Significance Test on Instance-Level F-measure, Precision, and Recall
| Szarvas 2 | Szarvas 1 | Wellner 3 | Wellner 1 | Aramaki 1 | Wellner 2 | Hara 3 | Wrenn 3 | Hara 2 | Hara 1 | Wrenn 2 | Wrenn 1 | Guo 1 | Guo 2 | |
| Szarvas 3 | F, P, R | R | F, R | |||||||||||
| Szarvas 2 | — | F, R | F, R | |||||||||||
| Szarvas 1 | — | — | F, R | P | ||||||||||
| Wellner 3 | — | — | — | P | ||||||||||
| Wellner 1 | — | — | — | — | ||||||||||
| Aramaki 1 | — | — | — | — | — | |||||||||
| Wellner 2 | — | — | — | — | — | — | F, P, R | F | P | P | ||||
| Hara 3 | — | — | — | — | — | — | — | F | P | P | ||||
| Wrenn 3 | — | — | — | — | — | — | — | — | P | |||||
| Hara 2 | — | — | — | — | — | — | — | — | — | P | ||||
| Hara 1 | — | — | — | — | — | — | — | — | — | — | ||||
| Wrenn 2 | — | — | — | — | — | — | — | — | — | — | — | R | ||
| Wrenn 1 | — | — | — | — | — | — | — | — | — | — | — | — | F | |
| Guo 1 | — | — | — | — | — | — | — | — | — | — | — | — | — |









