| Mean | Maximum |
---|
 |
Positive
|
Negative
|
Positive
|
Negative
|
SAINT
| 32 *** | 32 * * * | 32 * * * | 25 ** |
Reverse SAINT | 2 | 2 | 2 | 9 |
SAINT
| 11 | 5 | 19 | 16 |
Rosetta | 23 * | 29 * * * | 15 | 14 |
- The table shows the number of times an algorithm in a pair outperformed the other, separately for the positive and negative sets. Both mean GDT_TS and maximum GDT_TS are used as measures of performance. Asterisks indicate binomial test p-values where * is < 0.05, ** is < 0.01, *** is < 0.001.