2.2.1. Cheating, Lie-Telling, and Semantic Leakage ControlThe Preference Task, a modified version of the Trivia Game [13], was developed to elicit children’s cheating, lie-telling behaviors, and semantic leakage control while requiring different IDU levels (low versus high). The game contained five trivia questions and was presented in an E-Prime slide show. Each slide showed a question with three possible answers. The correct answer was displayed on the following slide. Children were told that for some of the questions, they would be asked to come up with plausible explanations for the given answer to win the game and obtain a desirable prize.

The game could be played by pressing a key for going forward and another key for going backward through the slides. At first, the experimenter demonstrated this and then asked the child to navigate through the game by themselves.

The game started with two “control” questions meant to accommodate children with the game’s rules. These were considered control questions due to their low level of complexity, simply asking children for easy answers known as common knowledge (e.g., the capital of their country). Moreover, in terms of IDU requirements, the first three questions did not elicit high IDU levels (Q1, Q2, and Q3; e.g., Q1: Which of the following is the capital city of Romania? a. Bacau, b. Timisoara, c. Bucharest), while the last two required reasoning about different perspectives (Q4 and Q5; e.g., Q4: A group of children and their parents were asked by researchers which of the following animals was the loveliest to have? a. Koala, b. Dog, c. Duck).

For the two questions that required high levels of IDU (Q4 and Q5), children were asked to answer by considering the perspective of two groups (children and their parents) and explaining each answer. Participants were told that, even though children and their parents had the same answer to the question, they did not always have the same reason for choosing it, thus tapping into understanding multiple perspectives of different targets. Q4 was designed as another “control” question, as it had an easy-to-know answer. However, in order to motivate their answer from two different perspectives, children had to minimally employ their interpretative reasoning when considering that parents’ responses might differ from children’s. This was meant as an IDU practicing question to prime participants on how to answer the last question, which was an “impossible to answer” question in the absence of cheating demands (Q5: A group of children and their parents were asked by researchers about what kind of music they think is the most fascinating? with the possible answers being a. Agrotech, b. Folktronica, c. Neurofunk).

To elicit cheating and lying, two of the questions were made up, so they were considered impossible to respond to without peeking at the correct answer because there was not a real correct answer to them (Q3 and Q5; e.g., Q3: Who discovered Tunisia? a. Alexander the Great, b. Vasco da Gama, c. Profidius Aikman). For these two questions, before the child answered each question, the experimenter excused themselves and left the room for 3 min, saying that they must take an important phone call, thus creating the opportunity for the child to cheat. If the child peeked by moving on to the slide in the experimenter’s absence, they would find an impossible-to-know answer on the slide. Upon return, the confederate asked the child if they peeked at the correct answer, and then the child was invited to give their answer to the respective question (i.e., to Q3 or Q5) [13].Subsequently, we had one deceptive question with low IDU level requirements (Q3) and another one eliciting high IDU levels (Q5). For Q5, if the child transgressed by moving on to the next slide in the experimenter’s absence, they would find an impossible-to-know answer on the slide along with the justifications for the children’s and their parents’ answer (e.g., The correct answer is: b. Folktronica; Explanations: Children: Folktronica is the most fascinating because it is easy to dance to; Parents: Folktronica is the most fascinating one because it combines multiple genres). Those who transgressed and denied their action had to generate different plausible justifications from those found in the following slide to be credible and win the game. After giving their answers, participants were shown the last slide containing the correct answer and the justifications given by children and parents (see Figure 2. for a summary of the task).

Children’s peeking behavior on the two deceptive questions was recorded by registering the keys pressed by children in the experimenter’s absence in the E-prime task. The adequacy of this new version of the task was initially piloted on an initial sample of 20 children, which led to various task refinements. Based on their behavior, children’s actions during the experimenter’s absence were scored as 2 if the child peeked on both occasions, 1 if they peeked only once, or 0 if they did not peek at all. Likewise, children’s lie-telling behavior was scored as 2 if they lied about peeking on both occasions, 1 if they lied about peeking only once, or 0 if they did not lie at all.

Also, a distinct score was obtained based on children’s given justifications for Q5 (dishonesty and IDU eliciting) and used as a proxy for semantic leakage control. We considered this score an indicator of children’s semantic leakage control because, in order to maintain the initial denial of peeking, children must be able to feign ignorance by giving different explanations than those presented to them on the slide. Children’s justifications were coded according to their match to those written on the last slide of the game (2 = entirely distinct explanations, e.g., Children chose Folktronica because they listen to it in school. Parents chose Folktronica because it reminds them of their youth; 1 = partially distinct justifications, e.g., Children chose Folktronica because they often dance to it. Parents chose Folktronica because it reminds them of their youth; 0 = identical explanations to those on the slides).

2.2.2. Interpretive Diversity Understanding (IDU)Droodle Task. Children’s IDU was assessed using the Droodle Task [28], which taps into children’s ability to understand that people exposed to the same stimuli can construct diverse interpretations due to their previous beliefs, attitudes, and knowledge (ToMi) [72,73]. First, children were shown a picture representing the first Droodle (e.g., an elephant and an orange) and asked to describe it. Then, the confederate fitted the drawing into an envelope into which a small viewing window was cut. This way, it masked most of the extended picture, exposing only a part of the drawing which was ambiguous (e.g., the trunk of the elephant and a part of the orange). Next, children were introduced to two dolls (i.e., naïve observers) who did not see the drawing beforehand. After that, children were asked to infer the interpretation of each doll upon the identity of the full drawing based on the ambiguous keyhole view, thus requiring them to ignore the information they had about the true identity of the drawing and to imagine two new interpretations that the dolls might have. A second trial immediately followed with a different picture.

The participants’ responses to each Droodle were coded according to the following criteria: (a) the similarity of children’s response with the original picture (1 = no similarity, 0 = obvious connection to the picture) and (b) the similarity between the attributions for the two dolls (1 = no similarity between the dolls’ descriptions, 0 = similar descriptions).

The Constructivist Theory of Mind Interview. Another independent measure of IDU was The Constructivist Theory of Mind Interview [71], which was meant to assess children’s capacity to reason about how a person is making sense of a situation depending on the mental processes involved and how children understand the inner workings of these processes (ToMc). The questionnaire contained 10 scenarios confronting one or two persons with visual, auditory, or verbal stimuli. Children were asked about the person(s)’ mental processes regarding those stimuli, reflecting their IDU across six different cognitive processes: Memory, Attention, Comprehension, Comparison, Planning, and Inference. Memory entails individual differences in how people remember things that happened or not (e.g., Could two people watch the same thing happen and both see and hear everything but remember it very differently?). Attention involves one’s ability to reflect on how people can operate with visual or auditory stimuli and make sense of them (e.g., Can somebody look at something but not see it?). The Comprehension scenarios question whether people can form a clear mental representation of a given material based on previous knowledge or current disposition (e.g., Could somebody remember everything someone said to them but not understand it?). Comparison involves contrasting different aspects of information from the world, whereas Planning involves anticipating action in relation to a predetermined goal. Finally, Inference refers to one’s ability to understand that people can come up with a conclusion regarding a situation based on different reasoning processes.

The responses were coded as “Yes, with Active mental Process Explanation” (scored as 2; e.g., Yes, if one sees things positively, one negatively) if children’s responses referred to the inherent differences of mental processes across individuals. However, if children made references to perceptual stimuli properties or knowledge differences between individuals, such as poor quality of perceptual information (e.g., Yes, if one didn’t pay attention), or if their response was Yes, but failed to explain (e.g., Yes, but I don’t know how), their responses were coded as “Yes, with Non-Active Mental Process Explanation” (scored as 1). Lastly, children’s lack of response or “I don’t know” answers were scored as 0. Six different ToMc scores corresponding to each mental process were calculated.

2.2.5. Socioeconomic Status

Besides basic sociodemographic information and languages spoken at home, parents completed a demographic survey that contained information about their education level and income. Income was assessed using a 5-point Likert scale indicating different levels of household incomes (1 = below 300 RON, 2 = between 400 and 500 RON, 3 = between 500 and 1000 RON, 4 = between 1000 and 2000 RON, and 5 = above 2000 RON). Parental education (mothers’ and fathers’) was evaluated on a 9-point nominal scale containing the formal education options available in Romania (1 = Primary School, 2 = Secondary School, 3 = Professional School, 4 = Pedagogical Highschool, 5 = Theoretical Highschool, 6 = Post-secondary School, 7 = Bachelor Degree, 8 = Master’s Degree, and 9 = Doctoral Degree). Parents had to choose one of the 9 possible options depending on the last formal education level graduated.

2.2.6. Procedure

At first, we obtained parental written consent for children’s involvement in the study. Before obtaining parental consent, parents received brief information about what we were interested in investigating in the current study. They also had to complete a questionnaire regarding demographical information. Next, children with parental consent were asked for verbal assent and then completed the parental practices questionnaire in a classroom setting with the teacher’s permission.

Next, every child went through an individual testing session in which the Droodle Task, Preference Task, and Constructivist Theory of Mind Interview were administered. The whole session lasted for about 40 minutes for every child. For bilingual children, all the tasks were administered in German by a trained research assistant. As for monolingual children, the testing sessions were administered in Romanian. At the end of the session, participants went through a short debriefing session about the game, and all of them received a small reward (as promised in the deceptive game’s scenario). All the testing sessions took place in children’s schools with the teachers’ permission.