Table 1.

Per-regime quality metrics obtained through a leave-one-out cross-validation evaluation scheme for all available signals

	Ternary			Binary
Metric	Conduction [%]	Stable keyhole [%]	Unstable keyhole [%]	Conduction [%]	Keyhole [%]
Global F1-score	97.04	69.90	89.83	95.89	98.34
Global Precision	97.39	58.32	96.81	95.44	98.53
Global Recall	96.70	87.21	83.79	96.36	98.15

The metrics shown include F1-score, precision, and recall. The F1-score, also known as the harmonic mean of precision and recall, balances the trade-off between the two and provides a comprehensive measure of overall performance. Precision, on the other hand, measures the proportion of true positive predictions among all positive predictions, while recall measures the proportion of true positive predictions among all actual positive instances. In addition to the per-regime metrics, the table also includes the global figures, calculated by concatenating all the obtained predictions and evaluating them against the concatenated ground truths. These global figures provide a comprehensive overview of the overall performance of the model across all regimes.