Papers

AI-moderated interviews are emerging as a scalable market-research method for generating consumer insights and building consumer "digital twins." Yet it remains unclear whether they match human-moderated interviews or improve on simpler, static data collection methods. In a pre-registered, between-subjects study (N = 317) with three industry partners, we compare AI-moderated (N = 139), human-moderated (N = 24), and static interviews (N = 154). AI moderation matches human moderation in depth, covers more themes, and, holding budget constant, recovers significantly more customer needs than human moderation or static interviews. However, participants sound more emotionally engaged when speaking to a live human. We then create digital twins using interview data and evaluate each twin against the participant's own held-out responses to six real-world marketing stimuli. We find that digital twins created from AI-moderated interviews predict consumer responses better than demographics-only personas. However, the additional richness from AI moderation does not translate into better quantitative predictions compared to static interviews. By analyzing open-ended thoughts generated from humans versus their twins, we find that prediction errors are connected both to differences in (self-reported) thinking styles between twins and humans, and to gaps between training and validation data (i.e., asking questions that are too far out of distribution).

National-scale digital health platforms generate usage data that reveal population healthcare needs. MediVerify, Sri Lanka's online medicines information platform providing access to National Medicines Regulatory Authority (NMRA)-approved medicines, recorded over 1.49 million queries in its first year. Large-scale medicine search behaviour in low- and middle-income countries (LMICs) remains poorly characterised. Objectives: To characterise medicine information-seeking behaviour, identify mismatches between public demand and essential medicines policy, and evaluate technical performance. Methods: We retrospectively analysed 1,497,304 anonymised queries submitted between July 2024-2025. Queries were normalised and mapped to 11,933 approved medicines using fuzzy matching based on Levenshtein distance (threshold <=5). Therapeutic categories were assigned using an Anatomical Therapeutic Chemical (ATC)-aligned classification. Query patterns and system performance were analysed, and energy consumption was estimated from processing times. Results: Vitamins/minerals (11.74%), antibiotics (10.57%), anti-diabetes (7.02%), and antihypertensives (6.84%) dominated searches. The top 20 accounted for 37.3% of queries, while approximately 40%-50% of registered medicines were never queried. Zero-result queries (~ 1%) indicated unmet information needs. Frequently searched medicines diverged from essential medicines lists. Median latency was 8ms, with >99% query resolution. Estimated energy consumption was approximately 0.12 kWh per million queries. Conclusions: Large-scale medicine search data provide insights into healthcare information demand and policy alignment. MediVerify demonstrates that a national digital health platform can achieve high utilisation at low computational and environmental cost. Usage analytics could strengthen pharmaceutical policy and digital health infrastructure in LMICs.

Frame refresh rate estimation is a fundamental step in identifying compromising harmonic frequencies in electromagnetic side-channel attacks. Methods based on discrete linear autocorrelation (DLA) are robust across different scenarios and require a computational complexity of $O(N\log N)$ for a signal containing $N$ samples. This work proposes reducing this complexity to $O(N)$ by exploiting prior knowledge of the target system's display resolution, as is available for certain models of the Brazilian electronic voting machine. Experiments using software-defined radios show that the proposed method preserves the accuracy of the conventional approach in the evaluated scenarios.

Societies worldwide are described as increasingly polarized, yet issue polarization – how divided a society is over political positions – has been measured almost entirely on a single left-right axis developed in Western democracies. Whether that axis describes political division elsewhere is largely untested, because no survey measures political attitudes on multiple dimensions across many countries. Here, we harmonize 1,299 items from nine cross-national survey programs and 23 national election studies to place 1.14 million people from 141 countries on four dimensions: social liberalism, economic left-right, democratic commitment, and anti-elite sentiment. A single left-right axis does not describe political division in most of the world. The median within-country correlation between a person's social and economic positions is -0.015. Societies differ instead in what they are divided about, and they do so by region. European countries divide most often over social liberalism, East Asian and Arab countries over democratic commitment, Latin American countries over economic left-right, and African countries over anti-elite sentiment. Of the 81 countries measured on all four dimensions, 39 are most divided on a dimension no left-right scale would capture. Most political disagreement lies within countries rather than between them, at 58 to 88 percent of the variance. Ideological constraint, long treated as a property of mass publics, holds in nineteen of the eighty-three we can test, most strongly in the United States at +0.70, and there it is concentrated among the politically attentive. Understanding political conflict therefore requires asking not how polarized a society is but what it is polarized about. Our released item bank and fitted parameters place respondents from any future survey on the same scale without re-estimation, once that survey's items are harmonized to the bank.

