We employ distinct Bayesian Neural Network discriminant functions which
were optimized for one of three tagging categories: double SECVTX tag,
one SECVTX tag + one JetProb/NN tag, and one SECVTX tag.
<!--We use BNN with 7 inputs, 8 hidden nodes, and one output node. --><br>
For each BNN function, we use next input variables.
<ul><fontcolor="red">double SECVTX tag</font>
<li><fontcolor="blue"><b>Dijet invariant mass</b></font>: The invariant mass reconstructed from the two jets. For this variable, we apply NN b-jet energy correction. </li>
<li><fontcolor="blue"><b>PT Imbalance</b></font>: The scalar sum of the lepton and jet transverse momenta minus the MET. </li>
<li><fontcolor="blue"><b>M <sub>max</sub> (lep + ν + jet)</b></font>: The invariant mass of the lepton, MET and one of the two jets, where the jet is chosen to give the maximum invariant mass.</li>
<li><fontcolor="blue"><b>Q x η<sub>lep</sub></b></font>: The charge of the lepton times the η of the lepton.</li>
<li><fontcolor="blue"><b>Sum ET (loose jets)</b></font>: The scalar sum of the loose jet transverse energy. </li>
<li><fontcolor="blue"><b>P<sub>T</sub>(W)</b></font>: The transverse momentum of the reconstructed W.</li>
<li><fontcolor="blue"><b>H<sub>T</sub></b></font>: The scalar sum of the transverse energies of the jets, the lepton, and the MET.</li>
</ul>
<ul><fontcolor="red">one SECVTX tag + one JetProb/NN tag</font>
<li><fontcolor="blue"><b>Dijet invariant mass</b></font>: Same variable as double SECVTX input. </li>
<li><fontcolor="blue"><b>Sum ET (loose jets)</b></font>: Same variable as double SECVTX input.</li>
<li><fontcolor="blue"><b>Q x η<sub>lep</sub></b></font>: Same variable as double SECVTX input.</li>
<li><fontcolor="blue"><b>M <sub>min</sub> (lep + ν + jet)</b></font>: The invariant mass of the lepton, MET and one of the two jets, where the jet is chosen to give the minimum invariant mass.</li>
<li><fontcolor="blue"><b>H<sub>T</sub></b></font>: Same variable as double SECVTX input.</li>
<li><fontcolor="blue"><b>P<sub>T</sub>(W)</b></font>: Same variable as double SECVTX input.</li>