Large Language Models (LLMs) enable unprecedented social science experimentation by creating controlled hybrid human-AI environments. We introduce Epitome (www.epitome-ai.com), an open experimental platform that operationalizes this paradigm through Matrix-like social worlds where researchers can study isolated human subjects and groups interacting with LLM agents. This maintains ecological validity while enabling precise manipulation of social dynamics. Epitome approaches three frontiers: (1) methodological innovation using LLM confederates to reduce complexity while scaling interactions; (2) empirical investigation of human behavior in AI-saturated environments; and (3) exploration of emergent properties in hybrid collectives. Drawing on interdisciplinary foundations from management, communication, sociology, psychology, and ethics, the platform's modular architecture spans foundation model deployment through data collection. We validate Epitome through replication of three seminal experiments, demonstrating capacity to generate robust findings while reducing experimental complexity. This tool provides crucial insights for understanding how humans navigate AI-mediated social realities, knowledge essential for policy, education, and human-centered AI design.
Henrik Häggström, Sebastian Persson, Marija Cvijovic
et al.
The analysis of data from multiple experiments, such as observations of several individuals, is commonly approached using mixed-effects models, which account for variation between individuals through hierarchical representations. This makes mixed-effects models widely applied in fields such as biology, pharmacokinetics, and sociology. In this work, we propose a novel methodology for scalable Bayesian inference in hierarchical mixed-effects models. Our framework first constructs amortized approximations of the likelihood and the posterior distribution, which are then rapidly refined for each individual dataset, to ultimately approximate the parameters posterior across many individuals. The framework is easily trainable, as it uses mixtures of experts but without neural networks, leading to parsimonious yet expressive surrogate models of the likelihood and the posterior. We demonstrate the effectiveness of our methodology using challenging stochastic models, such as mixed-effects stochastic differential equations emerging in systems biology-driven problems. However, the approach is broadly applicable and can accommodate both stochastic and deterministic models. We show that our approach can seamlessly handle inference for many parameters. Additionally, we applied our method to a real-data case study of mRNA transfection. When compared to exact pseudomarginal Bayesian inference, our approach proved to be both fast and competitive in terms of statistical accuracy.
Hypotheses are central to information acquisition, decision-making, and discovery. However, many real-world hypotheses are abstract, high-level statements that are difficult to validate directly. This challenge is further intensified by the rise of hypothesis generation from Large Language Models (LLMs), which are prone to hallucination and produce hypotheses in volumes that make manual validation impractical. Here we propose Popper, an agentic framework for rigorous automated validation of free-form hypotheses. Guided by Karl Popper's principle of falsification, Popper validates a hypothesis using LLM agents that design and execute falsification experiments targeting its measurable implications. A novel sequential testing framework ensures strict Type-I error control while actively gathering evidence from diverse observations, whether drawn from existing data or newly conducted procedures. We demonstrate Popper on six domains including biology, economics, and sociology. Popper delivers robust error control, high power, and scalability. Furthermore, compared to human scientists, Popper achieved comparable performance in validating complex biological hypotheses while reducing time by 10 folds, providing a scalable, rigorous solution for hypothesis validation.
The challenge of aligning artificial intelligence (AI) with human values persists due to the abstract and often conflicting nature of moral principles and the opacity of existing approaches. This paper introduces CogniAlign, a multi-agent deliberation framework based on naturalistic moral realism, that grounds moral reasoning in survivability, defined across individual and collective dimensions, and operationalizes it through structured deliberations among discipline-specific scientist agents. Each agent, representing neuroscience, psychology, sociology, and evolutionary biology, provides arguments and rebuttals that are synthesized by an arbiter into transparent and empirically anchored judgments. As a proof-of-concept study, we evaluate CogniAlign on classic and novel moral questions and compare its outputs against GPT-4o using a five-part ethical audit framework with the help of three experts. Results show that CogniAlign consistently outperforms the baseline across more than sixty moral questions, with average performance gains of 12.2 points in analytic quality, 31.2 points in decisiveness, and 15 points in depth of explanation. In the Heinz dilemma, for example, CogniAlign achieved an overall score of 79 compared to GPT-4o's 65.8, demonstrating a decisive advantage in handling moral reasoning. Through transparent and structured reasoning, CogniAlign demonstrates the feasibility of an auditable approach to AI alignment, though certain challenges still remain.
Javier Garcia-Bernardo, Eva Jaspers, Weverthon Machado
et al.
