Published October 23, 2023 | Version v2
Journal article Open

Language models and protocol standardization guidelines for accelerating synthesis planning in heterogeneous catalysis

Description

The repository is present in two versions. The V1 version contains excel files with data on the 127 paragraphs used for model training and a separate set of 145 paragraphs which were used for statistically analyze the synthetic routes in SAC literature. The DOIs for the respective papers are included in the excel sheets. The data on annotations performed on docanno platform are presented as JSON file.  The V2 version contains all the raw data to reproduces Figures 1, 4 and  5 from the manuscript and Supplementary Figure 2.

Files

Files (60.1 kB)

Name Size Download all
md5:c0beb1a5baa1c0abc72d886edbf50a59
13.8 kB Download
md5:bf67fbe591fe6f082f74a9f8c6c4aa6a
13.0 kB Download
md5:f15d906d27c307b2c27fb97d10b87275
16.0 kB Download
md5:81043481e93b0e97dde9e0b993b8b12c
17.2 kB Download

Additional details

Funding

NCCR Catalysis (phase I) 51NF40_180544
Swiss National Science Foundation