In these proceedings, a measurement of the differential cross section of top quark-antiquark pair ($\text{t}\overline{\text{t}}$) production in association with one additional jet ($\text{t}\overline{\text{t}}$+jet) as a function of the inverse of the invariant mass of the $\text{t}\overline{\text{t}}$+jet system, $\rho=340\,\text{GeV}/m_{\text{t}\overline{\text{t}}+\text{jet}}$, is presented. The normalized $\text{t}\overline{\text{t}}$+jet cross section is used to extract values for the top quark pole mass $m_{\text{t}}^{\text{pole}}$ by a comparison to theoretical predictions at next-to-leading order accuracy. The used data set corresponds to an integrated luminosity of 36.3fb$^{-1}$ of proton--proton collisions as collected by the CMS experiment at $\sqrt{s}=$ 13 TeV. Events with two opposite-sign leptons are analyzed. Machine learning techniques are employed to improve the kinematic reconstruction of the main observable and the event classification. The unfolding to the parton level is performed using a profiled likelihood fit. Given the ABMP16 parton distribution functions as a reference set, a value of $m_{\text{t}}^{\text{pole}}=172.94\pm1.37\,\text{GeV}$ is extracted using the normalized $\text{t}\overline{\text{t}}$+jet cross section.