Text-mined dataset of solid-state syntheses with impurity phases using Large Language Model
Sanghoon Lee, Kevin Cruse, Viktoriia Baibakova, Gerbrand Ceder, Anubhav Jain · 2025
Read Text-mined dataset of solid-state syntheses with impurity phases using Large Language Model by Sanghoon Lee, Kevin Cruse, Viktoriia Baibakova, Gerbrand Ceder, Anubhav Jain (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12717135.txt.
Description
Sanghoon Lee, Kevin Cruse, Viktoriia Baibakova, Gerbrand Ceder, and Anubhav Jain mine past papers for synthesis recipes in a 2025 study. Solid-state synthesis makes many inorganic materials, from batteries to thermoelectrics. The method lacks a general theory, so past records are a key guide. Prior mined sets often ignored whether extra impurity phases formed.
Using a large language model, the team extracts over eighty thousand syntheses from the literature. Nearly nineteen thousand list impurity phases. The set confirms expected heat based patterns for when impurities form. It also flags odd cases where impurities appear even when the target is far more stable.
Catalog record
| CREATOR | Sanghoon Lee, Kevin Cruse, Viktoriia Baibakova, Gerbrand Ceder, Anubhav Jain |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 32 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |