Use of Large Language Models for Extracting and Analyzing Data from Heterogeneous Catalysis Literature

Distributed as part of the publication "Use of Large Language Models for Extracting and Analyzing Data from Heterogeneous Catalysis Literature" by Benjamin W. Walls and Suljo Linic. CatMiner.zip -- All code associated with our text mining tool CatMiner used to extract data from publications on the oxidative coupling of methane, including benchmarking tests, databases, and downstream analysis. This is an archived copy of our initial commit to the associated GitHub repository: https://github.com/benjww/CatMiner/tree/main text_mining_prep.zip -- All code used to download and preprocess publications on the oxidative coupling of methane. This is an archived copy of our initial commit to the associated GitHub repository: https://github.com/benjww/text_mining_prep full-ocm-database.csv -- The raw database of oxidative coupling of methane experimental data extracted from the literature as described in our publication. It is also provided in CatMiner.zip along with code used to generate it. full-ocm-database-normalized.csv -- The standardized, machine-readable version of the same database. It is also provided in CatMiner.zip along with code used to generate it.