Intrinsic neural timescales shape memory encoding and retrieval

Historically, different memory processes like encoding and retrieval have been distinguished. However, recent models emphasize their continuum across the shorter and longer timescales of encoding and retrieval while, at the same time, both are featured by distinct cognitive demands. The exact neural mechanisms connecting and, at the same time, differentiating encoding and retrieval across their multiple timescales remain yet unclear, though. Using EEG, we here measure the brain's Intrinsic neural timescales (INT) by the autocorrelation window (ACW) during encoding and retrieval of memory. Our main findings are: (i) direct behavioral connection of encoding (spatial fit judgment of the pictures) with those of retrieval (precision, false alarms, accuracy); (ii) a clear state-dependent neural differentiation, with longer ACW during encoding (temporal integration) and shorter ACW during retrieval (temporal segregation), a distinction not observed for another dynamic measure, the power-law exponent (PLE); (iii) high trait-like stability of ACW, with an individual's ACW remaining strongly correlated across rest, encoding, and retrieval states; and (iv) this stable, trait-like ACW (but not its state-dependent modulation) robustly predicts memory performance, with longer trait ACW correlating with higher accuracy and precision and fewer false alarms. Together, we demonstrate that the brain's INT both connect and differentiate encoding and retrieval on both neural and behavioral grounds. This supports and extends current dynamic, e.g., temporal, models of memory by showing the key relevance of the brain's INT (as measured by the ACW) in shaping encoding and retrieval.