Open Research Repository ORR
Not a member yet
2835 research outputs found
Sort by
A hypergeometric approach to fair rankings with finite candidate pool
No full textRanking algorithms play a pivotal role in decision-making processes across diverse domains, from search engines to job applications. When rankings directly impact individuals, ensuring fairness becomes essential, particularly for groups that are marginalised or misrepresented in the data. Most of the existing group fairness frameworks often rely on ensuring proportional representation of protected groups. However, these approaches face limitations in accounting for the stochastic nature of ranking processes or the finite size of candidate pools. To this end, we present hyperFA∗IR, a framework for assessing and enforcing fairness in rankings drawn from a finite set of candidates. It relies on a generative process based on the hypergeometric distribution, which models real-world scenarios by sampling without replacement from fixed group sizes. This approach improves fairness assessment when top-k selections are large relative to the pool or when protected groups are small. We compare our approach to the widely used binomial model, which treats each draw as independent with fixed probability, and demonstrate-both analytically and empirically-that our method more accurately reproduces the statistical properties of sampling from a finite population. To operationalise this framework, we propose a Monte Carlo-based algorithm that efficiently detects unfair rankings by avoiding computationally expensive parameter tuning. Finally, we adapt our generative approach to define affirmative action policies by introducing weights into the sampling process
How to do science as a woman and laugh?:Insights and lessons from Hungary
No full textIt is difficult to write the closing chapter to this multifaceted yet coherent volume. It is multifaceted because the examples and case studies are drawn from many countries around the world and coherent because very similar patterns emerge about the position of women in science, engineering and medicine in the twentieth century. The contributions analyse trends in women’s participation in STEMM, complicating our understanding of what it meant to be in/visible in these fields and documenting the challenges women encountered as well as the strategies they devised to overcome them. Many of these hurdles have changed little in character over the decades. In this final chapter, which also functions as an epilogue, I will add another case study to this impressive collection, that of Hungary, to illustrate continuities in the challenges women have faced and suggest ways forward, discussing and drawing inspiration from the strategies and tactics they have employed to overcome them
Epidemic paradox induced by awareness driven network dynamics
No full textWe study stationary epidemic processes in scale-free networks with local-awareness behavior adopted by only susceptible, only infected, or all nodes. We find that, while the epidemic size in the susceptible-aware and the all-aware models scales linearly with the network size, the scaling becomes sublinear in the infected-aware model. Hence, fewer aware nodes may reduce the epidemic size more effectively; a phenomenon reminiscent of Braess's paradox. We present numerical and theoretical analysis and highlight the role of influential nodes and their disassortativity to raise epidemic awareness
What Drives International Cooperation? Evidence from WTO Negotiations
No full textWhy do some countries cooperate in international negotiations while others do not? This paper examines how regime type and trade relationships jointly shape cooperation among states. While prior research claims that democracies are inherently more cooperative and that trade fosters collaboration, we argue that neither factor alone sufficiently explains patterns of cooperation. Drawing on 1,567 documents submitted by World Trade Organization (WTO) members during the Doha Round negotiations (2000–2012), we analyse cooperation between country pairs (dyads) using hurdle models to assess both the likelihood and extent of cooperation. We find that democracies are not uniformly more cooperative but become so only when high levels of trade interdependence exist. Similarly, democracies also cooperate with authoritarian regimes when intensive trade relationships are present. These results challenge the assumption that democratic governance naturally generates cooperation, showing instead that economic incentives play a decisive role. The study advances understanding of international cooperation in complex multilateral negotiation settings
