Ordinal Solvation Framework: Polymer–Solvent Embeddings and Benchmark Data

A 14.9 MB dataset supporting the study 'Ordinal Alignment of Polymer Solvation States Enables Predictive Materials Design'. It contains processed data bundles for model training and a schema example, created by Zheng Jie Liew and last updated in April 2026. The dataset is intended for benchmarking and developing data-driven models for polymer–solvent solvation behavior.

Use Cases

• Benchmarking machine learning models based on provided polymer–solvent embeddings and precomputed descriptors.
• Reproducing the Ordinal Solvation Framework (OSF) modeling and evaluation workflows.
• Developing new data-driven models for predicting solvation-state labels in polymer–solvent systems.

Strengths

• Includes a 10% stratified subset illustrating the descriptor structure and labels.
• Provides embeddings enabling full reproduction of reported workflows without proprietary chemical structures.
• Dataset size is 14.9 MB, facilitating relatively quick download and processing.

Limitations

• The complete experimental dataset with extended annotations is not publicly released due to intellectual property constraints.
• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred from the provided schema example.

Provenance

Source

figshare

Collection Method

Likely contains experimentally annotated solvation-state labels and precomputed descriptors for polymer–solvent systems.

Freshness

Last updated 2026-04-12 18:43:44