Unravelling the gender productivity gap in science: a meta-analytical review.

Women underrepresentation in science has frequently been associated with women being less productive than men (i.e. the gender productivity gap), which may be explained by women having lower success rates, producing science of lower impact and/or suffering gender bias. By performing global meta-analyses, we show that there is a gender productivity gap mostly supported by a larger scientific production ascribed to men. However, women and men show similar success rates when the researchers' work is directly evaluated (i.e. publishing articles). Men's success rate is higher only in productivity proxies involving peer recognition (e.g. evaluation committees, academic positions). Men's articles showed a tendency to have higher global impact but only if studies include self-citations. We detected gender bias against women in research fields where women are underrepresented (i.e. those different from Psychology). Historical numerical unbalance, socio-psychological aspects and cultural factors may influence differences in success rate, science impact and gender bias. Thus, the maintenance of a women-unfriendly academic and non-academic environment may perpetuate the gender productivity gap. New policies to build a more egalitarian and heterogeneous scientific community and society are needed to close the gender gap in science.

Disentangling the co-structure of multilayer interaction networks: degree distribution and module composition in two-layer bipartite networks.

Species establish different interactions (e.g. antagonistic, mutualistic) with multiple species, forming multilayer ecological networks. Disentangling network co-structure in multilayer networks is crucial to predict how biodiversity loss may affect the persistence of multispecies assemblages. Existing methods to analyse multilayer networks often fail to consider network co-structure. We present a new method to evaluate the modular co-structure of multilayer networks through the assessment of species degree co-distribution and network module composition. We focus on modular structure because of its high prevalence among ecological networks. We apply our method to two Lepidoptera-plant networks, one describing caterpillar-plant herbivory interactions and one representing adult Lepidoptera nectaring on flowers, thereby possibly pollinating them. More than 50% of the species established either herbivory or visitation interactions, but not both. These species were over-represented among plants and lepidopterans, and were present in most modules in both networks. Similarity in module composition between networks was high but not different from random expectations. Our method clearly delineates the importance of interpreting multilayer module composition similarity in the light of the constraints imposed by network structure to predict the potential indirect effects of species loss through interconnected modular networks.

The robustness of plant-pollinator assemblages: linking plant interaction patterns and sensitivity to pollinator loss.

Most flowering plants depend on pollinators to reproduce. Thus, evaluating the robustness of plant-pollinator assemblages to species loss is a major concern. How species interaction patterns are related to species sensitivity to partner loss may influence the robustness of plant-pollinator assemblages. In plants, both reproductive dependence on pollinators (breeding system) and dispersal ability may modulate plant sensitivity to pollinator loss. For instance, species with strong dependence (e.g. dioecious species) and low dispersal (e.g. seeds dispersed by gravity) may be the most sensitive to pollinator loss. We compared the interaction patterns of plants differing in dependence on pollinators and dispersal ability in a meta-dataset comprising 192 plant species from 13 plant-pollinator networks. In addition, network robustness was compared under different scenarios representing sequences of plant extinctions associated with plant sensitivity to pollinator loss. Species with different dependence on pollinators and dispersal ability showed similar levels of generalization. Although plants with low dispersal ability interacted with more generalized pollinators, low-dispersal plants with strong dependence on pollinators (i.e. the most sensitive to pollinator loss) interacted with more particular sets of pollinators (i.e. shared a low proportion of pollinators with other plants). Only two assemblages showed lower robustness under the scenario considering plant generalization, dependence on pollinators and dispersal ability than under the scenario where extinction sequences only depended on plant generalization (i.e. where higher generalization level was associated with lower probability of extinction). Overall, our results support the idea that species generalization and network topology may be good predictors of assemblage robustness to species loss, independently of plant dispersal ability and breeding system. In contrast, since ecological specialization among partners may increase the probability of disruption of interactions, the fact that the plants most sensitive to pollinator loss interacted with more particular pollinator assemblages suggest that the persistence of these plants and their pollinators might be highly compromised.