Consequences of predictable temporal structure in multi-task situations

Abstract

In everyday life, we often anticipate the timing of an upcoming task or event while actively engaging in another. Here, we investigated the effects of predictable temporal structure within such a multi-task scenario. In a visual working-memory task, we manipulated whether the onset of a working-memory probe could be predicted in time, while also embedding a simple intervening task within the delay period. We first show that working-memory performance benefitted from temporal expectations, even though an intervening task had to be completed in the interim. Moreover, temporal predictions regarding the upcoming working-memory probe additionally affected performance on the intervening task, resulting in faster responses when the memory probe was expected early, and slower responses when the memory probe was expected late, as compared to when it was temporally unpredictable. Because the intervening task always occurred at the same time during the memory delay, differences in performance on this intervening task result from a between-task consequence of temporal expectation. Thus, we show that within multi-task settings, knowing when working-memory contents will be required for an upcoming task not only facilitates performance of the associated working-memory task, but can also influence the performance of other, intervening tasks.

Keywords: Attention; Intervening task; Temporal expectation; Working memory.

Fig. 1

Task schematic and effects of temporal prediction on reaction times. (A) Two lateralised oriented bars were presented for 250 ms. For the working-memory task, participants had to remember the angle of both bars, of which one had to be reported at the end of the trial. Following a delay of 1000 ms, an intervening task occurred wherein another tilted bar was presented centrally for 250 ms. For this intervening task, participants had to indicate as quickly as possible whether this bar was tilted to the left or to the right. In “Early Blocks”, the intervening item offset was followed by a delay of 1250 ms, whereas in “Late Blocks”, it was followed by a delay of 2500 ms. In “Variable Blocks”, the delay between the intervening-item offset and the memory-probe onset was either 1250 ms or 2500 ms equally often. After this delay, a colour change of the central fixation cross indicated which of the two bars from the encoding display would have to be reproduced from memory. (B) Intervening task performance. Top panel: Reaction times (RTs) in the intervening task significantly increased from fixed-early to variable and from variable to fixed-late blocks. Bottom panel: Between-task effects of temporal expectation in fixed-early and fixed-late blocks, relative to variable blocks. (C) Working-memory task performance. Top panel: RTs to early probes were faster when the probe could be temporally predicted as compared to when it was temporally unpredictable. Bottom panel: Temporal expectations reduced RTs in the early condition. Violin plots for each delay condition were calculated by taking the difference in RTs between fixed variable blocks (Fixed - Variable). Dots represent individual participants. Error bars indicate ±1 standard error of the mean.

Fig. 2

Effects of temporal prediction on reproduction errors. (A) Intervening task. Top panel: Error rates did not differ significantly between conditions. Bottom panel: Temporal expectations did not influence error rates. (B) Working-memory task. Top panel: Reproduction errors were significantly higher in variable versus fixed blocks. Bottom panel: Temporal expectations decreased error rates for both delays. Violin plots for each delay were calculated by taking the difference in error rates between fixed blocks and variable blocks (Fixed - Variable). Dots represent individual participants. Error bars indicate ±1 standard error of the mean.

Fig. 3

Sequential effects of temporal intervals on intervening-task performance (A) Left panel: Reaction times (RTs) in variable blocks of the intervening task were significantly faster when the immediately preceding working-memory probe occurred early versus late. Right panel: Violin plots showing the difference in RTs between trials of which the working-memory delay of the preceding trial was early versus late (Previous-early – Previous-late) (B) Left panel: Error rates in variable blocks did not differ significantly depending on the working-memory delay interval of the previous trial. Right panel: As in the right panel in Fig. 3A, with the difference in errors rates instead of RTs. Dots represent individual participants. Error bars indicate ±1 standard error of the mean.