AI-generated summaries are increasingly used in high-stakes settings, like policing, despite considerable evidence that AI often generates misleading or inaccurate information. This research asked: do errors in AI-generated summaries distort human memory? To answer this question, we adopted two methodological approaches. First, we conducted an analysis of AI summary output, prompting large language models to generate summaries of videos. This analysis quantified how often AI summaries contain errors and the categories of these errors, revealing the kinds of misleading information that may distort human memory. Second, we conducted a human-subjects experiment to test the impact of misleading information in AI-generated summaries on human memory. Participants were first exposed to an event via watching a video of a car-pedestrian accident, and later read an AI-generated summary describing the video that either contained misleading or accurate information. Participants' memory for the original event was assessed in a memory recognition test. In the AI analysis, we found a high frequency of mistakes in AI summaries, and particularly frequent omissions of critical details. For instance, the majority of summaries omitted the most central event of the video, a critical error which is likely to be impactful. We also observed a strong effect of AI misinformation on human memory. People who read a misleading AI summary were significantly less likely to accurately recall the original event, compared to people who read an accurate AI summary. These findings have implications for how AI should be used in critical settings. Though "humans-in-the-loop" are often expected to correct for AI's mistakes, our work suggests human memory can instead be distorted by these mistakes. AI has the potential to generate misinformation, even absent any adversarial intent, which can meaningfully impact human memory.

The ongoing digital transformation of work, administration, health, mobility, and social interaction is profoundly reshaping everyday life, steadily shifting control from individuals to large platform providers. Although data is often labeled the "gold of the 21st century", its real value is realized through services that access, combine, and exploit it. Today, individuals have little sovereignty: life events (e.g., changing an address, insurance, job, or marital status) require fragmented, repetitive interactions across numerous systems, leaving users overwhelmed rather than empowered. We argue for a fundamental rethinking of this situation and propose a virtual, trustworthy platform, called "MyVirtualME" that acts on behalf of the human individual towards companies, administrations, and other actors. This platform centers services, data, permissions, and data usage around humans, not foreign actors, allowing genuine control and transparency. Our vision goes beyond a pure data focus: supported by trusted services ranging from basic notifications to intelligent assistants, MyVirtualME aims to reduce digital bureaucracy, improve and even automate interactions, and support informed oversight of an individual's health, financial, and administrative situation. We firmly believe that a human-centered MyVirtualME is essential for restoring personal sovereignty in our digital future.

Artificial Intelligence agents based on large language models provide convenient natural language interfaces to scientific software, but reliability is not automatic. Here we introduce the Epydemix Agent Framework, an additive layer over Epydemix, an open-source Python library for stochastic compartmental epidemic modeling. The framework extends the library with four capabilities to facilitate interaction with an AI agent: discovery of available models and parameters, preventive validation of a declarative scenario specification, execution through tested library code, and inspectability of results. These capabilities let an agent handle the entire modeling process, from the natural-language description of the scenario to quantitative results, figures, and interpretation of findings without writing custom code. Each step reads input files and saves results in a separate output bundle, making the process auditable and reproducible. First, we show the end-to-end workflow with a case study comparing vaccination strategies for a novel respiratory virus. Second, we assessed the framework across 50 agent sessions and five modeling tasks by comparing the agent use of the framework against the direct use of the Python interface. The framework reduced turns, output tokens, and cost on most tasks, unless it trades resources for per-point reproducibility.

