Effects of a narrative template on memory for the time of movie scenes: automatic reshaping is independent of consolidation

Abstract

Memory for time is influenced by reconstructive processes, but the underlying mechanisms remain unclear. The present study investigated whether the effect of schematic prior knowledge on temporal memory for movie scenes, produced by the incomplete presentation (cut) of the movie at encoding, is modulated by cut position, retention interval, and task repetition. In a timeline positioning task, participants were asked to indicate when short video clips extracted from a previously encoded movie occurred on a horizontal timeline that represented the video duration. In line with previous findings, removing the final part of the movie resulted in a systematic underestimation of clips' position as a function of their proximity to the missing part. Further experiments demonstrate that the direction of this automatic effect depends on which part of the movie is deleted from the encoding session, consistent with the inferential structure of the schema, and does not depend on consolidation nor reconsolidation processes, at least within the present experimental conditions. We propose that the observed bias depends on the automatic influence of reconstructive processes on judgments about the time of occurrence, based on prior schematic knowledge.

Fig. 1

Results of Experiment 1. The figure illustrates the memory for time performance for video clips extracted from the first 60 min of the “Sherlock” episode, which was presented the day before. A Scatter plot showing the relationship between actual (x-axis) and estimated position (y-axis). Circles above or below the diagonal represent an over- and an under-estimation, respectively. Transparent circles indicate single-subject data while opaque circles indicate group data. White and black circles indicate a significant overestimation or underestimation effect, respectively (timewise one-sample t-test, corrected for multiple comparisons). B Relative error as a function of the video part (part duration: 10 min). The plot shows the group average (lighter square) and the quantiles of the distribution for each part: the bigger box represents the second quartile (Q1–Q3) while smaller boxes represent lower-order quantiles (octiles, hexadeciles, etc.)

Fig. 2

Results of Experiment 2. Memory for time performance for video clips extracted from the “Sherlock” episode, of which only the first and the last thirds were presented at encoding. A Scatter plot showing the relationship between actual and estimated position. White circles indicate a significant overestimation effect at the group level. B Relative error as a function of the video part in Experiment 1 (grey) and Experiment 2 (blue)

Fig. 3

Results of Experiment 3 (immediate recall). Memory for time performance for video clips extracted from the first 60 min of the “Sherlock” episode when the retrieval task was performed immediately after the encoding session. A Scatter plot showing the relationship between actual and estimated position. White and black circles indicate a significant overestimation or underestimation effect respectively. B Relative error as a function of the video part in Experiment 1 (grey) and Experiment 3, Immediate Recall (red)

Fig. 4

Results of Experiment 3 (delayed recall). Memory for time performance for video clips extracted from the first 60 min of the “Sherlock” episode when the retrieval task was performed a second time the next day. A Scatter plot showing the relationship between actual and estimated position. White and black circles indicate a significant overestimation or underestimation effect respectively. B Relative error as a function of the video part in Experiment 1 (grey) and Experiment 3, delayed recall (green)