Common-Pool Resource Experiments (CPREs) are an integral part of the economists’ toolbox for analysing user harvest behaviours. Since the first CPRE—25 years ago [1]—a growing number of these experiments have been conducted for many different resources, using different sample populations, and with participants of vastly diverse backgrounds, both in the field and in the laboratory. These experiments, as any other economic experiments, have attempted to test theory and to design incentives to overcome common-pool resource dilemmas. Overall, the conclusions of these studies can be summarized as follows: (1) non-cooperative game theoretical solutions do not always hold; and (2) certain institutional settings increase cooperation levels.

A careful analysis of the relevant literature suggests that the focus of CPRE research has changed considerably over the last years. A first generation of studies aimed at contesting the non-cooperative game theoretical normative solution [2–4], whereas more recent works focused on policy implications in a myriad of different communities [5–9]. In 2011, [10] affirmed the need for yet another direction for CPREs, this time concerning “attributes of individuals as well as the social and social-ecological context in which they interact” in order to gain additional insights on the reasons behind users’ harvesting decisions. Most experimental designs of field studies account for the specific social settings of the system under investigation, but its ecological characteristics are often poorly represented. Thus, the time-continuous interaction between user behaviour and resource dynamics is not accounted for in a realistic manner. The consequences of this neglect for the external validity of the experimental results are unclear [11]. [10] suggested that a new wave of experiments should head towards intercultural comparisons, an aspect very much studied in experimental economics [12–16], and should especially address the ecological context of a social-ecological system.

However, moving towards intercultural comparisons omits aspects of how users, e.g. fishermen, decide on the quantity of their harvest [17]. Instead, CPREs keep centring their attention on institutional rules that determine “where, when, and how” one can harvest, and not on “how much” [17]. By contrast, research of exploited CPRs in natural sciences typically adopts a complementary perspective. When considering the case of fisheries, for example, arguably the CPR system of major global importance, the main research objectives have always focused on ecological aspects in order to minimize uncertainties in the assessment of exploited stocks and to ultimately optimize economic returns by adjusting extraction levels. However, although sophisticated methods have been successfully implemented to deal with the uncertainties involved, fishery management has all too often proven to be myopic, stretching cautionary scientific recommendations too far [18, 19], with consequences that have been at times catastrophic [20]. The more the quality of stock assessments and ecological models improved, however, the more apparent it became that human behaviour constitutes a considerable source of uncertainty. Even the most accurate stock assessment is of limited value when fishermen’s response to management cannot be anticipated. While this finding is neither new nor surprising [21, 22], the lack of understanding of human harvest behaviour is still regarded as a key problem in fishery management [23]. There is no simple and robust way to adequately integrate human behaviour into ecological resource management because it is context-specific and it continuously adapts to a changing environment, revealing all the characteristics of a complex adaptive system [24, 25].

Therefore, we argue here that a new generation of CPREs should incorporate attributes and characteristics of resource dynamics as well as elements of human behaviour that allow for an understanding of the time-continuous nature of effort choices and extraction levels. Incorporating the aspects just outlined in the design of CPREs will provide: (1) a much-needed push towards higher applicability of CPREs, (2) more relevance for urgent real-world problems, and (3) the capacity to produce more accurate policy recommendations for achieving a sustainable use of ecological resources in the long run.

Following these lines, we developed a new software system called OGUMI (https://www.ogumi.de), a powerful and robust yet flexible and easy-to-use tool (for example, likewise other existing software, it does not require expertise in behavioural game theory) for running CPREs in continuous time. In alternative to similar existing tools [26], which focus on standard game theoretical situations [27], are difficult to run in the field [28], or are not designed to capture real-time user responses to dynamically varying resources [29, 30], OGUMI produces high-frequency time-series chronicling the instantaneous adaptive reaction of humans to changing resource levels on mobile platforms.

OGUMI can be run on desktops, laptops, tablets, and mobile telephones. This offers the possibility to conduct experiments over telephone networks with thousands of participants. A tool that can be run on mobile devices presents several advantages [29]. Field experiments, which are an important complement to laboratory experiments, because they provide external validity and allow the use of a subject pool other than students, can be easily conducted in remote locations without the need to carry heavy equipments. Furthermore, computing devices have changed dramatically in the last years and usage has shifted from desktop computers to tablets and telephones, thus calling for platform-independent software [29].

OGUMI has been already used with over a hundred participants in actual harvest experiments in the laboratories of the Leibniz Centre for Tropical Marine Research, Bremen, Germany (results presented here in the section Testing OGUMI) and in the field in Mbour, Senegal, with local fishermen (manuscript in preparation).

OGUMI is open-source so that it can be used, modified and redistributed freely with the aims of fostering reproducibility and encouraging the undertake of field and laboratory experiments under dynamic changing conditions (e.g. under varying resource growth rate and effort levels). OGUMI also allows for conducting incentivised tasks and surveys.

