Table 4.

F1-scores, precision, and recall from leave-one-sample-out cross-validation and p-values from a randomization test.

Rating	Classification from auton. param.				Classification from obj. perform.
	F1-score	p	prec.	recall	F1-score	p	prec.	recall
Own performance (R1, collab.)	0.32	0	0.43	0.26	0.19	0.048	0.18	0.19
Partner performance (R2)	0.37	0	0.47	0.3	0.14	0.866	0.11	0.18
Collaboration (R3)	0.37	0	0.46	0.31	0.14	0.905	0.11	0.18
Own performance (R1, indiv.)	0.23	0	0.23	0.23	0.16	0.461	0.14	0.2