The missing data for intelligent scientific instruments
(2025) In Nature Methods- Abstract
Most scientific instruments currently discard rich streams of commands, data and metadata from which AI systems could learn to conduct experiments with expert-level decision-making and troubleshooting skills. Recording and using this data at scale requires rethinking what data to store, incentivizing large-scale cooperation, and determining how to quantify the reliability of such autonomous systems.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/7d3bf5ee-284f-4972-8b4b-8859ac9ca0db
- author
- Pinkard, Henry LU and Norlin, Nils LU
- organization
- publishing date
- 2025
- type
- Contribution to journal
- publication status
- epub
- subject
- in
- Nature Methods
- pages
- 4 pages
- publisher
- Nature Publishing Group
- external identifiers
-
- scopus:105026411684
- ISSN
- 1548-7091
- DOI
- 10.1038/s41592-025-02995-7
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © Springer Nature America, Inc. 2025.
- id
- 7d3bf5ee-284f-4972-8b4b-8859ac9ca0db
- date added to LUP
- 2026-01-09 17:20:13
- date last changed
- 2026-01-13 11:47:06
@misc{7d3bf5ee-284f-4972-8b4b-8859ac9ca0db,
abstract = {{<p>Most scientific instruments currently discard rich streams of commands, data and metadata from which AI systems could learn to conduct experiments with expert-level decision-making and troubleshooting skills. Recording and using this data at scale requires rethinking what data to store, incentivizing large-scale cooperation, and determining how to quantify the reliability of such autonomous systems.</p>}},
author = {{Pinkard, Henry and Norlin, Nils}},
issn = {{1548-7091}},
language = {{eng}},
publisher = {{Nature Publishing Group}},
series = {{Nature Methods}},
title = {{The missing data for intelligent scientific instruments}},
url = {{http://dx.doi.org/10.1038/s41592-025-02995-7}},
doi = {{10.1038/s41592-025-02995-7}},
year = {{2025}},
}