Group living and hence sociality is a widespread phenomenon among animals. Because groups are often composed of individuals of different age, sex and relatedness, conflicts arise concerning reproduction or access to resources. Such conflicts may dramatically increase when groups are perturbed from the outside or undergo changes in composition through dispersal or immigration. Conflicts may disrupt group stability, so if individual fitness is dependent on group stability [1], evolution should favour mechanisms that decrease disruption [2], [3].

Researchers have identified several mechanisms through which social animals, especially nonhuman primates, manage conflicts, including dominance [4], reconciliation [3], bystander affiliation to recipients and/or initiators of aggression [5], [6], [7], [8], [9], mediation [10], punishment [11], [12] and policing [1], [13]. The focus of this paper is on events of policing, which we define as impartial interventions by third parties in ongoing conflicts. Being impartial, these interventions never include aggression directed specifically at one of the contestants. Such policing is different from the common partial bystander involvement in conflicts, which involves agonistic support of one of the contestants. It is also different from punishment [11], which concerns aggression directed specifically at the wrongdoer. To emphasize the impartiality of the performers of policing, we call them “arbitrators”.

Policing has been reported in chimpanzees [14], bonobos [15], mountain gorillas [16], [17], [18] and in captive Bornean orang-utans [19], [20]. Other species include the golden monkeys [21], hamadryas baboons [22], and several macaques species such as Barbary (A. Bissonnette; unpublished data), rhesus [23], [24], Japanese [25], pigtailed [13], [26] and Tonkean macaques [27].

Policing is risky because it requires approaching two or more fighting contestants, which may lead to becoming the recipient of aggression [13]. Additionally, arbitrators may incur energy and opportunity costs. To be favoured by natural selection, therefore, policing should bring fitness benefits for the arbitrator. However, the impartiality makes it difficult to recognize such direct fitness benefits.

Various hypotheses have been proposed for the function of policing in nonhuman primates. However, because policing is a relatively rare behaviour among primates, the cross-species data thus far has not consistently supported any functional hypothesis. In this paper, we discuss the proposed hypotheses and develop predictions for policing in chimpanzees, where conflicts often arise among females over access to food [28] or among males over access to females [29] and may result in severe dyadic or even polyadic agonistic interactions [10].

The most popular hypothesis claims that policing brings only indirect benefits to the arbitrator, because it serves to increase group stability [30] by reducing the number of conflicts [13], [30] and by allowing all individuals build up larger and more diverse social networks [1]. Increased group stability may indirectly increase the arbitrator's fitness via the reproductive benefits of living in a stable network of beneficial relationships [26]. In terms of proximate causation [31], [32], policing might be motivated by a concern about the conflicts of others and thus might reflect a basic “community concern” [33]. As a result, policing has been seen as a precursor of human morality [33], [34], and therefore may inform of its evolution.

If the increase of group stability is the primary function of policing, it should occur most often when group stability is weakened (see Table 1 for predictions). Group instability may arise due to major relationship changes, such as rank reversals near the top of the hierarchy, death of an important social player, or immigration/emigration. In such unstable circumstances, relationships are easily damaged and thus group stability is at stake. First, the group stability hypothesis predicts that arbitrators are high-ranking individuals because high-ranking individuals have the power to effectively stop aggression [13] and simultaneously have a lower risk of receiving aggression upon approaching combatants. Second, it predicts that arbitrators can be both male and female because both sexes have a stake in group stability. Social instability in a group constitutes a major stress factor for all group members as it has negative influences on social relationships and hence various social interactions such as grooming, play and physical contact [1] and also individual health [35], [36]. Hence, all group members have a stake in group stability but not all individuals possess enough social power to control group stability. Third, policing should occur in conflicts that are most likely to disrupt relationships in a group, in particular those involving intensive aggression involving multiple individuals. Finally, because of the primacy of conflict intensity, policing should not be limited to particular sex-dyad combinations.

Whereas the group stability hypothesis may indirectly increase the arbitrator's fitness, alternative hypotheses propose direct benefits. Thus, a second hypothesis assumes that policing helps high-ranking individuals to assert their social interests [37], [38], [39]. This assurance of dominance hypothesis is supported in fallow deer (Dama dama), where impartial interventions are a male strategy to control other males' social advance in the hierarchy [40], [41]. The hypothesis predicts for chimpanzees that arbitrators are high-ranking males, and that policing occurs only in conflicts among direct social competitors, i.e. in male-male conflicts. It does not expect the same pattern for females because chimpanzee females tend not to fight over rank.

