Search for: All records

How universities can influence socially responsible AI technology development and use. 

Discontinuities can be fairly arbitrary but also cause a significant impact on outcomes in social systems. Indeed, their arbitrariness is why they have been used to infer causal relationships among variables in numerous settings. Regression discontinuity from econometrics assumes the existence of a discontinuous variable that splits the population into distinct partitions to estimate causal effects. Here we consider the design of partitions for a given discontinuous variable to optimize a certain effect. To do so, we propose a quantization-theoretic approach to optimize the effect of interest, first learning the causal effect size of a given discontinuous variable and then applying dynamic programming for optimal quantization design of discontinuities that balance the gain and loss in the effect size. We also develop a computationally-efficient reinforcement learning algorithm for the dynamic programming formulation of optimal quantization. We demonstrate our approach by designing optimal time zone borders for counterfactuals of social capital. 

Both the search for extraterrestrial intelligence (SETI) and messaging extraterrestrial intelligence (METI) struggle with a strong indeterminacy in what data to look for and when to do so. This has led to attempts at finding both fundamental mathematical limits for SETI as well as benchmarks regarding specific signals. Due to the natural correspondence, previous information-theoretic work has been formulated in terms of communication between extraterrestrial and human civilizations. In this work, we instead formalize SETI as a detection problem, specifically (quantum) one-shot asymmetric hypothesis testing. This framework holds for all detection scenarios-in particular, it is relevant for detection of any technosignature, including quantum mechanical signals. To the best of our knowledge, this is the first work to consider the applicability of SETI for quantum signals. Using this formalism, we are able to unify the analysis of fundamental limits and benchmarking specific signals. To show a distinction between METI and SETI, we show that significantly weaker signals may be useful in detection in comparison to communication. Furthermore, the framework is computationally efficient, so it can be implemented by practicing astrobiologists. 

Abstract Designing effective and inclusive governance and public communication strategies for artificial intelligence (AI) requires understanding how stakeholders reason about its use and governance. We examine underlying factors and mechanisms that drive attitudes toward the use and governance of AI across six policy-relevant applications using structural equation modeling and surveys of both US adults (N = 3,524) and technology workers enrolled in an online computer science master’s degree program (N = 425). We find that the cultural values of individualism, egalitarianism, general risk aversion, and techno-skepticism are important drivers of AI attitudes. Perceived benefit drives attitudes toward AI use but not its governance. Experts hold more nuanced views than the public and are more supportive of AI use but not its regulation. Drawing on these findings, we discuss challenges and opportunities for participatory AI governance, and we recommend that trustworthy AI governance be emphasized as strongly as trustworthy AI. 

Background Social capital has been associated with health outcomes in communities and can explain variations in different geographic localities. Social capital has also been associated with behaviors that promote better health and reduce the impacts of diseases. During the COVID-19 pandemic, social distancing, face masking, and vaccination have all been essential in controlling contagion. These behaviors have not been uniformly adopted by communities in the United States. Using different facets of social capital to explain the differences in public behaviors among communities during pandemics is lacking. Objective This study examines the relationship among public health behavior—vaccination, face masking, and physical distancing—during COVID-19 pandemic and social capital indices in counties in the United States. Methods We used publicly available vaccination data as of June 2021, face masking data in July 2020, and mobility data from mobile phones movements from the end of March 2020. Then, correlation analysis was conducted with county-level social capital index and its subindices (family unity, community health, institutional health, and collective efficacy) that were obtained from the Social Capital Project by the United States Senate. Results We found the social capital index and its subindices differentially correlate with different public health behaviors. Vaccination is associated with institutional health: positively with fully vaccinated population and negatively with vaccination hesitancy. Also, wearing masks negatively associates with community health, whereases reduced mobility associates with better community health. Further, residential mobility positively associates with family unity. By comparing correlation coefficients, we find that social capital and its subindices have largest effect sizes on vaccination and residential mobility. Conclusion Our results show that different facets of social capital are significantly associated with adoption of protective behaviors, e.g., social distancing, face masking, and vaccination. As such, our results suggest that differential facets of social capital imply a Swiss cheese model of pandemic control planning where, e.g., institutional health and community health, provide partially overlapping behavioral benefits.