Looking Under the Streetlight: Evaluation in Generative Molecular Dynamics
Abstract
This position paper argues that the generative molecular dynamics (GenMD) community is not properly evaluating its progress: current evaluations let a model match what is reported while being arbitrarily wrong on what was claimed, which risks over-claiming advantage over classical baselines. This reflects a structural misalignment between common evaluation practices and the scientific tasks the field sets for itself. The reason is that the ground truth---exhaustive molecular dynamics on the systems of interest---is computationally costly, and this cost is what motivates the field. With ground truth inaccessible, evaluation drifts toward convenient proxies, and the resulting norms entrench easily. We identify misaligned evaluation patterns that persist as a community-level equilibrium, and propose concrete observables, reporting standards, and benchmark designs, both computational and experimental, that better reflect what GenMD aspires to deliver. Our aim is to give the field shared language and tools for evaluation that match its scientific ambitions before today's conventions calcify into norms.
Related
- SupraTITO: Transferable Generative Molecular Dynamics for Supramolecular Systems
- Computational Evaluation of Carbazole–Chalcone Urea and Thiourea Derivatives Against EGFR: Molecular Docking, Pharmacokinetic Profiling, Target Prediction, and Molecular Dynamics Simulation
- Design and computational evaluation of reversible covalent cathepsin S inhibitors using molecular docking, ADMET, molecular dynamics, MM/PBSA, and density functional theory
- Molecular Docking and Molecular Dynamics Studies: Evaluation of the Potential Interaction between Ciprofloxacin-DAB-PAMAM Dendrimer-Based Prodrug Prototypes and Human Carboxylesterase 1
- Comparative Anti-Inflammatory Evaluation of Lamiaceae Essential Oils and Mechanistic Insights into Mentha haplocalyx Essential Oil via Network Pharmacology and Molecular Dynamics
BibTeX
@misc{olsson2026looking,
title = {{Looking Under the Streetlight: Evaluation in Generative Molecular Dynamics}},
author = {Simon Olsson and Frank Noé and Grant M. Rotskoff and Kresten Lindorff-Larsen},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.12518},
eprint = {2610.12518},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.12518},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Looking Under the Streetlight: Evaluation in Generative Molecular Dynamics
AU - Simon Olsson
AU - Frank Noé
AU - Grant M. Rotskoff
AU - Kresten Lindorff-Larsen
PY - 2026
DA - 2026/10/07
PB - arXiv
DO - 10.48550/arxiv.2610.12518
UR - https://arxiv.org/abs/2610.12518
AB - This position paper argues that the generative molecular dynamics (GenMD) community is not properly evaluating its progress: current evaluations let a model match what is reported while being arbitrarily wrong on what was claimed, which risks over-claiming advantage over classical baselines. This reflects a structural misalignment between common evaluation practices and the scientific tasks the field sets for itself. The reason is that the ground truth---exhaustive molecular dynamics on the systems of interest---is computationally costly, and this cost is what motivates the field. With ground truth inaccessible, evaluation drifts toward convenient proxies, and the resulting norms entrench easily. We identify misaligned evaluation patterns that persist as a community-level equilibrium, and propose concrete observables, reporting standards, and benchmark designs, both computational and experimental, that better reflect what GenMD aspires to deliver. Our aim is to give the field shared language and tools for evaluation that match its scientific ambitions before today's conventions calcify into norms.
ER -