2026-10-14T01:46:47Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34010472 2026-09-29T03:25:56Z category_26749 category_29173 item_type_3 month_year_09_2026

MetalloSR: Curated Metallurgical Equations, Structural Annotations, and Synthetic Benchmarks for Symbolic Regression AKASH RAJ A S (25104835) Prince Gideon Kubendran Amos (22423150) Materials engineering not elsewhere classified Machine learning not elsewhere classified MetalloSR Symbolic Regression Metallurgy Materials Informatics Metallurgical equations Equation discovery Scientific machine learning PySR Structural Clustering Synthetic benchmark datasets Interpretable Machine Learning Probabilistic grammar <p dir="ltr">This dataset supports the development and evaluation of MetalloSR, a metallurgy-specific symbolic regression framework that uses structural information from established metallurgical equations to guide the search for interpretable mathematical relationships.</p><p dir="ltr">The core corpus comprises 1,324 equations curated from textbooks and reference materials in metallurgy and materials science. The equations cover topics including mechanical behaviour, thermodynamics, kinetics, diffusion, phase transformations, metal forming, welding, and casting and solidification. Equations are represented in machine-readable form using LaTeX expressions and associated metadata.</p><p dir="ltr">Structural annotations describe mathematical operators, functions, exponent patterns, and equation families. The accompanying feature representations and assignments to 13 structural clusters support the construction of cluster-specific probabilistic grammars for symbolic regression with PySR. Parsing methods and annotation fields should be considered when interpreting the structural information, because automatically extracted representations may contain parsing limitations.</p><p dir="ltr">The accompanying synthetic benchmark datasets are generated from known physical and metallurgical relationships and are intended to evaluate equation recovery and regression performance. These numerical benchmarks are simulated data, rather than experimental measurements.</p><p dir="ltr">The resources support research into domain-informed symbolic regression, mathematical structure analysis, materials informatics, and interpretable scientific machine learning. The equation corpus provides information for grammar construction, while the synthetic numerical datasets provide separate regression tasks.</p><p dir="ltr">This dataset accompanies the manuscript “MetalloSR - A Metallurgy Specific Symbolic Regression Framework.” When using these resources, please cite this dataset and acknowledge the original literature sources associated with the underlying equations. A link to the associated article will be added when available.</p> 2026-09-29T03:25:56Z Dataset Dataset 10.6084/m9.figshare.34010472.v3 https://figshare.com/articles/dataset/MetalloSR_Curated_Metallurgical_Equations_Structural_Annotations_and_Synthetic_Benchmarks_for_Symbolic_Regression/34010472 CC BY 4.0