A Search for "New Physics'' "Beyond the Standard Model'' in Open Data with Machine Learning

Abstract

In this new era of large data, it is important to make sure we do not miss any signs of new physics. Using the publicly-available open data collected by the arXiv.org experiment in the \texttt{hep-ph} channel, corresponding to a raw total integrated $\mathcal{L}$iterature of 65,276 papers, we perform a search for ``New Physics'' and related signals. In the worst-case, we are able to detect ``New Physics'' with ``the LHC'' at a significance level of at least $6.5\ddot{I}ƒ$. This ``New Physics'' signature is primarily ``Dark'' in nature, and is potentially axion(-like) dark matter. We also show the potential for further improvement in the future, and that ``New Physics'' can be found with ``a Future Collider'' at at least $8.9\ddot{I}ƒ$, as well as the potential to find ``New Physics'' without any collider at all. This search is performed using code that was $80\%$ written by Machine Learning methods.

11 pages, 5 figures, code available at https://github.com/rikab/QuoteNewPhysics