10-Fold Cross-Validation Dice Scores for a 10-Table Model

Muthulakshmi Kirubakaran published a 5.5 KB Excel file on figshare in May 2026. The dataset contains the best validation Dice score per fold from a 10-fold cross-validation procedure, presented as a mean and standard deviation across folds. The data likely originates from a machine learning experiment involving a model trained on 10 tables.

Use Cases

• Benchmarking model performance based on reported cross-validation Dice scores.
• Analyzing the stability of a model across different data folds based on the standard deviation metric.
• Comparing validation strategies for multi-table learning tasks referenced in the description.

Strengths

• Data is licensed under CC-BY-4.0, permitting open sharing and adaptation.
• The 5.5 KB file size indicates a lightweight, easily downloadable resource.

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 is unknown, which may limit suitability assessment.

Provenance

Source

figshare

Collection Method

Likely generated from a machine learning experiment involving 10-fold cross-validation.

Freshness

Last updated 2026-05-18 17:47:22; freshness should be verified.