arXiv subjects

César A. Hidalgo

Publications and source records attributed to César A. Hidalgo.

At least 19 recordsLinked to original sources

arXiv2026

Reasoning Enhances Robustness to Prompt Injection in LLM-Based Consensus

Large Language Models (LLMs) are gaining traction as a method to generate consensus statements and aggregate preferences in digital democracy experiments. Yet, participants can introduce critical vulnerabilities in LLM-based systems. Here, we examine the vulnerability and robustness of off-the-shelf consensus-generating LLMs to prompt-injection attacks, which consist of introducing strategically designed texts to amplify particular viewpoints, erase certain opinions, or divert consensus toward unrelated or irrelevant topics. Using data collected from a 2023 experiment conducted in the UK and predefining a majority-rule, we construct attack-free and adversarial variants of prompts containing public policy questions and opinion texts, classify opinion and consensus valences with a fine-tuned BERT model, and estimate LLM--human majority agreement rates. Overall, we find that default LLMs exhibit widespread vulnerability, especially when: (i) disagreement and agreement are finely balanced, (ii) under rational, instruction-like rhetorical strategies, and (iii) for attacks that shift consensus toward positions aligned with GB-unionist conservative manifestos relative to pro-independence left manifestos. A robustness pipeline combining GPT-OSS-SafeGuard injection detection, structured opinion representations, and GSPO-based reinforcement learning substantially reduces directional failures, outperforming state-of-the-art alternatives. While more effective detectors may enable more sophisticated attacks, these findings advance our understanding of both the vulnerabilities and the potential defenses of consensus-generating LLMs in digital democracy applications.

cs.CY↗

arXiv2026

Algorithmic Shortlisting in Participatory Budgeting

Participatory budgeting is a democratic innovation that allows citizens to propose and vote on public investment projects. To help organizers manage large volumes of submissions, we design and test privacy-preserving methods for algorithmic shortlisting. These algorithms predict which projects are likely to be funded using only project features and anonymous historical voting data. We demonstrate the limitations of a naive approach that uses a large language model to rank projects based on past success and propose a vote-based pipeline that enables state-of-the-art LLMs to perform on par with classical machine learning. Our findings indicate that user preferences in participatory budgeting are stable enough to allow algorithmic shortlisting to approximate an initial selection of projects effectively.

cs.CY↗

arXiv2026

The Theory of Economic Complexity

We provide a mechanistic foundation for economic complexity methods. In our model, an economy's ability to produce an activity depends on the joint presence of required capabilities. We analytically derive the Economic Complexity Index (ECI) for this model and show that it is a monotonic function of the stock of capabilities in an economy. We then explore the family of functions and conditions that are compatible with economic complexity estimates and show that multiplicatively separable production functions are incompatible with economic complexity estimates. By contrast, additive non-separable functions are sufficient regardless of whether they are log super-modular. We also show that this model explains differences in the shape of networks of related activities, such as the product space or research space. These findings solve long standing puzzles in the literature on economic complexity.

econ.GN↗

arXiv2026

The Software Complexity of Nations

Despite the growing importance of the digital sector, research on economic complexity and its implications continues to rely mostly on administrative records, e.g. data on exports, patents, and employment, that have blind spots when it comes to the digital economy. In this paper we use data on the geography of programming languages used in open-source software to extend economic complexity ideas to the digital economy. We estimate a country's software economic complexity index (ECIsoftware) and show that it complements the ability of measures of complexity based on trade, patents, and research to account for international differences in GDP per capita, income inequality, and emissions. We also show that open-source software follows the principle of relatedness, meaning that a country's entries and exits in programming languages are partly explained by its current pattern of specialization. Together, these findings help extend economic complexity ideas and their policy implications to the digital economy.