Artificial intelligence offers an unprecedented opportunity to augment human capabilities, yet progress at the frontier has focused primarily on advancing model capabilities. We introduce StudentBench, a suite of AI teaching evaluations and a public platform that enables large-scale data collection with over 175,000 student-AI messages to study whether large language models (LLMs) produce learning gains equivalent to human tutoring. Using StudentBench, we measured learning gains on Quantitative and Verbal GRE questions across 2,383 human participants receiving AI tutoring, human tutoring, or no tutoring. We establish that AI tutoring is statistically equivalent to expert human tutoring for GRE learning gains (p = .015), and in five of the seven GRE domains, the best performing AI tutor surpassed the human tutor, on average. In a second study, expert human tutors compared LLM-generated lesson plans and practice problems through 2,028 pairwise rubric evaluations. Together, the two studies clearly separate AI tutors across: (1) lesson planning, (2) practice-problem creation, (3) conversational pedagogy, (4) cost, and (5) engagement. Surprisingly, one AI tutor achieved learning gains equivalent to human tutoring (p = .044) at 918 times lower cost (USD 0.0052 for AI versus USD 4.81 for human, per percentage point gained). For Quantitative GRE sessions, faster AI replies correlated with more student messages, more messages with more correct practice, and more correct practice with larger learning gains (all p < .002). To support future research, we open-source the de-identified data collected in our studies.

How news media frame and emotionally code a public health emergency shapes public risk perception and trust, yet outbreak-coverage dynamics remain understudied for low- and middle-income countries (LMICs). We examine sentiment and stance in English-language Bangladeshi coverage of the 2026 measles outbreak – the country's most severe in two decades, with over 97,000 suspected cases and 600 deaths across 61 of 64 districts, unfolding after the 2024 change of government and a 2024-2025 vaccine stockout. Using the Internet Archive, we build a reproducible corpus of 403 headlines from seven national outlets (396 in-window in 2026), label them for binary sentiment and four-way stance via a large language model under a locked codebook, and validate against a two-coder human-adjudicated gold standard (n=153; Cohen's kappa=0.89 stance, 0.75 sentiment). Aligned to the DGHS epidemic curve, coverage grew significantly more negative (56% to 88% negative; Cochran-Armitage z=4.12, p<.001) and risk-amplification framing intensified (44% to 84%; z=4.15, p<.001). Media negativity lagged incidence, tracking cumulative mortality. Contrary to the political backdrop, blame remained a minority frame (~9% overall) and was overwhelmingly systemic (32 of 37, 86%) rather than directed at named actors. The pipeline offers a scalable, transparent method for LMIC outbreak-media analysis; Bangladeshi coverage amplified threat far more than it assigned political blame.

This paper investigates the threat to ballot secrecy in the Brazilian electronic voting machine (UEB) posed by electromagnetic side-channel attacks, also known as TEMPEST attacks. In these attacks, screen content can be reconstructed remotely by intercepting electromagnetic emanations associated with the target device's video signal. This work is motivated by a recent ruling by a Brazilian electoral court concerning an attempt to violate ballot secrecy using electronic equipment. Based on publicly available information about the electoral system, attack scenarios against polling stations are proposed. Experiments using software-defined radio show that the effectiveness of TEMPEST attacks strongly depends on the lack of oversight resulting from public unawareness of the threat. Finally, awareness guidelines are proposed for voters, poll workers, and party representatives to mitigate attack risks within a polling station.

