Table 6 Mean absolute deviation between ground truth and predicted template cardinality. Each cell shows mean and standard deviation of 10 training runs with the best found hyperparameters for best (w.r.t. validation \(F_1\) score) configurations of each category. Numbers rounded to two decimal places, best values marked bold

Arm

0.01 (± 0.02)

1.09 (± 0.03)

0.02 (± 0.04)

1.33 (± 0.05)

DiffBetweenGroups

1.01 (± 0.96)

0.69 (± 0.08)

0.39 (± 0.36)

0.17 (± 0.13)

Endpoint

5.32 (± 1.11)

3.83 (± 0.03)

2.91 (± 1.09)

0.35 (± 0.22)

Intervention

0.1 (± 0.04)

1.22 (± 0.03)

0.19 (± 0.05)

0.8 (± 0.1)

Medication

0.21 (± 0.07)

0.18 (± 0.1)

0.11 (± 0.08)

0.47 (± 0.2)

Outcome

1.08 (± 0.82)

8.36 (± 0.07)

0.94 (± 0.57)

2.98 (± 0.04)