A multi-dimensional search for new heavy resonances decaying to boosted W W , W Z , or Z Z boson pairs in the dijet final state at 13 Te

Abstract

A search in an all-jet final state for new massive resonances decaying to $\text{W}$ $\text{W}$ , $\text{W}$ $\text{Z}$ , or $\text{Z}$ $\text{Z}$ boson pairs using a novel analysis method is presented. The analysis is performed on data corresponding to an integrated luminosity of 77.3 ${\text{fb}}^{-1}$ recorded with the CMS experiment at the LHC at a centre-of-mass energy of 13 $\text{Te}$ . The search is focussed on potential narrow-width resonances with masses above 1.2 $\text{Te}$ , where the decay products of each $\text{W}$ or $\text{Z}$ boson are expected to be collimated into a single, large-radius jet. The signal is extracted using a three-dimensional maximum likelihood fit of the two jet masses and the dijet invariant mass, yielding an improvement in sensitivity of up to 30% relative to previous search methods. No excess is observed above the estimated standard model background. In a heavy vector triplet model, spin-1 ${\text{Z}}^{\text{'}}$ and ${\text{W}}^{\text{'}}$ resonances with masses below 3.5 and 3.8 $\text{Te}$ , respectively, are excluded at 95% confidence level. In a bulk graviton model, upper limits on cross sections are set between 27 and 0.2 $\text{fb}$ for resonance masses between 1.2 and 5.2 $\text{Te}$ , respectively. The limits presented in this paper are the best to date in the dijet final state.

Keywords: CMS; Diboson resonances; Physics; Substructure.

Fig. 1

The ${\tau }_{21}$ (upper) and ${\tau }_{21}^{\mathrm{DDT}}$ (lower) profile dependencies on ${\rho }^{\prime }=ln(m_{\mathrm{jet}}^2/(p_{\mathrm{T}}\mu ))$ examined in QCD multijet events simulated with pythia . A fit to the linear part of the spectrum for $p_{\mathrm{T}}>200\text{Ge}$ yields the slope $M=-0.080$, which is used to define the mass- and $p_{\mathrm{T}}$-decorrelated variable ${\tau }_{21}^{\mathrm{DDT}}={\tau }_{21}-M{\rho }^{\prime }$

Fig. 2

Distribution of the N-subjettiness discriminants (${\tau }_{21}$ and ${\tau }_{21}^{\mathrm{DDT}}$) for $\text{W}$-jets and quark/gluon jets from QCD multijet events (upper). Distributions in the jet mass of QCD multijet events for four $m_{\mathrm{jj}}$ bins in the range 1126–5500$\text{Ge}$ after a cut on ${\tau }_{21}$ and ${\tau }_{21}^{\mathrm{DDT}}$ corresponding to the same mistag rate of about 2% (lower). For both discriminants, darker colours correspond to higher $m_{\mathrm{jj}}$ ranges. The distributions are arbitrarily scaled for better readability. The analysis selections applied to derive these distributions are specified in the plots. For this analysis the working point of ${\tau }_{21}^{\mathrm{DDT}}\le 0.43$ is chosen

Fig. 3

The trigger efficiency as a function of the dijet invariant mass for a combination of all triggers used in this analysis (upper) and the event efficiency for either of the selected jets to pass triggers requiring an online trimmed mass of at least 30$\text{Ge}$ as a function of the jet mass (lower). The solid yellow circles correspond to the trigger efficiencies for the full 2017 data set and do not reach 100% efficiency because the jet mass based triggers were unavailable for a period at the beginning of data taking (corresponding to 4.8${\text{fb}}^{-1}$). The open yellow circles are the corresponding efficiencies excluding this period. The uncertainties shown are statistical only

Fig. 4

Jet mass (upper left) and ${\tau }_{21}^{\mathrm{DDT}}$ (upper right) distributions for selected jets (one random jet per event), and dijet invariant mass distribution (lower), for events with a jet mass between 55 and 215$\text{Ge}$. For the QCD multijet simulation, several alternative predictions are shown, scaled to the data minus the other background processes, which are scaled to their SM expectation as described in the text. The different signal distributions are scaled to be visible. No selection on ${\tau }_{21}^{\mathrm{DDT}}$ is applied. The ratio plots show the fraction of data over QCD multijet simulation for pythia 8 (black markers), herwig ++ (dotted line), and MadGraph +pythia 8 (dashed line)

Fig. 5

The jet mass distribution for events that pass (left) and fail (right) the ${\tau }_{21}^{\mathrm{DDT}}\le 0.43$ selection in the $\text{t}\overline{\text{t}}$ control sample. The results of the separate fits to data and to simulation are shown by the dash-dotted blue and solid red lines, respectively. The background components of the fits are shown as dashed and dash-dotted lines. The fit to 2016 data is shown in the upper panels and the fit to 2017 data in the lower panels. The associated uncertainties are shown in Table 1 and discussed further in Sect. 4.4