econ.GN↗

arXiv2025

Optimizing Economic Complexity

Efforts to apply economic complexity to identify diversification opportunities often rely on diagrams comparing the relatedness and complexity or products, technologies, or industries. Yer, the use of these diagrams is not based on empirical or theoretidal evidence supporting some notion of optimality. Here, we introduce an optimization-based framework that identifies diversification opportunities by minimizing a cost function capturing the constraints imposed by an economy's pattern of specialization. We show that the resulting portfolios often differ from those implied by relatedness-complexity diagrams, providing a target-oriented optimization layer to the economic complexity toolkit.

econ.GN↗

arXiv2025

Economic Complexity Alignment and Sustainable Development

Economic complexity has been linked to sustainability outcomes, such as income inequality and greenhouse gas emissions. Yet, it is unclear whether the pursuit of complex and/or related activities naturally aligns with these outcomes, or whether meeting sustainability goals requires policy interventions that pursue unrelated diversification. Here, we exploit multidimensional social and environmental sustainability indicators to quantify the alignment between a country's closest diversification opportunities and sustainability goals. We find that high- and upper-middle-income countries face significantly better environmentally aligned diversification opportunities than poorer economies. This means that, while richer countries enjoy diversification opportunities that align complexity, relatedness and environmental performance, this alignment is weaker for developing economies. These findings underscore the value of evaluating future diversification trajectories through a multidimensional sustainability framework, and emphasise the strategic relevance of unrelated diversification for less developed economies to foster sustainable development.

econ.GN↗

arXiv2025

Augmenting the availability of historical GDP per capita estimates through machine learning

Can we use data on the biographies of historical figures to estimate the GDP per capita of countries and regions? Here we introduce a machine learning method to estimate the GDP per capita of dozens of countries and hundreds of regions in Europe and North America for the past 700 years starting from data on the places of birth, death, and occupations of hundreds of thousands of historical figures. We build an elastic net regression model to perform feature selection and generate out-of-sample estimates that explain 90% of the variance in known historical income levels. We use this model to generate GDP per capita estimates for countries, regions, and time periods for which this data is not available and externally validate our estimates by comparing them with four proxies of economic output: urbanization rates in the past 500 years, body height in the 18th century, wellbeing in 1850, and church building activity in the 14th and 15th century. Additionally, we show our estimates reproduce the well-known reversal of fortune between southwestern and northwestern Europe between 1300 and 1800 and find this is largely driven by countries and regions engaged in Atlantic trade. These findings validate the use of fine-grained biographical data as a method to produce historical GDP per capita estimates. We publish our estimates with confidence intervals together with all collected source data in a comprehensive dataset.

econ.GN↗

arXiv2024

Large Language Models (LLMs) as Agents for Augmented Democracy

We explore an augmented democracy system built on off-the-shelf LLMs fine-tuned to augment data on citizen's preferences elicited over policies extracted from the government programs of the two main candidates of Brazil's 2022 presidential election. We use a train-test cross-validation setup to estimate the accuracy with which the LLMs predict both: a subject's individual political choices and the aggregate preferences of the full sample of participants. At the individual level, we find that LLMs predict out of sample preferences more accurately than a "bundle rule", which would assume that citizens always vote for the proposals of the candidate aligned with their self-reported political orientation. At the population level, we show that a probabilistic sample augmented by an LLM provides a more accurate estimate of the aggregate preferences of a population than the non-augmented probabilistic sample alone. Together, these results indicates that policy preference data augmented using LLMs can capture nuances that transcend party lines and represents a promising avenue of research for data augmentation.

cs.CY↗

arXiv2024

Intercity Connectivity and Innovation

Urban outputs, from economy to innovation, are known to grow as a power of a city's population. But, since large cities tend to be central in transportation and communication networks, the effects attributed to city size may be confounded with those of intercity connectivity. Here, we map intercity networks for the world's two largest economies (the United States and China) to explore whether a city's position in the networks of communication, human mobility, and scientific collaboration explains variance in a city's patenting activity that is unaccounted for by its population. We find evidence that models incorporating intercity connectivity outperform population-based models and exhibit stronger predictive power for patenting activity, particularly for technologies of more recent vintage (which we expect to be more complex or sophisticated). The effects of intercity connectivity are more robust in China, even after controlling for population, GDP, and education, but not in the United States once adjusted for GDP and education. This divergence suggests distinct urban network dynamics driving innovation in these regions. In China, models with social media and mobility networks explain more heterogeneity in the scaling of innovation, whereas in the United States, scientific collaboration plays a more significant role. These findings support the significance of a city's position within the intercity network in shaping its success in innovative activities.