Increasing numbers of people now routinely interact with large language models (LLMs) across many aspects of life, including in the workplace, educational settings, and for personal activities. The pace at which these tools have been adopted across society in recent years has led to substantial shifts in the ways in which people approach tasks and access information and advice. As a result, it is important for researchers and policymakers to gain up-to-date evidence on how the public engages with these technologies, including what people typically use them for, the extent to which users trust the information and advice that LLMs provide, and how the public perceives the potential benefits and risks associated with their use. We surveyed a nationally representative sample of 2,002 adults in the UK. Participants were asked about their use of LLMs, including both practical applications and more personal and social forms of engagement, their trust in the information provided by these systems across a range of topics and compared with other common sources, and their attitudes towards the potential societal benefits and risks associated with these tools. Results show that while practical tasks remain the most common type of LLM use, many people now engage with these tools for personal support. Almost one third of regular users (31%) say they use LLMs for personal and emotional support, such as talking through problems and asking for help with decisions, while one quarter report interacting with LLMs for meaningful conversation. We also find that trust in LLM-generated information is relatively high, but that public attitudes towards LLMs are characterised by both optimism and concern. While over three quarters of our sample report feeling enthusiastic about the potential benefits of LLMs (77%), a majority also express concern about their potential risks (70%).

Educational technology (EdTech) platforms collect highly sensitive student data, including behavioral logs, disability records, and academic histories. However, privacy considerations are often postponed rather than treated as a foundational design requirement. We present a mixed-methods study combining 12 semi-structured interviews with EdTech professionals and a privacy policy audit of 48 platforms coded across five dimensions, with strong inter-rater reliability (mean Cohen's Kappa = 0.781). Our interviews reveal a recurring organizational pattern in which privacy is recognized as important but deferred across the product lifecycle as organizations prioritize product functionality, growth, funding, and immediate educational outcomes. Responsibility is often delegated to cloud providers, policy documents, or downstream institutions, while limited privacy-related feedback gives organizations little pressure to change these practices. The policy analysis reflects these patterns: platforms describe what data they collect relatively well but provide substantially less information about how that data is subsequently governed. Thirty-three percent make no meaningful Artificial Intelligence (AI) disclosure despite visible AI features, and 73% provide only generic accountability and breach-response language. K-12 platforms perform better on children's consent where regulation creates explicit requirements, but this advantage does not extend to AI governance or accountability. These findings suggest that meaningful improvement requires enforceable institutional and regulatory mechanisms rather than voluntary privacy commitments alone.

The widespread use of social media, particularly image- and video-based platforms, has turned them into key sources of both normative and informational content related to health and diet. This may contribute to the development of disordered eating behaviors or, potentially, eating disorders. This study uses mixed-methods analysis applied to 3129 YouTube videos about diet and weight loss in order to quantify the level of risk of low-quality information and heightened focus on the body image. We adapt three quality measurement frameworks from the literature – PRHISM, HONcode and SMEC – to the online video context, perform manual annotation of a sample of the data, and design an LLM content characterization pipeline to score the videos on the quality of their content and the focus on the human body. Surprisingly, we find that videos around personal storytelling and mindset & motivation are associated with higher-quality content, whereas supplement reviews (arguably more medically sensitive ones) are not. Further, the body-related mentions of weight measurement and negative body image are associated with an increased viewership, whereas the mentions of positive body image are associated with an increased engagement rate in terms of likes and comments, but not viewership. Worryingly, we find a cluster of videos categorized as "music" which promote the dietary supplements Mitolyn and the injectable weight loss drug Mounjaro. As video-based platforms grow in popularity, particularly among younger audiences, studies such as the one presented here are essential for developing empirically grounded tools to enhance the detection of harmful content and inform more effective moderation practices.

Researchers in industry and academia use synthetic survey respondents powered by large language models as substitutes for human samples. These synthetic populations require validation against real-world data, so researchers often address them using ad hoc comparisons with human surveys. Inspired by the intention-behaviour gap in behavioural science, we argue that these validations test the wrong thing for most applied cases where decision makers commission synthetic research to anticipate consequential behaviour. To address this problem, we propose a validation framework with two requirements. First, every validity claim must state its level of correspondence with human data: does the sample predict what the represented people do, which of four diagnostics (location, dispersion, response process and structure) does the validation address, and does the validation compare against experimental effects? Second, researchers must report validity claims for subgroups, since these groups are often the most affected by consequential decisions and aggregate accuracy hides their misrepresentation. Our validation framework operationalises three justice dimensions (distributional, procedural, and recognition) as measurable quantities and treats within-persona counterfactual experiments as a design that itself requires validation. We then apply the framework to electric vehicle charging tariffs, before closing with a reporting checklist that researchers can use to make convincing validity claims.

