Towards Unlocking Insights from Logbooks Using AI
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910494135156736 |
|---|---|
| author | Sulc, Antonin Bien, Alex Eichler, Annika Ratner, Daniel Rehm, Florian Mayet, Frank Hartmann, Gregor Hoschouer, Hayden Tuennermann, Henrik Kaiser, Jan John, Jason St. Maldonado, Jennefer Hazelwood, Kyle Kammering, Raimund Hellert, Thorsten Wilksen, Tim Kain, Verena Hu, Wan-Lin |
| author_facet | Sulc, Antonin Bien, Alex Eichler, Annika Ratner, Daniel Rehm, Florian Mayet, Frank Hartmann, Gregor Hoschouer, Hayden Tuennermann, Henrik Kaiser, Jan John, Jason St. Maldonado, Jennefer Hazelwood, Kyle Kammering, Raimund Hellert, Thorsten Wilksen, Tim Kain, Verena Hu, Wan-Lin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_12881 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Unlocking Insights from Logbooks Using AI Sulc, Antonin Bien, Alex Eichler, Annika Ratner, Daniel Rehm, Florian Mayet, Frank Hartmann, Gregor Hoschouer, Hayden Tuennermann, Henrik Kaiser, Jan John, Jason St. Maldonado, Jennefer Hazelwood, Kyle Kammering, Raimund Hellert, Thorsten Wilksen, Tim Kain, Verena Hu, Wan-Lin Accelerator Physics Computation and Language 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. |
| title | Towards Unlocking Insights from Logbooks Using AI |
| topic | Accelerator Physics Computation and Language |
| url | https://arxiv.org/abs/2406.12881 |