A third hypothesis is that policing functions to assure sexual benefits. It has been argued that in species where females transfer between groups, males may police female-female conflicts to discourage females from emigrating, and so preserve reproductive payoffs for the policing males [39]. In addition, policing may reduce stress faced by females due to aggressive conflicts. In chimpanzees, as in other male-philopatric species, immigrant females often meet aggressive resistance by resident females [42], [43], [44], [45] and male policing could make immigrants more likely to stay in the group. Indeed, by policing such conflicts males may also be able to establish and preserve valuable relationships with the females without damaging their relationship with either opponent [39], [46]. This sexual benefits hypothesis predicts that policing is always performed by males, who intervene only in female-female conflicts.

Finally, policing may be directly self-serving in preventing escalated aggression from “spilling over” to affect the policing individual. In this case, we expect it to be performed by individuals with the highest likelihood of being targets of aggression, i.e. low-ranking individuals. However, given the potential risk of intervening in agonistic interactions, the existing literature on policing in various species does not support this protection from aggression hypothesis, as arbitrators appear to be predominantly high-ranking individuals [13], [47], [48]. Therefore, we will not consider this hypothesis any further.

The aim of this study is to test the predictions of the three hypotheses to identify the function of policing in chimpanzees (see Tab. 1). The predictions focus on the identity of the arbitrators, the kinds of dyads in which interventions are expected, and the role of social instability. First, we report a detailed study of a captive group of chimpanzees (Gossau) with a high level of social instability and a high rate of policing, which allowed us to directly test the aforementioned hypotheses. This represents the first systematic study of chimpanzee policing, which so far has been reported on a rather anecdotal level in the literature [14], [47], [49]. Second, we compare the policing patterns found in Gossau with three other captive chimpanzee groups (Basel, Chester, Arnhem). The comparison relies on data collected earlier for other research purposes. Therefore, the policing data are extracted from the records post hoc. This comparison allowed us to assess the generality of the findings of the first part regarding the identity of arbitrators, sex-dyad combinations of policed conflicts and, qualitatively, the social conditions in which policing occurred.

We explored impartial interventions, i.e. policing, as a conflict management mechanism in chimpanzees. We addressed three hypotheses for the function of policing in chimpanzees: a group-stabilizing function, consistent with an expression of “community concern” by the arbitrators; male assurance of dominance by prohibiting rise of social competitors; and male assurance of sexual benefits by alleviating female-female aggression and simultaneously improving own relationship with females.

In the main study, we found that only adult, high-ranking males performed policing and they policed conflicts of all sex-dyad combinations. The primary predictor of policing was conflict complexity, in that polyadic conflicts were policed more often than dyadic ones. The occurrence of policing across all sex-dyad combinations does not support the assurance of dominance hypothesis or the assurance of sexual benefits hypotheses, but is consistent with the group stability hypothesis. Moreover, the high prevalence of policing coincided with social instability in the group, i.e. the introduction of three adult females and a rank reversal between the two top-ranking males. Thus, social relationships were unstable and easily disturbed. Policing as a group stabilizer may have prevented conflicts from escalating, thereby preventing further disruption of group stability.

However, as all policing in Gossau was performed by adult males, and one of them showed a tendency to police male-male conflicts, we could not distinguish between the group stability hypothesis and the assurance of dominance hypothesis. Therefore, we conducted a broader evaluation of the hypotheses by combining policing data from three other captive groups. The comparative data added support for the group stability hypothesis. High-ranking individuals of both sexes performed the vast majority of policing, and they intervened in conflicts among all sex-dyad combinations. Moreover, although policing was rare overall, policing was more likely during times of social instability. These patterns are consistent with the hypothesis of a group-stabilizing function.

Available reports from wild chimpanzees give further support to this hypothesis. In both Mahale and Gombe National Parks [47], [48], [69], arbitrators were high-ranking individuals of both sexes [28], conflicts of all sex-dyad combinations were policed and, at least in Mahale, occurred at times of social instability. Altogether, it appears plausible that the main function of policing in chimpanzees is to stabilize group dynamics.

The data did not support the two alternatives proposing a direct fitness benefit to the interveners. Moreover, an alternative possibility to explain policing, namely that arbitrators merely dislike noisy disturbances and take action to stop them [12], [52], also seems unlikely because policing is relatively rare while noisy conflicts occur frequently.

The results stressed the importance of social power in effective policing. In Gossau, arbitrators exhibited a high success rate of policing (86.96%) and almost never received aggression in response to their behaviour. The near-absence of aggression towards arbitrators is not surprising given their high social ranks. In the other zoos too, the arbitrators were high-ranking in nearly all cases, and in the only two exceptions (once in Chester and once in Arnhem) they were nevertheless individuals of potential social importance. The fact that mostly high ranking individuals engaged in policing is consistent with the theoretical models of Frank [30], [70], [71] and the empirical work in pigtailed macaques of Flack et al. [13], in which heterogeneities in power lead to heterogeneities in the tendency to police. The more powerful an individual is, the more effective it is in controlling a conflict and this at a low cost [72].