Fig. 6

Total signal efficiency as a function of $m_{\mathrm{X}}$ after all selections are applied, for signal models with a ${\text{Z}}^{\prime }$ decaying to $\text{W}$ $\text{W}$ , $\text{G}{}_{\mathrm{bulk}}$ decaying to $\text{W}$ $\text{W}$ , ${\text{W}}^{\prime }$ decaying to $\text{W}$ $\text{Z}$ , and $\text{G}{}_{\mathrm{bulk}}$ decaying to $\text{Z}$ $\text{Z}$ . The denominator is the number of generated events. The solid and dashed lines show the signal efficiencies for the HPHP and HPLP categories, respectively. The decrease in efficiency between 5.0 and 5.5 $\text{Te}$ is due to the requirement $m_{\mathrm{jj}}<5500\text{Ge}$

Fig. 7

The final $m_{\mathrm{jj}}$ (upper) and $m_{\mathrm{jet}1}$ (lower) signal shapes extracted from the parameterization of the dCB function. The same $m_{\mathrm{jj}}$ shapes are used for both purity categories. The jet mass distributions are shown for a range of resonance masses between 1.2 and 5.2 $\text{Te}$ for one of the two jets in the events in the HPHP category. Because the jets are labelled randomly, the jet mass distributions for the second jet are essentially the same as the one shown. The distributions for a $\text{G}{}_{\mathrm{bulk}}$ decaying to $\text{W}$ $\text{W}$ have the same shapes as those for the ${\text{Z}}^{\prime }$ signal and are therefore not visible

Fig. 8

The mass scale (upper) and resolution (lower) of the jet as a function of $m_{\mathrm{X}}$, obtained from the mean and width of the dCB function used to fit the jet mass spectrum. The HPHP (solid lines) and HPLP (dotted lines) categories are shown for different signal models. The distributions are only shown for one of the two jets in the event, since the distributions for the second jet are essentially the same

Fig. 9

Nominal QCD multijet simulation using pythia 8 (data points) and three-dimensional pdfs derived using a forward-folding kernel approach (black solid line), shown together with the five alternate shapes that are added to the multi-dimensional fit as shape nuisance parameters. The shapes for the high-purity (left) and low-purity (right) categories obtained with the 2017 simulation are shown for the projection on $m_{\mathrm{jet}1}$ (upper) and $m_{\mathrm{jj}}$ (lower). The projection on $m_{\mathrm{jet}2}$ is omitted since it is equivalent to the $m_{\mathrm{jet}1}$ projection except for statistical fluctuations. The pdfs and the simulations shown are normalized to unity. The normalization uncertainty of 50% is not shown. The distributions for 2016 simulations are similar

Fig. 10

For the HPHP category: comparison between the signal+background fit and the data distributions of $m_{\mathrm{jet}1}$ (upper left), $m_{\mathrm{jet}2}$ (upper right), and $m_{\mathrm{jj}}$ (lower). The background shape uncertainty is shown as a gray shaded band, and the statistical uncertainties of the data are shown as vertical bars. An example of a signal distribution is overlaid, where the number of expected events is scaled by a factor of 5. Shown below each mass plot is the corresponding pull distribution $(\text{Data-fit})/\sigma$, where $\sigma =\sqrt{{\sigma }_{\mathrm{data}}^2-{\sigma }_{\mathrm{fit}}^2}$ for each bin to ensure a Gaussian pull-distribution, as defined in Ref. [83]

Fig. 11

For the HPLP category: comparison between the signal+background fit and the data distributions of $m_{\mathrm{jet}1}$ (upper left), $m_{\mathrm{jet}2}$ (upper right), and $m_{\mathrm{jj}}$ (lower). The background shape uncertainty is shown as a gray shaded band, and the statistical uncertainties of the data are shown as vertical bars. An example of a signal distribution is overlaid, where the number of expected events is scaled by a factor of 5. Shown below each mass plot is the corresponding pull distribution $(\text{Data-fit})/\sigma$, where $\sigma =\sqrt{{\sigma }_{\mathrm{data}}^2-{\sigma }_{\mathrm{fit}}^2}$ for each bin to ensure a Gaussian pull-distribution, as defined in Ref. [83]

Fig. 12

Observed and expected 95% $\text{CL}$ upper limits on the product of the production cross section ($\sigma$) and the branching fraction, obtained after combining categories of all purities with 77.3${\text{fb}}^{-1}$ of 13 $\text{Te}$ data, for $\text{G}{}_{\mathrm{bulk}}\to \text{W}\text{W}$ (upper left), $\text{G}{}_{\mathrm{bulk}}\to \text{Z}\text{Z}$ (upper right), ${\text{W}}^{\prime }\to \text{W}\text{Z}$ (lower left), and ${\text{Z}}^{\prime }\to \text{W}\text{W}$ (lower right) signals. For each signal scenario the theoretical prediction (red line) and its uncertainty associated with the choice of PDF set (red hashed band) is shown. The theory cross sections (red line) are calculated at LO in QCD [6, 34]

Fig. 13

Expected 95% $\text{CL}$ upper limits on the product of the production cross section ($\sigma$) and the branching fraction for a $\text{G}{}_{\mathrm{bulk}}\to \text{W}\text{W}$ signal using 35.9${\text{fb}}^{-1}$ of data collected in 2016 obtained using the multi-dimensional fit method presented here (red solid line), compared to the result obtained with previous methods (black dash-dotted line) [29]. The final limit obtained when combining data collected in 2016 and 2017 is also shown (blue dashed line)