As explained, OGUMI is specifically designed to address and combine continuous-time, resource-user dynamics, characteristics of the resource, and large and heterogeneous sample sizes. To test the data generated by the software, we conducted a pilot experiment that mimicked a fishery.

A total of 72 participants from Bremen (Germany) participated in the pilot CPRE in August 2015. The experiment was conducted with Android tablets. All data were collected and analysed anonymously. Subjects were not allowed to participate in more than one session. After the CPRE, participants were asked to complete a questionnaire and perform an incentivised task. At the end, participants were presented with their final payoff, which was calculated as the sum of (1) earnings from the CPRE (2) 2 € for the questionnaire, and (3) one option of the incentivised task that was chosen at random. We run a total of 6 sessions during which the participants earned an average of 15.75 €.

Fig 5 shows the client interface during one of the sessions. Users rapidly reduced the CPR from the carrying capacity to almost zero 4. The individual catch of the user also decreased. Typical of CPR experiments in continuous time is the short pause of the initially linear decrease of the CPR, which in our case occurred between time steps 570 and 590. Users seemed to realise that harvesting at current pace would lead to a collapse and thus reduce their efforts. The CPR then recovered for a short period of time until the temptation of resuming intense harvesting prevailed again. Eventually, resource level and catches collapsed and remained at very low levels. Users hence failed to coordinate the collective task of sustainable harvesting from the CPR.

Major findings based on CPREs can be summarized as follows: when facing a social dilemma [4], aspects that build trust among users, such as communication [35, 36], sanctions [6, 37], and monitoring [38, 39], increase individuals’ cooperation levels. To prove that the data generated by OGUMI are robust and consistent with this findings, we explored the impact of communication on the resource level by running two different treatments:

The results of this test (Figs 8 and 9) reveal that the effort levels, which in OGUMI can be modified by users during the experiment, change consistently with the resource: higher effort levels are associated to lower resource levels. Resource levels (Fig 8) show that (1) both treatments follow the same trend and present an abrupt decline around time 100, after which the trend stabilizes, (2) the linear representation corresponding to the treatment without communication stabilizes to resource levels that are lower than those reached in the treatment with communication, and (3) both treatments exhibit similar volatility. From Fig 9 we observe that the trends are inverted compared to the resource levels: (1) both treatments follow the same trend and present an abrupt increase around time 100, after which the trend stabilizes; (2) the linear representation corresponding to the treatment without communication stabilizes to resource levels that are higher than those reached in the treatment with communication. However, in the treatment with communication, effort levels are less volatile than in the treatment without communication. This suggests that participants do not significantly deviate from their chosen collective exploitation strategy when choosing their effort levels.

These results are consistent with knowledge consolidated by many CPR experiments run in the field and in the laboratory: face-to-face communication encourages choices towards a more efficient outcome.

Pen-and-paper methods have been for a long time the first choice for conducting CPREs. In the last years, however, computer-based experiments are becoming more popular. Several software systems have been developed [26] with z-Tree [30] being probably one of the most used. Recently, [40] made a significant step forward by abandoning the round-based design and instead adopting a time-continuous and spatially explicit five-player lab-experiment. Several authors have begun to explore human behaviour with continuous-time economic experiments using customised software [27, 40–45]. An essential finding of these works is that the possibility of participants to instantaneously react to ecological changes substantially increases cooperation. This suggests that experimental designs adopting discrete time analysis could be producing misleading environmental and conservation public policy suggestions, especially in the current context of abrupt environmental changes and rapid degradation of ecosystem services.

In relation to existing tools, OGUMI presents the following new features. 1) A large number of users can interact by harvesting from a dynamically changing ecological resource (in its current setup OGUMI mimics fisheries); 2) Users can respond to ecological changes in real-time by altering their efforts; 3) it is flexible as it can be (a) customized to account for different components of the ecosystem under study, (b) framed for different resources and multiple species thus accounting for biodiversity changes, and (c) configured to capture perturbations and shocks in resource abundance; 4) it produces high-frequency time-series chronicling the instantaneous adaptive reaction of users to current resource levels; 5) it is not a tool exclusive for the behavioural economist, i.e. it does not require expert knowledge on standard economic games, and can be easily used by ecologists interested on experimenting with the dynamical aspects of human-resource interactions.

We provide OGUMI as free software under the Apache License 2.0 (http://www.apache.org/licenses/). The source code, for both client and server, and full documentation are available in GitHUB (https://github.com/ogumi), a web repository that offers distributed version control and source code management functionalities such as bug tracking. A compiled, ready-to-use version of OGUMI, which we use to run the experiments presented in this paper, and the necessary documentation are available at https://www.ogumi.de. We ask that people cite the present paper when using OGUMI for academic or other purposes.