Social contexts -- such as families, schools, and neighborhoods -- shape life outcomes. The key question is not simply whether they matter, but rather for whom and under what conditions. Here, we argue that prediction gaps -- differences in predictive performance between statistical models of varying complexity -- offer a pathway for identifying surprising empirical patterns (i.e., not captured by simpler models) which highlight where theories succeed or fall short. Using population-scale administrative data from the Netherlands, we compare logistic regression, gradient boosting, and graph neural networks to predict university completion using early-life social contexts. Overall, prediction gaps are small, suggesting that previously identified indicators, particularly parental status, capture most measurable variation in educational attainment. However, gaps are larger for girls growing up without fathers -- suggesting that the effects of social context for these groups go beyond simple models in line with sociological theory. Our paper shows the potential of prediction methods to support sociological explanation.
Information security culture has been studied as a systemic phenomenon that determines generation Z managers’ behavior in the digital environment. Internet addiction and digital anxiety are socio-psychological factors affecting individual digital hygiene habits and compliance with information security rules. The psychological portrait of generation Z managers has been revealed, how they differ from other generations, and what socio-psychological problems arise in this regard. Special attention has been paid to new social phenomena that have become widespread, such as the emergence of Internet addiction and digital anxiety among generation Z managers, and an explanation of these scientific terms and how they affect information security culture has been given. The structural components of information security culture (values and norms, knowledge and skills, daily practices, leadership, and organizational artifacts) and their relationship to management activities of generation Z people have been described. The analysis of what negative consequences in the context of management activities digital anxiety, Internet addiction, and digital hygiene non-observance can lead to at the level of an organization and personality as a whole has been carried out. For preventing and correcting Internet addiction and digital anxiety in generation Z managers in the context of digital hygiene and information security, a comprehensive approach to solving this scientific issue has been proposed, including both individual psychological strategies (digital detox, cognitive behavioral techniques, development of offline activities and social connections, manager’s digital hygiene, strengthening information security, and mindfulness practices), as well as organizational strategies (creating a culture of information security and digital well-being, reviewing performance metrics, and maintaining work-life balance).
The rapid evolution of large language models (LLMs) and their capacity to simulate human cognition and behavior has given rise to LLM-based frameworks and tools that are evaluated and applied based on their ability to perform tasks traditionally performed by humans, namely those involving cognition, decision-making, and social interaction. This survey provides a comprehensive examination of such human-centric LLM capabilities, focusing on their performance in both individual tasks (where an LLM acts as a stand-in for a single human) and collective tasks (where multiple LLMs coordinate to mimic group dynamics). We first evaluate LLM competencies across key areas including reasoning, perception, and social cognition, comparing their abilities to human-like skills. Then, we explore real-world applications of LLMs in human-centric domains such as behavioral science, political science, and sociology, assessing their effectiveness in replicating human behaviors and interactions. Finally, we identify challenges and future research directions, such as improving LLM adaptability, emotional intelligence, and cultural sensitivity, while addressing inherent biases and enhancing frameworks for human-AI collaboration. This survey aims to provide a foundational understanding of LLMs from a human-centric perspective, offering insights into their current capabilities and potential for future development.
Resumo Atento às concepções do tempo que orientam os retratos da vida social brasileira delineados nas versões inaugurais de História econômica do Brasil e Sobrados e mucambos, o artigo examina duas hipóteses: primeiramente, as imagens do país projetadas nos ensaios assentam-se sobre um mesmo referencial epistemológico que estreita as possibilidades de intelecção de ambos tanto a respeito dos ingredientes e processos implicados na formação brasileira, quanto acerca do lugar e das perspectivas dessa sociedade no Ocidente moderno. Conforme a segunda hipótese, não obstante suas intenções críticas, HEB e SeM mantêm-se presos aos horizontes de cognição de certo enquadramento hegemônico da modernidade, o qual conduz Caio Prado Jr. e Gilberto Freyre a ratificarem a posição retardatária e coadjuvante do país vis-à-vis os chamados contextos modernos modelares.
Loa Gordon, Gabriella Christopher, Nicole McNair
et al.
The authors explore how the coronavirus disease 2019 (COVID-19) pandemic amplified a broad range of care practices for women in academia. Engaging the lived experiences of faculty and research staff members, the authors investigate the entangled impact of care on work-life productivity during the first year and a half of the global pandemic. Mixed-methods data include roundtable accounts focusing on the COVID-19 experiences of woman employees at a Canadian university with supplementary analyses from a related institutional survey. The findings demonstrate a triangulated configuration of care responsibilities: care directly associated with work, care outside of work without disruption to professional excellence, and pressures of self-care. The authors conclude by describing the “cruel optimism” of care that is at once rewarding but simultaneously diminishing to personal flourishing. This article contributes to analytical efforts to critically redefine care in higher education as an ambivalent set of laborious practices steeped in inequities.
