Table 1. Performance metrics of the ECG encoder methods.

task	n training labels	Ribeiro-R	CAE	CLOCS	PCLR
LVH (f1 score)	640	0.14 ± 0.02	0.25 ± 0.02	0.19 ± 0.02	0.36 ± 0.02
	1280	0.19 ± 0.02	0.37 ± 0.02	0.18 ± 0.02	0.43 ± 0.02
	2560	0.27 ± 0.03	0.33 ± 0.02	0.19 ± 0.02	0.44 ± 0.02
	5120	0.28 ± 0.02	0.41 ± 0.03	0.20 ± 0.02	0.47 ± 0.02
	10240	0.33 ± 0.03	0.43 ± 0.03	0.23 ± 0.02	0.46 ± 0.03
	20480	0.29 ± 0.03	0.49 ± 0.03	0.27 ± 0.03	0.47 ± 0.03
age (r2)	640	0.33 ± 0.01	0.24 ± 0.01	0.41 ± 0.01	0.56 ± 0.01
	1280	0.36 ± 0.01	0.29 ± 0.01	0.43 ± 0.01	0.57 ± 0.01
	2560	0.38 ± 0.01	0.32 ± 0.01	0.47 ± 0.01	0.58 ± 0.01
	5120	0.40 ± 0.01	0.34 ± 0.01	0.49 ± 0.01	0.59 ± 0.01
	10240	0.41 ± 0.01	0.35 ± 0.01	0.50 ± 0.01	0.60 ± 0.01
	20480	0.42 ± 0.01	0.36 ± 0.01	0.51 ± 0.01	0.60 ± 0.01
sex (f1 score)	640	0.72 ± 0.00	0.77 ± 0.00	0.77 ± 0.00	0.84 ± 0.00
	1280	0.74 ± 0.00	0.78 ± 0.00	0.78 ± 0.00	0.86 ± 0.00
	2560	0.75 ± 0.00	0.79 ± 0.00	0.78 ± 0.00	0.87 ± 0.00
	5120	0.76 ± 0.00	0.80 ± 0.00	0.78 ± 0.00	0.86 ± 0.00
	10240	0.77 ± 0.00	0.80 ± 0.00	0.79 ± 0.00	0.87 ± 0.00
	20480	0.77 ± 0.00	0.80 ± 0.00	0.80 ± 0.00	0.87 ± 0.00
AF (f1 score)	640	n/a	0.20 ± 0.02	0.68 ± 0.02	0.60 ± 0.02
	1280	n/a	0.23 ± 0.02	0.76 ± 0.01	0.61 ± 0.02
	2560	n/a	0.24 ± 0.02	0.78 ± 0.01	0.64 ± 0.02
	5120	n/a	0.28 ± 0.02	0.79 ± 0.01	0.65 ± 0.02
	10240	n/a	0.26 ± 0.02	0.79 ± 0.01	0.69 ± 0.02
	20480	n/a	0.24 ± 0.02	0.80 ± 0.01	0.70 ± 0.02

Bold results indicate the best model with a fixed task and number of training labels. The best models are picked using 1,000 bootstraps of the test data. The performance ranges are ± one standard deviation of the bootstrapped performances.