Generative Matter

Harvard Dataverse 2026 Dataset Open access

Read full text
Authors: Catherine Graubard
DOI: 10.7910/dvn/u6o6ks
Cited by: 0

Abstract

The Generative Matter database is a large-scale, structured collection of inorganic material synthesis recipes designed to support AI-assisted material discovery, computational design workflows, and architectural material research. The database comprises over 120,000 unique material compositions, each represented by a standardized synthesis protocol, associated physicochemical properties, and machine-readable descriptors suitable for downstream analysis and generative applications.

Fields of Study & Subjects

Machine Learning in Materials Science History and advancements in chemistry Material Selection and Properties

Publication details

Journal / source
Harvard Dataverse
Publication date
11 January 2026
Document type
Dataset