physics.soc-ph↗

arXiv2023

The Role of Immigrants, Emigrants, and Locals in the Historical Formation of European Knowledge Agglomerations

Did migrants make Paris a Mecca for the arts and Vienna a beacon of classical music? Or was their rise a pure consequence of local actors? Here, we use data on more than 22,000 historical individuals born between the years 1000 and 2000 to estimate the contribution of famous immigrants, emigrants, and locals to the knowledge specializations of European regions. We find that the probability that a region develops or keeps specialization in an activity (based on the birth of famous physicists, painters, etc.) grows with both, the presence of immigrants with knowledge on that activity and immigrants with knowledge in related activities. In contrast, we do not find robust evidence that the presence of locals with related knowledge explains entries and/or exits. We address some endogeneity concerns using fixed-effects models considering any location-period-activity specific factors (e.g. the presence of a new university attracting scientists).

econ.GN↗

arXiv2023

Understanding Political Divisiveness using Online Participation data from the 2022 French and Brazilian Presidential Elections

Digital technologies can augment civic participation by facilitating the expression of detailed political preferences. Yet, digital participation efforts often rely on methods optimized for elections involving a few candidates. Here we present data collected in an online experiment where participants built personalized government programs by combining policies proposed by the candidates of the 2022 French and Brazilian presidential elections. We use this data to explore aggregates complementing those used in social choice theory, finding that a metric of divisiveness, which is uncorrelated with traditional aggregation functions, can identify polarizing proposals. These metrics provide a score for the divisiveness of each proposal that can be estimated in the absence of data on the demographic characteristics of participants and that explains the issues that divide a population. These findings suggest divisiveness metrics can be useful complements to traditional aggregation functions in direct forms of digital participation.

cs.CY↗

arXiv2023

Why people judge humans differently from machines: The role of perceived agency and experience

People are known to judge artificial intelligence using a utilitarian moral philosophy and humans using a moral philosophy emphasizing perceived intentions. But why do people judge humans and machines differently? Psychology suggests that people may have different mind perception models of humans and machines, and thus, will treat human-like robots more similarly to the way they treat humans. Here we present a randomized experiment where we manipulated people's perception of machine agency (e.g., ability to plan, act) and experience (e.g., ability to feel) to explore whether people judge machines that are perceived to be more similar to humans along these two dimensions more similarly to the way they judge humans. We find that people's judgments of machines become more similar to that of humans when they perceive machines as having more agency but not more experience. Our findings indicate that people's use of different moral philosophies to judge humans and machines can be explained by a progression of mind perception models where the perception of agency plays a prominent role. These findings add to the body of evidence suggesting that people's judgment of machines becomes more similar to that of humans motivating further work on dimensions modulating people's judgment of human and machine actions.

cs.CY↗

arXiv2023

The Policy Implications of Economic Complexity

In recent years economic complexity has grown into an active field of fundamental and applied research. Yet, despite important advances, the policy implications of economic complexity remain unclear or misunderstood. Here I organize the policy implications of economic complexity in a framework grounded on 4 Ws: what approaches, focused on identifying target activities and/or locations; when approaches, focused on timing support for related and unrelated activities; where approaches, focused on the geographic diffusion of knowledge; and who approaches, focused on the role played by agents of structural change. The goal of this paper is to provide a framework that groups, organizes, and clarifies the policy implications of economic complexity to facilitate its continued use in regional and international development.