The existential and socio-psychological threats to human bodily and emotional existence are observed in the urbanized environment, and the origins of the modern urban crisis are discovered. The author attempts to assess the danger and consequences of urbanization for modern human society. The paper formulates a typology of urban activism in the context of socio-philosophical discourse.
The aim of the research is philosophical comprehension of human existence in an urbanized environment. In accordance with the purpose, the tasks are outlined: to characterize the “city man”; to identify the contradictory consequences of urbanization for a modern Human; to determine the influence of urbanization atpeople’s lifestyle; to analyze the typology of the activities of city residents which(the activities) transform the urban environment in the context of modern urbanism.
Object: urbanism as a socio-philosophical phenomenon, subject: the existential dimension of Human in an urban environment.
Methodology. To achieve this goal, general scientific methods were used: analysis and synthesis, analogies, classifications, as well as philosophical methods of cognition (dialectical and hermeneutic). The method of generalization of philosophical and sociological issueswas applied and in particular by using interdisciplinary approach. The means of visual anthropology (cinematography, photography) are engaged in the study to analyze the documentary series “Homo Urbanus” whichis of special scientific value as a source of important social knowledge.
The originality of the study: the existential crisis was studied in the focus of urban anthropology, a classification of types of urban activism was proposed. Practical application. The results of the study can be applied in the future interdisciplinary research, as well as in the urban anthropology studies, in the research of the mutual influence of the city and man, as well as of separate topics of educational courses (“Urban Studies”, “Philosophy”, “Sociology”, “Anthropology”, “Aesthetics of Architecture and Design”, etc.).
本研究從教育與勞動市場連結的觀點探討「學用相符」與「就業職能」對畢業生初入職場薪資的影響，以文憑主義、訊號理論與人力資本論為理論依據，研究方法採多層次分析，總體層次包含團隊合作能力、溝通協調能力、專業技術能力三項就業職能，個體層次則探討垂直和水平學用相符程度對薪資的影響，且考慮總體與個體兩個層次的互動效應。資料來源為「臺灣高等教育整合資料庫」95 學年度畢業後一年流向調查，合併學士及碩士之資料。研究發現，總體層次的「團隊合作能力」以及「專業技術能力」對於薪資有顯著的提升效果，「溝通協調能力」則是負向作用；個體層次方面，垂直與水平的學用不符皆會導致薪資減少。總體與個體層次的調節效果呈現：縱向的學用相符與薪資間的關係會受到「團隊合作能力」與「專業技術能力」調節作用之影響，而三個就業職能在水平學用相符與薪資間則無調節效果。回應到理論的解釋，文憑和訊號對職場新鮮人的薪資提升皆有正向的影響，它的作用就像是過濾器，在第一階段先淘汰了學用不符者，人力資本在第二階段才發生實質的效果。本研究主題契合聯合國「永續發展目標」中「勞力市場制度」關懷的議題。
This study investigated the factors influencing graduates’ salaries. pecifically, this study analyzed the relationship between education and the labor market by considering education-job match and employee competencies. This article used credentialism, signaling theory and human capital theory as the theoretical basis to conduct in-depth analysis and discussion. To achieve
research purpose, a multilevel analysis was adopted. At the group level, the study investigated several competencies, such as teamwork, communication skills, and expertise, among individuals with different university majors. At the individual level, the study focused on how vertical and horizontal education-job matches influence salary. The moderating effect of the two levels was also considered. Data were obtained from the 2006 follow-up of a university graduate survey from the Taiwan Integrated Higher Education Database, which contains data from bachelor’s and master’s degree holders. Our findings at the group level indicate that teamwork and expertise positively affect salaries. However, communication skills have the opposite effect. At the individual level, both vertical and horizontal education-job mismatches result in lower salaries. The interactions between
these two levels, teamwork, and expertise moderate the relationship between vertical education-job match and salary. The three competencies do not moderate the relationship between horizontal education-job match and salary. In terms of theoretical explanations, credentialism and signaling
theory have a positive impact on the salary increase of freshmen to the labor market. They act as a filter, eliminating education-misfit and major-misfit workers in the first stage. Thereafter, human capital theory takes substantial effect in the second stage. The research topic and analysis process are
consistent with the labor market institution issues concerned by the “decent work and economic growth” project under the United Nations Sustainable Development Goals.