An interesting exception to this pattern was seen in Gossau, where the introduced females, despite being high-ranking and large-bodied, did not engage in policing. We think that this might be explained by the fact that as newcomers, they were not yet fully accepted by the others and thus did not hold the necessary social power. Alternatively, the immigrant females may have lacked the motivation to police, if they did not yet regard the group as their “own”. Another limiting factor might have been the fact these females conceived soon after the introduction and subsequently carried vulnerable infants.

When policing, arbitrators in Gossau used different tactics, mainly preferring to literally “run through” the conflict thereby separating the combatants, or to attend the conflict (see Results: Tactics of Policing for definition). For the latter tactic to be effective, arbitrators need to be perceived by all combatants as being more powerful than themselves. Similarly, various policing behaviours were seen in Arnhem and Chester. However, we could reliably extract only policing events that involved clear physical involvement. Thus, the overall prevalence may have been underestimated by excluding the passive attendance-type of interventions. However, we think these conclusions are not affected by this possible bias, because passive interventions are likely to have been done by high-ranking individuals, as in Gossau.

Policing occurs only rarely in chimpanzees, which is probably why its function has remained elusive to researchers. We hypothesize that several preconditions are necessary for impartial interventions to occur regularly. First, conflicts that occur in a group must have the potential to endanger group stability. This is probably not the limiting factor in chimpanzees, where intensive, polyadic conflicts occur regularly. Second, relationship stability in a group must be challenged, leading to increased likelihood of disruption by conflicts. This aspect may explain why policing is so rare. Several effective, mainly dyadic, conflict management mechanisms exist in the chimpanzee behavioural repertoire, which may suffice maintaining group stability under normal conditions. However, rank reversals among the highest-ranking individuals, or significant demographic changes such as the removal or addition of adults may promote conditions in which policing emerges. Third, a group needs to include individuals that possess sufficient authority and power to successfully control conflicts. Gaining authority may be associated with long-term membership and high rank in the group, and given chimpanzee socio-ecology, lack of authoritative individuals is probably not the explanation for scarcity of policing in chimpanzees. However, personality may influence the individual tendency to engage in policing. High-ranking individuals are not necessarily all equally likely to be involved in group activities [73]. Future studies should explore whether chimpanzees change their policing strategy during their lifetime as they rise or fall in rank, whether it is dependent on the group composition, and whether it is determined by individual personality of the arbitrators.

Increase of group stability by active policing may be rooted in a basic “community concern”, i.e. the motivation to maintain stable, harmonious dynamics in a group [33]. Although there may also be additional, self-serving benefits at the proximate level (e.g. females may prefer males that engage in policing as mates and allies [14]), group-stabilizing policing may be driven by a pacifying motivation and as such, can be considered as prosocial behaviour.

In humans, community concern is expressed in its highest degree and can be seen as the very foundation of human morality and indeed social norms. Thus, in humans, as in chimpanzees, community concern may constitute one of the proximate mechanisms for conflict management, which likely is independent of its ultimate goal of group stability, which in turn increases fitness of group members. Thus, from a proximate perspective, policing behaviour may be genuinely prosocial in that arbitrators perform it without self-serving motives [32], [74].

Theoretical and empirical studies on the emergence of human large-scale cooperation have shown that one of the important mechanisms is the existence of punishment, either directly or through externalized “pool-punishment” forces [75]. Institutionalized pool-punishing by law enforcement effectively maintains cooperation through social norms [76]. Nonhuman primates, despite the existence of small-scale cooperation, social learning and potentially proto-normative behaviour [77], do not exert direct or pool-punishment. Neither do most small-scale human foragers [78]. Thus, the policing as a conflict management mechanism seen among nonhuman primates might be a precursor for large-scale “police forces” that maintain normative behaviour in large-scale human societies.

In conclusion, we found that although policing behaviour is overall rare, it occurs in several chimpanzee groups. Its frequency appears to increase at times of social instability. High-ranking individuals of both sexes police conflicts, and all sex-dyad combinations of conflicts are policed. The higher the conflict's disruption potential (i.e. polyadic and/or severe aggression), the more likely it is policed. This was especially shown in the main study, in which we could assess the occurrence of policing with a predictive model. We hypothesized that high rates of policing are due to considerable social instability, which may disrupt the group's social structure. Policing was highly effective in stopping conflicts. These results suggest that the main function of policing is to maintain the group's social stability. This behaviour may reflect arbitrator's pacifying motivation in the form of a basic “community concern”.