KITE queries a typed behavioral kernel once per unique state, then executes populations of any size from the table with event-keyed randomness and common random numbers. An expensive flagship model is reserved for sparse paired anchors that estimate intervention effects. Measured human-model discrepancy is propagated as shared error into every conclusion. Population-experiment cost thus scales with unique states and anchors, while uncertainty is governed by evidence about people rather than Monte Carlo noise. On Epstein experiments with 9,070 participants, anchors covering 1.7% of states reduced effect error by 41% (absolute MAE reduction 0.0125). On 37 held-out SocSci210 experiments, 0.5-1.5% anchor coverage raised captured decision gain from 0.27 to 0.39. The kernel passed content-fidelity criteria in all 15 new countries of a 16-country study. Shared discrepancy yielded retrospective coverage of 93% and 96% at nominal 80% and 90%, versus 29% and 36% from human sampling uncertainty alone. A million agents executed 20 tabulated steps in 0.9 seconds on a laptop. This architecture offers a route to screening candidate interventions before human trials, multi-country content audits, and uncertainty-aware policy comparison at the cost of a few thousand kernel calls with sparse flagship anchors. Property-specific evidence records connect each use to its validation scope, correction provenance, and uncertainty, making these applications auditable.

Citizens' assemblies are deliberative bodies intended to form a microcosm of the population. Organizers rely on quota-based stratification and must decide which attributes define resemblance to the public. Yet meeting every quota can still leave a dimension citizens value unrepresented. We study this attribute-selection problem in general-purpose and climate-focused assemblies through randomized conjoint experiments. We find that demographic attributes matter for perceived representation, but political alignment and context-specific attributes such as climate concern exert a stronger influence. When both are shown in a climate-focused setting, each remains influential, with political alignment having the larger estimated marginal effect. We also examine the omission of a relevant stratification attribute. Panels stratified on demographics, even with political alignment included, match the observed pool's climate-concern distribution no better than uniform random samples. These results suggest that representation on a relevant topic-specific attribute cannot always be recovered through correlated demographic or political quotas, and may therefore require explicit stratification. Finally, we ask whether representation preferences can be learned from the observed profiles. We compare predictive models, from simple, interpretable matching rules to a learned metric and a respondent-conditioned utility model. Both learned models predict choices for respondents excluded from training with substantial accuracy, revealing generalizable structure without fully capturing these judgments. Together, these findings guide attribute selection in citizens' assemblies: designers should consider political and topic-specific dimensions alongside demographics, avoid assuming correlated proxies protect omitted dimensions, and use predictive models to diagnose how profiles shape representation choices.

Secondary use of educational records is increasingly mediated by platforms that share a differentially private synthetic version of a dataset and validate specific findings against the real data on request. The synthetic version is evaluated by comparing summary statistics of each variable, yet reported confirmation rates suggest that such comparisons do not predict which findings survive. We propose a structural check: the number of connected components of a weekly proximity graph over learners, tracked across a term. Across four annual cohorts of lower-secondary study-habit logs, the synthetic versions reproduced the level of this quantity and the shape of the weekly partition, but its variation across the term was between 2.6 and 4.9 times smaller than in the real data at a common working point, without exception, and those changes fell in different weeks: the synthetic cohorts single out the term's examination weeks and the real cohorts do not. We also show that a routine rule for setting the graph threshold makes naive comparisons between two datasets invalid, and illustrate this with an error of our own. The real curves are also distinguishable from marginal-preserving surrogates of themselves in all four cohorts, where three of the four synthetic ones are not, a comparison that needs no real data; these differences trace to what the generator was given.

