Uncertainty monitoring in Eurasian jays (Garrulus glandarius)

Abstract

Metacognition- namely the capacity to reflect on one's own cognitive processes - provides animals with numerous evolutionary advantages. Metacognition abilities encompass enhanced decision-making in uncertain situations, more efficient resource management, error detection and correction, and improved problem-solving skills. Here, we investigate how Eurasian jays, Garrulus glandarius, monitor uncertainty through a working memory food-retrieval task. In this task, a desirable food item is hidden under one of two cups, which are then shuffled either once (easy treatment) or several times (difficult treatment). The jays then choose to either engage in locating the food or opt out by selecting a third cup that offers a less preferred food reward. Our findings reveal that the difficulty of the task significantly influenced the jays' choice, with a higher tendency to opt out during difficult trials. Individual performance analysis revealed that when jays that typically opted out of difficult trials chose to engage instead, they exhibited significant accuracy. This suggests their decisions were guided by a confidence assessment of their knowledge. Overall, our study indicates that Eurasian jays possess metacognitive abilities that enable them to evaluate their own certainty and make strategic decisions based on perceived task difficulty and confidence in their knowledge. These capabilities likely confer advantages in natural settings, such as caching behaviours, allowing jays to make well-informed decisions about when to store or retrieve food based on environmental cues and internal assessments of uncertainty.

Keywords: Avian cognition; Eurasian jays; Individual differences; Metacognition; Self-awareness; Uncertainty monitoring.

Fig. 1

Training procedure

Fig. 2

Test procedure

Fig. 3

Predicted probability of correct choices by treatment difficulty: This figure shows the predicted probability of making correct choices when engaged in the tasks (easy vs. difficult). Error bars (whiskers) showing the standard error of the mean

Fig. 4

Predicted probability of choosing to opt out across treatments: This figure shows the predicted probability of opting out as a function of treatment difficulty (easy vs. difficult). Bars on the plot display the probabilities, with error bars (whiskers) showing the standard error of the mean

Fig. 5

Individual performance. In light blue, individual performance in the easy trials; in blue, individual performance in the difficult trials. Each individual is represented on the x-axis. The dashed red line indicates chance level. (A) Percentage of correct responses. (B) Percentage of opt-out responses

Fig. 6

Proportion of Opt-Out Trials by Subject. The bars represent 95% confidence intervals. Subjects that showed a proportion of trials different from chance levels are highlighted in light green. Specifically, Dolci, Jaylo, and Poe exhibited a significant tendency to opt out more than to choose incorrectly. Godot displayed a preference for engaging with the task