{"references": ["Ramakrishnan, R.; Dral, P. O.; Rupp, M. & Von Lilienfeld, O. A. Quantum chemistry structures and properties of 134 kilo moleculesSci. Data, 2014, 1, 140022. https://www.nature.com/articles/sdata201422", "Sch\u00fctt, K. T.; Arbabzadah, F.; Chmiela, S.; M\u00fcller, K. R. & Tkatchenko, A. Quantum-chemical insights from deep tensor neural networks Nat. Commun., 2017, 8, 13890. https://www.nature.com/articles/ncomms13890", "Sch\u00fctt, K.; Kindermans, P.-J.; Sauceda Felix, H. E.; Chmiela, S.; Tkatchenko, A. & M\u00fcller, K.-R. Guyon, I.; Luxburg, U. V.; Bengio, S.; Wallach, H.; Fergus, R.; Vishwanathan, S. & Garnett, R. (Eds.) SchNet: A continuous-filter convolutional neural network for modeling quantum interactions. Adv. Neural Inf. Process. Syst. 30, 2017, 991-1001. https://papers.nips.cc/paper/6700-schnet-a-continuous-filter-convolutional-neural-network-for-modeling-quantum-interactions"]}

Data curated by the QCArchive team, originally sourced from quantum-machine.org. Molecular dynamics trajectories of 129 isomers of C7H10O2, each containing 5,000 snapshots at a resolution of 1 fs. All molecules are neutral singlets. Calculations are performed at the PBE-TS level of theory. For more information, see http://qcarchive.molssi.org/apps/ml_datasets/.