Generative artificial intelligence (GenAI) is increasingly described in higher education as a tool, collaborator, evaluator, proxy, and infrastructure. These labels are not neutral: they shape who is seen as acting, knowing, and, crucially, being answerable when someone uses AI. This study examines how scholars distribute such responsibility across 366 English-language titles and abstracts published between November 2022 and 14 August 2026. A corpus-assisted discourse analysis combined frequency counts, five-word collocations, actor-predicate associations, obligation-clause coding, and heuristic analysis of passives, nominalisations, and reporting metonymies. The final corpus contained 91,405 tokens, drawn from 8,734 unique records screened after deduplication. AI was the most frequently named actor, appearing 2,050 times and entering 447 predicate associations, most involving action. Students, by contrast, were more often associated with knowing, judging, and verifying, yet no sentence ever made AI explicitly responsible. Responsibility fell largely on educators, institutions, and policy, or disappeared through passive and nominalised constructions. Even frequent phrases such as "responsible AI" and "responsible use" rarely identify who is accountable for what. The findings reveal a persistent gap between giving AI functional agency and assigning normative accountability.

In recent years, disinformation has increasingly proliferated across social networks. The firing of fact-checkers from Meta and the disbanding of Twitter's Trust and Safety Council suggest that this trend will continue to escalate. While disinformation sources (e.g., social network accounts) can sometimes be identified, new accounts emerge daily, making tracking a moving target. In this work, we propose a graph-based methodology to discover previously unknown Telegram accounts that spread disinformation. Starting from a set of verified disinformation groups, we examine their interconnections and identify new accounts that contribute to the dissemination of false narratives. Our approach is language-agnostic, as it relies solely on structural relationships between accounts rather than analyzing their message content. Using this approach, we identify 37 previously unknown disinformation channels (a threefold increase). We demonstrate that Telegram channels display extremely dogmatic behavior with up to 80% of messages being labeled as propaganda. Our findings reveal that misinformation on Telegram spreads within tightly interconnected clusters, in some cases, with over 86K identical messages being shared to multiple channels, suggesting coordinated disinformation campaigns.

This study introduces a dual-matrix computational architecture to mathematically quantify the morphological and theological divergence of 196 Hindu and Vajrayana Buddhist esoteric deities. Physical morphology is evaluated via a discrete Gower distance matrix enhanced by a novel "Cardinality Weighting" algorithm, while theological function is mapped via dense vector embeddings generated from Large Language Model (LLM) semantic expansions, explicitly utilized as a synthetic proxy to mitigate circular reasoning. The multi-modal topological projections provide algorithmic validation of "iconographic camouflage", demonstrating how distinct visual forms structurally obscure shared cross-tradition functions. Furthermore, I computationally model the "Atin Effect" - serving simultaneously as a psychological observation of sequential cognitive bias and a machine learning benchmark - demonstrating how high-cardinality esoteric anchors (e.g., a veena or a severed head) override systemic theological disparities to mathematically cluster orthodox and Tantric entities. Cross-tradition spatial analysis establishes that the highest esoteric manifestations, such as the Hindu Chinnamasta and the Buddhist Chinnamunda, share a near-identical mathematical coordinate across both visual ($D_G = 0.288$) and semantic ($D_C = 0.068$) boundaries, indicating a 1:1 esoteric transfer. By open-sourcing this architecture, I provide a scalable, unsupervised machine learning tool for Digital Humanities scholars and comparative theologians to rigorously map latent structural continuities across qualitative cultural corpora.

This paper presents a multi-source classroom study conducted during a 10-week quarter in data science courses at Drexel University. We first investigate the behaviors of student engagement with large language models (LLMs) using four surveys across three data science courses. Second, we evaluate the construct validity of multiple-choice questions (MCQs) generated by an LLM for in-lecture retrieval practice. Based on 378 authored questions (311 deployed, producing 7{,}888 student responses), we analyze whether the difficulty ratings assigned by an LLM match empirical item difficulty. Our study shows that student engagement with LLMs varied across courses and increased over the term. Although students expressed high satisfaction and reported saving considerable time, their perception of deep learning benefits declined, and many noted a tendency toward over-reliance. Regarding the difficulty ratings of LLM-generated MCQs, the Easy, Medium, and Hard labels correlated closely with its assigned Bloom's Taxonomy levels (Spearman $\rho=0.90$), reflecting an artifact of co-generation. However, neither metric predicted empirical item difficulty (difficulty label $\rho=0.06$; Bloom level $\rho=0.02$). The ratings reflect the structural formatting of a question rather than its underlying difficulty.

