is 2014; last update is unknown.

Geography

null