amc: The Automated Mission Classifier for Telescope Bibliographies

TL;DR

The paper introduces amc, an AI tool using large language models to automatically classify telescope-related literature, improving scalability and accuracy in bibliographies for assessing scientific impact.

Contribution

We developed amc, a novel LLM-based classifier that automates telescope literature categorization, outperforming previous manual methods and enabling scalable bibliographic analysis.

Findings

amc achieved a macro F1 score of 0.84 on the TRACS Kaggle challenge

amc effectively identifies papers featuring scientific results from NASA missions

the tool can detect label errors and analyze historical datasets

Abstract

Telescope bibliographies record the pulse of astronomy research by capturing publication statistics and citation metrics for telescope facilities. Robust and scalable bibliographies ensure that we can measure the scientific impact of our facilities and archives. However, the growing rate of publications threatens to outpace our ability to manually label astronomical literature. We therefore present the Automated Mission Classifier (amc), a tool that uses large language models (LLMs) to identify and categorize telescope references by processing large quantities of paper text. A modified version of amc performs well on the TRACS Kaggle challenge, achieving a macro $F_1$ score of 0.84 on the held-out test set. amc is valuable for other telescopes beyond TRACS; we developed the initial software for identifying papers that featured scientific results by NASA missions. Additionally, we investigate how amc can also be used to interrogate historical datasets and surface potential label errors. Our work demonstrates that LLM-based applications offer powerful and scalable assistance for library sciences.