Large language models have enabled rapid deployment of language classification and analysis, allowing users to describe complex constructs in natural language, such as pedagogical moves or expressions of learning and engagement, and label them in conversational datasets such as classroom or tutoring transcripts. However, because LLM reasoning is opaque, we have no verifiable, mechanistic insight into why a model chose a label for an utterance, and output differences over time or across models challenge replication. We introduce the EduBehaviors framework to generate interpretable, reliable, and scalable construct annotations in educational dialogue data that retain human agency while leveraging the strengths of generative AI, encoders, and machine learning models. We evaluate the framework on the TalkMoves dataset, predicting the Teacher TalkMoves labels. Our best configuration results in a macro-F1 of 0.764 and 0.756 Cohen's kappa, demonstrating improvements over direct prompting approaches and showing competitiveness with fine-tuned classifiers while gaining the benefit of greater transparency and comparability. To facilitate adoption and operationalization of the EduBehaviors framework in educational dialogue data by other researchers, we also release the EduBehaviors Toolkit with two complementary open-source tools based on the TalkMoves application.

We describe deploying imaging AI at six hospitals through PACS-AI, an open self-hosted platform. The binding constraint is not model accuracy but infrastructure to route studies, display results, capture feedback, and audit what runs. At one center, angiography models completed 515 of 607 jobs (84.8%); failures reflected absent diagnostic views, and 78.1% of 638 clinician ratings were positive. Publishing honest readiness levels for every model is itself a governance practice.

Providing students with experience from chip specification to fabricated silicon can strengthen chip-design education, but integrating tapeout into regular teaching is difficult to scale, especially across universities with different curricula, schedules, regulations, and technical infrastructures. This article discusses the implementation experience and lessons learned from a cross-university approach developed within the Edu4Chip European project. The approach combines aligned learning outcomes, local Master's implementations, and a shared design-to-silicon framework across five European universities.

Fairness audits in production ML typically occur once, at deployment, on a single domain. Both fail in practice: fairness can shift after retraining or a changing user base, and interventions validated on one dataset are rarely tested across the heterogeneous domains an organization deploys. We present FAPE (Fairness Auditing for Production Environments), a four-stage framework evaluating a single post-processing intervention, Fairlearn's ThresholdOptimizer, across eight domain evaluations: criminal justice, income prediction, legal admissions, credit lending, agricultural lending, a multi-domain benchmark corpus, healthcare, and education. Each is scored on demographic parity and equalized odds difference, plus disparate impact ratio and accuracy cost where computable. Intervention effectiveness tracks baseline disparity magnitude: across model-domain pairs the constraint improved disparity in 9 of 14 high-disparity cases and worsened it in 3 of 4 near-fair ones. Each of the five high-disparity exceptions reverses under one of two measurement checks, a minimum group size or thresholds fit on held-out data. A CUSUM monitor started at deployment, tested on a simulated shift, separates constrained models that never met a 0.1 parity convention from those that met it and later regressed. A single deployment-time audit is therefore an unreliable guide, which argues for baseline-disparity screening and continuous monitoring

Judicial reasoning remains challenging for large language models (LLMs) to analyze. This paper contributes a sentence-level benchmark for evaluating the ability of LLMs to classify interpretive canons as articulated by Larenz in the tradition of Savigny. Our contributions are threefold. First, we operationalize this conception of interpretation as classification criteria. Second, we provide a dataset of decisions of the German Federal Constitutional Court annotated at the sentence level. Third, we report baseline evaluations of four LLMs from three model families under expert hand-written prompts, compared against prompts optimized with Genetic-Pareto (GEPA). Mean F1 over the seven binary subtasks clusters between 70.4 and 79.2 across models, with grammatical interpretation usually the easiest canon to identify and systematic interpretation usually the hardest; under the tested configuration, GEPA-optimized prompts do not systematically outperform the hand-written ones, suggesting that the expert prompts provide a meaningful baseline.