Behavioral studies using personal digital devices typically produce rich longitudinal datasets of mixed data types. These data provide information about the behavior of users of these devices in real-time and in the users' natural environments. Analyzing the data requires multidisciplinary expertise and dedicated software. Currently, no generalizable, device-agnostic, freely available software exists within Python scientific computing ecosystem to preprocess and analyze such data. This paper introduces a Python package, Niimpy, for analyzing digital behavioral data. The Niimpy toolbox is a user-friendly open-source package that can quickly be expanded and adapted to specific research requirements. The toolbox facilitates the analysis phase by offering tools for preprocessing, extracting features, and exploring the data. It also aims to educate the user on behavioral data analysis and promotes open science practices. Over time, Niimpy will expand with extra data analysis features developed by the core group, new users, and developers. Niimpy can help the fast-growing number of researchers with diverse backgrounds who collect data from personal and consumer digital devices to systematically and efficiently analyze the data and extract useful information. This novel information is vital for answering research questions in various fields, from medicine to psychology, sociology, and others.
Abu Toasin Oakil, AHM Mehbub Anwar, Alma Alhussaini
et al.
Saudi Arabia intends to reduce GHG emissions by 278 million tons of CO2eq annually by 2030 through Nationally Determined Contribution (NDC) to UNFCCC. Among many policies, mass transit system and transit-oriented development are being developed with the expectation to reduce energy consumption and GHG emissions in Riyadh. To what extent such initiative can reduce energy consumption and GHG emission is an important question. In this paper, a methodology to systematically measure the impact of mass transit and transit-oriented development in Riyadh city on the energy demand has been developed. For Riyadh, a comprehensive travel demand model considering the impact of mass transit and transit-oriented development is still missing. To this end, this paper aims to fill the gap. This methodology considers the state-of-the-art in travel demand analysis and the local context by combining traditional four-step model and activity-based model for modal-shift. This paper describes the methodology and its application for Riyadh by analyzing modal-shift only between car and metro. The results suggest that metro can reduce energy consumption, but the reduction varies with varying accessibility, car, and metro situations. At high urban density and higher car travel cost, we may achieve as high as 13% reduction in fuel demand.
Abhishek Gupta, Connor Wright, Marianna Bergamaschi Ganapini
et al.
This report from the Montreal AI Ethics Institute covers the most salient progress in research and reporting over the second quarter of 2021 in the field of AI ethics with a special emphasis on "Environment and AI", "Creativity and AI", and "Geopolitics and AI." The report also features an exclusive piece titled "Critical Race Quantum Computer" that applies ideas from quantum physics to explain the complexities of human characteristics and how they can and should shape our interactions with each other. The report also features special contributions on the subject of pedagogy in AI ethics, sociology and AI ethics, and organizational challenges to implementing AI ethics in practice. Given MAIEI's mission to highlight scholars from around the world working on AI ethics issues, the report also features two spotlights sharing the work of scholars operating in Singapore and Mexico helping to shape policy measures as they relate to the responsible use of technology. The report also has an extensive section covering the gamut of issues when it comes to the societal impacts of AI covering areas of bias, privacy, transparency, accountability, fairness, interpretability, disinformation, policymaking, law, regulations, and moral philosophy.
Distributionally-robust optimization is often studied for a fixed set of distributions rather than time-varying distributions that can drift significantly over time (which is, for instance, the case in finance and sociology due to underlying expansion of economy and evolution of demographics). This motivates understanding conditions on probability distributions, using the Wasserstein distance, that can be used to model time-varying environments. We can then use these conditions in conjunction with online stochastic optimization to adapt the decisions. We considers an online proximal-gradient method to track the minimizers of expectations of smooth convex functions parameterised by a random variable whose probability distributions continuously evolve over time at a rate similar to that of the rate at which the decision maker acts. We revisit the concepts of estimation and tracking error inspired by systems and control literature and provide bounds for them under strong convexity, Lipschitzness of the gradient, and bounds on the probability distribution drift. Further, noting that computing projections for a general feasible sets might not be amenable to online implementation (due to computational constraints), we propose an exact penalty method. Doing so allows us to relax the uniform boundedness of the gradient and establish dynamic regret bounds for tracking and estimation error. We further introduce a constraint-tightening approach and relate the amount of tightening to the probability of satisfying the constraints.
Beck E. Strauss, Schuyler R. Borges, Thea Faridani
et al.
Gender equity remains a major issue facing the field of planetary science, and there is broad interest in addressing gender disparities within space science and related disciplines. Many studies of these topics have been performed by professional planetary scientists who are relatively unfamiliar with research in fields such as gender studies and sociology. As a result, they adopt a normative view of gender as a binary choice of 'male' or 'female,' leaving planetary scientists whose genders do not fit within that model out of such research entirely. Reductive frameworks of gender and an overemphasis on quantification as an indicator of gendered phenomena are harmful to people of marginalized genders, especially those who live at the intersections of multiple axes of marginalization such as race, disability, and socioeconomic status. In order for the planetary science community to best serve its marginalized members as we move into the next decade, a new paradigm must be established. This paper aims to address the future of gender equity in planetary science by recommending better survey practices and institutional policies based on a more profound approach to gender.