econ.GN↗

arXiv2023

Mapping Global Value Chains at the Product Level

Value chain data is crucial to navigate economic disruptions, such as those caused by the COVID-19 pandemic and the war in Ukraine. Yet, despite its importance, publicly available value chain datasets, such as the ``World Input-Output Database'', ``Inter-Country Input-Output Tables'', ``EXIOBASE'' or the ``EORA'', lack detailed information about products (e.g. Radio Receivers, Telephones, Electrical Capacitors, LCDs, etc.) and rely instead on more aggregate industrial sectors (e.g. Electrical Equipment, Telecommunications). Here, we introduce a method based on machine learning and trade theory to infer product-level value chain relationships from fine-grained international trade data. We apply our method to data summarizing the exports and imports of 300+ world regions (e.g. states in the U.S., prefectures in Japan, etc.) and 1200+ products to infer value chain information implicit in their trade patterns. Furthermore, we use proportional allocation to assign the trade flow between regions and countries. This work provides an approximate method to map value chain data at the product level with a relevant trade flow, that should be of interest to people working in logistics, trade, and sustainable development.

econ.GN↗

arXiv2023

Multidimensional Economic Complexity and Inclusive Green Growth

To achieve inclusive green growth, countries need to consider a multiplicity of economic, social, and environmental factors. These are often captured by metrics of economic complexity derived from the geography of trade, thus missing key information on innovative activities. To bridge this gap, we combine trade data with data on patent applications and research publications to build models that significantly and robustly improve the ability of economic complexity metrics to explain international variations in inclusive green growth. We show that measures of complexity built on trade and patent data combine to explain future economic growth and income inequality and that countries that score high in all three metrics tend to exhibit lower emission intensities. These findings illustrate how the geography of trade, technology, and research combine to explain inclusive green growth.

econ.GN↗

arXiv2022

Knowledge is non-fungible

What would you do if you were asked to "add" knowledge? Would you say that "one plus one knowledge" is two "knowledges"? Less than that? More? Or something in between? Adding knowledge sounds strange, but it brings to the forefront questions that are as fundamental as they are eclectic. These are questions about the nature of knowledge and about the use of mathematics to model reality. In this chapter, I explore the mathematics of adding knowledge starting from what I believe is an overlooked but key observation: the idea that knowledge is non-fungible.

econ.TH↗

arXiv2019

Strategic reciprocity improves academic performance in public elementary school children

Social networks are pivotal for learning. Yet, we still lack a full understanding of the mechanisms connecting networks with learning outcomes. Here, we present the results of a large scale study (946 elementary school children from 45 different classrooms) designed to understand the social strategies used by elementary school children. We mapped the social networks of students using both, a non-anonymous version of a prisoner's dilemma and a survey of nominated friendships, and compared the strategies played by students with their GPAs. We found that higher GPA students invest more strategically in their relationships, cooperating more generously with friends and less generously with non-friends than lower GPA students. Our findings suggest that the higher selectivity of social capital investments by high performing students may be one of the mechanisms helping them reap the learning benefits of their social networks.

physics.soc-ph↗

arXiv2018

VizML: A Machine Learning Approach to Visualization Recommendation

Data visualization should be accessible for all analysts with data, not just the few with technical expertise. Visualization recommender systems aim to lower the barrier to exploring basic visualizations by automatically generating results for analysts to search and select, rather than manually specify. Here, we demonstrate a novel machine learning-based approach to visualization recommendation that learns visualization design choices from a large corpus of datasets and associated visualizations. First, we identify five key design choices made by analysts while creating visualizations, such as selecting a visualization type and choosing to encode a column along the X- or Y-axis. We train models to predict these design choices using one million dataset-visualization pairs collected from a popular online visualization platform. Neural networks predict these design choices with high accuracy compared to baseline models. We report and interpret feature importances from one of these baseline models. To evaluate the generalizability and uncertainty of our approach, we benchmark with a crowdsourced test set, and show that the performance of our model is comparable to human performance when predicting consensus visualization type, and exceeds that of other ML-based systems.

cs.HC↗