Music Surprisal Benchmarks: MIR Dataset Derivatives

MEX assets include metadata and precomputed baseline MID artifacts derived from standard Music Information Retrieval datasets. The dataset is a derivative of public sources like SALAMI and session, with licenses including CC0-1.0 and MIT. It was last updated on 2026-05-21 by author muthissar.

Use Cases

• Benchmarking music information retrieval models based on precomputed MID artifacts.
• Analyzing musical surprisal patterns based on metadata from standard MIR datasets.
• Training or evaluating machine learning models for music structure analysis based on SALAMI-derived configurations.

Strengths

• Derived from established public MIR datasets like SALAMI, which suggests a foundation in recognized research data.
• Includes precomputed baseline artifacts, which may reduce initial processing time for researchers.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and file formats are unknown, which may limit suitability assessment.

Provenance

Source

Derivatives of public datasets including SALAMI and session.

Collection Method

Metadata configurations and precomputed artifacts derived from source datasets.

Freshness

Last updated 2026-05-21 08:54:06; freshness should be verified.