Build-up of serial dependence in color working memory

Abstract

Serial dependence, how immediately preceding experiences bias our current estimations, has been described experimentally during delayed-estimation of many different visual features, with subjects tending to make estimates biased towards previous ones. It has been proposed that these attractive biases help perception stabilization in the face of correlated natural scene statistics, although this remains mostly theoretical. Color, which is strongly correlated in natural scenes, has never been studied with regard to its serial dependencies. Here, we found significant serial dependence in 7 out of 8 datasets with behavioral data of humans (total n = 760) performing delayed-estimation of color with uncorrelated sequential stimuli. Moreover, serial dependence strength built up through the experimental session, suggesting metaplastic mechanisms operating at a slower time scale than previously proposed (e.g. short-term synaptic facilitation). Because, in contrast with natural scenes, stimuli were temporally uncorrelated, this build-up casts doubt on serial dependencies being an ongoing adaptation to the stable statistics of the environment.

Figure 1

Serial dependence in color. (a) Top, illustration of the prototypical experimental design. All experiments were variations of a delayed-estimation of color task as in ref., differing mostly on set size and number of trials (see Table S1 and original references for more details). Briefly, subjects were shown a disc colored randomly in each trial. After a blank delay (of different durations, Supplementary Table S1), subjects were asked to report the color on a wheel rotated by a random angle in each trial. Bottom, serial dependence was simulated as a drift towards the previous trial trace in a diffusion process. In purple, 50 trials with a stimulus feature (purple triangle) close to the previous trial trace (gray) and in black, 50 far trials. Thick lines represent the averages of each condition, which are attracted to previous trial stimulus for trials that are close by. (b) Serial bias in the delayed-estimation of color task for all datasets. We found significant serial dependence relative to the previous report in all datasets (two-tailed t-test, t(7) = 6.5, p = 0.0003), except for the dataset collected by Souza et al. (p = 0.14). Black bar on the top marks points where the mean was above zero (bootstrap, p < 0.05). (c) Left, error to target stimulus reveals systematic biases on simulated trials. Middle, serial dependence calculated separately for trials simulated with and without systematic bias. Right, folded version of serial dependence removes all systematic biases without any additional preprocessing. (d), same as (c) for trials of Foster et al. I.

Figure 2

Serial bias builds up during a session. (a) Serial biases computed using first third (black) and second third (green) of the trials for two example experiments: Cam-Can^, and Foster et al. I. Black bars on the top mark where curves are significantly different, p < 0.05, permutation test. (b) Both experiments show a significant increase in serial dependence through the session computed with a sliding window of 75 trials for Cam-Can and 200 for Foster et al. I. (c) For each subject, we computed the slope of serial dependence over the course of the session (without averaging). We found that serial-bias build-up was significant in two experiments (marked with black error-bars: Cam-Can, p = 0.008; Foster et al. I, p < 1e−6). Error-bars were calculated from bootstrap distributions and unless stated otherwise (all experiments in (c), red), are standard errors of the mean.