just came across this critique of that paper on Twitter: https://twitter.com/Robert_Palgrave/status/1730358675523424344 Robert Palgrave (@Robert_Palgrave) on X twitter.com
https://twitter.com/Robert_Palgrave/status/1730358675523424344but I'm not enough of an expert to judge - perhaps some characterizations were wrong and a lot of the paper does stand. > On 1 Dec 2023, at 20:51, Bryan Lepore <[email protected]> wrote: > > Adding to that literature list a bit outside : > > Merchant, A., Batzner, S., Schoenholz, S.S. et al. > > Quote: > > "... we show that graph networks trained at scale can reach unprecedented > levels of generalization, improving the efficiency of materials discovery by > an order of magnitude. " > > Scaling deep learning for materials discovery. > > Nature (2023), November > > https://doi.org/10.1038/s41586-023-06735-9 > > > To unsubscribe from the CCP4BB list, click the following link: > https://www.jiscmail.ac.uk/cgi-bin/WA-JISC.exe?SUBED1=CCP4BB&A=1 > ######################################################################## To unsubscribe from the CCP4BB list, click the following link: https://www.jiscmail.ac.uk/cgi-bin/WA-JISC.exe?SUBED1=CCP4BB&A=1 This message was issued to members of www.jiscmail.ac.uk/CCP4BB, a mailing list hosted by www.jiscmail.ac.uk, terms & conditions are available at https://www.jiscmail.ac.uk/policyandsecurity/