Sustainability disclosure in the European Union has so far focused on corporate reporting and sustainability information attached to traditional financial products. Crypto-assets, with consensus-mechanism-driven environmental externalities and fragmented issuer structures, largely fell through this disclosure architecture. The EU Markets in Crypto-Assets Regulation (MiCA) introduces the first EU-wide, asset-class-specific sustainability disclosure regime for crypto-assets by mandating standardised sustainability indicators for both issuers and crypto-asset service providers. Drawing on a policy and legal analysis of MiCA and its Level 2 measures, and on early implementation evidence from public registers and market practice, this paper shows how the policy approach shifted from debates about restricting energy-intensive consensus mechanisms to a transparency regime built on quantitative metrics, machine-readable reporting, and methodological alignment with the broader EU sustainable-finance framework. The paper also highlights practical frictions in implementation, including data gaps, responsibility allocation between issuers and intermediaries, and cross-border supervisory fragmentation. The overview and quantitative summary of the ESMA Interim MiCA Register in this paper may also provide valuable information to regulators and market participants in the context of the European Commission's 2026 targeted consultation on the review of MiCA, including its specific question on environmental and sustainability reporting.

People hold diverse, sometimes conflicting values, so no single aligned model can satisfy everyone. Pluralistic alignment therefore calls for steerable models that can balance competing objectives differently. Multi-Objective Direct Preference Optimization (MODPO) does this by using an objective weight to span a continuum of trade-offs. We study two questions: when can one model improve two objectives simultaneously, and how can many trade-offs be covered without training a separate model for each? Across seven objective pairs from HelpSteer and UltraFeedback, two pre-training measurements predict whether objectives align or conflict for human-annotated data, but not for AI-annotated data, where response length and repetition confound reward-model scores. For broader trade-off coverage, selecting the nearest trained model and merging model parameters both help, but neither consistently matches direct training. These findings yield practical guidance for building steerable models that serve diverse preferences.

The objective of this article is to provide design principles and a software architecture for enabling interaction between humans and multiple agents in simulated dynamic worlds. This connects the current era of general artificial intelligence (AI/AGI) with the proliferation of transformer-based conversational agents and the increased computational capabilities. Given an overview of current and previous multi-agent theories of mind (socially and affectively-aware agents), the existence of an integrative design of agent interactions with themselves and with humans must be crucial for understanding how to create sustainable and governance in future human-agent reasoning systems. In this work is presented a software "AGIMUD" that integrates: A. socially-aware reasoning and emotion in agent behavior and interaction, B. a design of human multimodal scheme for human users, artificial agents and simulated worlds, and C. distributing the AI processing through the network to enable multiple autonomous agents. These integrations allow the dynamic world recreation as multi-user dungeons (MUDs) where both agents and humans can interact simultaneously in real time. Find the code online in https://github.com/dberga/AGIMUD.

Conversational AI systems can pose safety risks to their users such as hallucination, sycophancy, overconfidence, and anthropomorphism, but these risks are difficult for users to detect during everyday use. We introduce Safety Nudges, a browser-based tool that provides lightweight, in situ flags when concerning behavior is detected in chatbot conversations. We evaluated Safety Nudges in a two-week field study with 45 frequent chatbot users, collecting interaction logs, surveys, and feedback on individual nudges. Participants found the tool useful, clear, and minimally disruptive, with nearly all users reporting an increased awareness of potential AI harms, though we found that this improved awareness alone did not necessarily lead to discernible behavioral changes. Our results suggest that user facing safety nudges can complement model-level safeguards by helping people critically evaluate AI responses in context, while highlighting the importance of relevance, calibration, and user control in nudge design for conversational AI safety. The code for our Safety Nudges extension is publicly available at https://github.com/jtbwedgwood/safety-nudges.