JACOW : Towards Unlocking Insights from Logbooks Using AI

Sulc, Antonin; Rehm, Florian; Tuennermann, Henrik; St. John, Jason; Wilksen, Tim; Mayet, Frank; Maldonado, Jennefer; Hazelwood, K.J.; Bien, Alex; Kain, Verena; Kaiser, Jan; Hartmann, Gregor; Hoschouer, Hayden; Eichler, Annika; Hellert, Thorsten; Ratner, Daniel; Hu, Wan-Lin; Kammering, Raimund

doi:10.18429/JACoW-IPAC2024-THPR37

Article
Report number	arXiv:2406.12881 ; FERMILAB-CONF-24-0237-AD
Title	Towards Unlocking Insights from Logbooks Using AI
Author(s)	Sulc, Antonin (Helmholtz-Zentrum, Berlin) ; Bien, Alex (SLAC) ; Eichler, Annika (DESY) ; Ratner, Daniel (SLAC) ; Rehm, Florian (CERN) ; Mayet, Frank (DESY) ; Hartmann, Gregor (Helmholtz-Zentrum, Berlin) ; Hoschouer, Hayden (Fermilab) ; Tuennermann, Henrik (DESY) ; Kaiser, Jan (DESY) ; St. John, Jason (Fermilab) ; Maldonado, Jennefer (Brookhaven) ; Hazelwood, K.J. (Fermilab) ; Kammering, Raimund (DESY) ; Hellert, Thorsten (LBL, Berkeley) ; Wilksen, Tim (DESY) ; Kain, Verena (CERN) ; Hu, Wan-Lin (SLAC)
Publication	2024-07-01
Imprint	2024-05-25
Number of pages	4
In:	JACoW IPAC 2024 (2024) pp.THPR37
In:	15th International Particle Accelerator Conference (IPAC 2024), Nashville, TN, United States, 19 - 24 May 2024, pp.THPR37
DOI	10.18429/JACoW-IPAC2024-THPR37
Subject category	cs.CL ; Computing and Computers ; physics.acc-ph ; Accelerators and Storage Rings
Abstract	Electronic logbooks contain valuable information about activities and events concerning their associated particle accelerator facilities. However, the highly technical nature of logbook entries can hinder their usability and automation. As natural language processing (NLP) continues advancing, it offers opportunities to address various challenges that logbooks present. This work explores jointly testing a tailored Retrieval Augmented Generation (RAG) model for enhancing the usability of particle accelerator logbooks at institutes like DESY, BESSY, Fermilab, BNL, SLAC, LBNL, and CERN. The RAG model uses a corpus built on logbook contributions and aims to unlock insights from these logbooks by leveraging retrieval over facility datasets, including discussion about potential multimodal sources. Our goals are to increase the FAIR-ness (findability, accessibility, interoperability, and reusability) of logbooks by exploiting their information content to streamline everyday use, enable macro-analysis for root cause analysis, and facilitate problem-solving automation.
Copyright/License	publication: (License: CC-BY-4.0) preprint: (License: CC BY 4.0)