Clever materials: when models identify good materials for the wrong reasons
Faraday Discussions · 2026 · 268 · 464-478
DOI: 10.1039/d6fd00024j ↗Kurz gefasst
Fachartikel in der Zeitschrift Faraday Discussions, 2026. Verfasst von Kevin Maik Jablonka. Beteiligte Einrichtung: Laboratory of Organic and Macromolecular Chemistry (IOMC), Friedrich Schiller University Jena, Humboldtstrasse 10, 07743 Jena, Germany. mail@kjablonk…. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 3.0). Gefördert von: Carl-Zeiss-Stiftung.
Abstract (Originalsprache)
Machine learning can accelerate materials discovery. Models perform well on benchmarks. However, strong performance does not imply learning of chemistry. The alternative hypothesis that prediction may be driven by bibliographic confounding is tested.
Autor:innen und Institutionen
- Laboratory of Organic and Macromolecular Chemistry (IOMC), Friedrich Schiller University Jena, Humboldtstrasse 10, 07743 Jena, Germany. mail@kjablonka.com.
- Helmholtz Institute for Polymers in Energy Applications Jena (HIPOLE Jena), Lessingstrasse 12-14, 07743 Jena, Germany.
- Center for Energy and Environmental Chemistry Jena (CEEC Jena), Friedrich Schiller University Jena, Philosophenweg 7a, 07743 Jena, Germany.
- Jena Center for Soft Matter (JCSM), Friedrich Schiller University Jena, Philosophenweg 7, 07743 Jena, Germany.
Förderung
- Carl-Zeiss-Stiftung
Zitieren
APA
Jablonka, K. M. (2026). Clever materials: when models identify good materials for the wrong reasons. Faraday Discussions, 268, 464-478. https://doi.org/10.1039/d6fd00024j
Vancouver
Jablonka KM. Clever materials: when models identify good materials for the wrong reasons. Faraday Discussions. 2026;268:464-478. doi:10.1039/d6fd00024j
BibTeX
@article{Jablonka2026,
author = {Jablonka, Kevin Maik},
title = {Clever materials: when models identify good materials for the wrong reasons},
journal = {Faraday Discussions},
year = {2026},
volume = {268},
pages = {464--478},
doi = {10.1039/d6fd00024j}
}
EUVIMED