The study aims to decode specific cognitive states from brain activity using a novel whole-brain functional connectivity analysis. The researchers defined 90 functional regions of interest (ROIs) across 14 large-scale resting-state brain networks to generate a 3960-cell matrix reflecting whole-brain connectivity. They trained a classifier to identify specific patterns of whole-brain connectivity during four subject-driven cognitive states: undirected rest, retrieval of recent episodic memories, serial subtractions, and silent singing of music lyrics. The classifier achieved 84% accuracy in leave-one-out cross-validation and 85% accuracy in an independent cohort. Classification accuracy remained high with imaging runs as short as 30-60 seconds. The 90 functionally defined ROIs outperformed 112 commonly used structural ROIs in classifying cognitive states. This approach enables the decoding of various subject-driven cognitive states from brief imaging data samples.The study aims to decode specific cognitive states from brain activity using a novel whole-brain functional connectivity analysis. The researchers defined 90 functional regions of interest (ROIs) across 14 large-scale resting-state brain networks to generate a 3960-cell matrix reflecting whole-brain connectivity. They trained a classifier to identify specific patterns of whole-brain connectivity during four subject-driven cognitive states: undirected rest, retrieval of recent episodic memories, serial subtractions, and silent singing of music lyrics. The classifier achieved 84% accuracy in leave-one-out cross-validation and 85% accuracy in an independent cohort. Classification accuracy remained high with imaging runs as short as 30-60 seconds. The 90 functionally defined ROIs outperformed 112 commonly used structural ROIs in classifying cognitive states. This approach enables the decoding of various subject-driven cognitive states from brief imaging data samples.