Computers and Society Papers@WGOV
Oct 30
The Price of a Chance in Artificial Societies

Shuqi Zhao, Boyu Wang, Shuangyue Niu, Chenhao Zhang, Zhanzhan Zhao
arxiv.org/abs/2610.40259 [𝚌𝚜.𝙲𝚈]
Rapid advances in large language models (LLMs) have enabled autonomous agents to interact, coordinate, and pursue individual goals in artificial societies. However, our understanding of how reward structures shape their competitive behavior and collective outcomes remains incomplete. We simulate 200 LLM agents competing over 50 rounds to maximize individual wealth. We define overcompetition and lying flat as population investment above and below a Bayesian adaptive baseline, respectively. At the lowest tested reward, populations lie flat; at the two highest, they overcompete, most strongly at intermediate winner coverage. The investment committed to pursuing an uncertain reward constitutes the price of a chance. Agents near the qualification cutoff can invest heavily yet receive no prize, finishing poorer than nonwinners who invest less. Agents' stated rationales link investment decisions to perceived qualification prospects and expected returns. At the collective level, greater invest
0
0
0
16
Computers and Society Papers@WGOV
Oct 30
Measuring Organizational Influence on Digital News: An Information-Theoretic Framework for Media Pluralism and Editorial Independence

Peter Carragher, Kathleen M. Carley
arxiv.org/abs/2610.40172 [𝚌𝚜.𝙲𝚈]
News consolidation is accelerating, yet regulators have no measurement frameworks for determining whether owners shape editorial decisions. Existing evidence comes from single cases, where pluralism and independence are measured separately, if at all. We ask whether ownership impacts editorial decisions across the digital news ecosystem, and if so, how acquisitions affect this. We derive editorial independence and internal pluralism using partial information decomposition, which separates news coverage overlap with sister outlets from coverage overlap with all outlets. Using public datasets, we apply our measures monthly from 2018 to 2026 to 1,364 US news websites on three editorial decisions: which events they cover, which sources they link to, and what they put on their front pages. We find that co-owned outlets share up to 40 times more information about these decisions than expected by chance. Ownership accounts for far more variation in independence than network affiliation does a
0
0
0
27
Computers and Society Papers@WGOV
Oct 30
Who Owns Digital News, and Who Gets Cited: Measuring Media Concentration Across 77 Countries and Seven AI Systems

Peter Carragher, Kathleen M. Carley
arxiv.org/abs/2610.40164 [𝚌𝚜.𝙲𝚈]
Digital news outlets compete for audience attention. Search engines equipped with generative AI systems such as Google's AI overviews increasingly decide where that attention goes, as well as the revenue it represents. Yet, the lack of a consistent data collection infrastructure between national-level regulatory bodies has hindered between-country comparative analysis of media concentration, and with it any assessment of how these intermediaries reshape digital news markets. To address this issue, we compile an ownership dataset for 9,761 digital news outlets drawn from Wikipedia and Wikidata, achieving high agreement with independently compiled US and UK news directories. Using this dataset, we derive traffic-weighted concentration indices for 77 countries. We find that journalists report more owner pressure in countries with higher concentration, and that outlet-level measures understate concentration, with owner-level indices a median 1.30x higher. Applying concentration measures to
0
0
0
23
Computers and Society Papers@WGOV
Oct 30
Reconstructing Missing Mandi Prices in North-East India with Regional Factors

Pritam Deka
arxiv.org/abs/2610.39949 [𝚌𝚜.𝙲𝚈]
Agricultural price panels contain prolonged and clustered reporting gaps, yet their reconstruction is often evaluated by deleting isolated observations. We investigate a regional-factor approach to weekly mandi-price reconstruction in five North-East Indian states, with Bihar and Goa as additional comparison states. The model combines a common price path with persistent market-specific deviations; an adaptive ensemble weights alternative borrowing structures using internally masked reports. On a matched retrospective benchmark against ten baselines, pooled North-East mean absolute percentage error is 19.3%, compared with 26.5% for SAITS. The corresponding calendar-aligned panel/time-block bootstrap interval for the error difference is 2.8-12.7 percentage points. Removing the target state's monthly aggregate leaves pooled error at 19.4%, but eliminates the apparent advantage in Goa. An origin-restricted pipeline combining week-close input processing with revised ensemble validation yiel
0
0
0
17
Computers and Society Papers@WGOV
Oct 30
TokWatt: an open, boundary-annotated database of AI inference energy, from chat answers to agents

Abderaouf Bahi
arxiv.org/abs/2610.39846 [𝚌𝚜.𝙲𝚈]
Electricity supply is becoming a binding constraint on the deployment of artificial intelligence (AI), yet public evidence on the energy used by a single AI task is scattered and hard to compare. Published figures for one chatbot answer differ by two orders of magnitude, largely because studies count different parts of the system and measure different units of work. We present TokWatt, an open database of 134 published estimates of AI inference energy drawn from 13 sources (2023-2026) and covering 20 tasks, from classic machine-learning inferences to chat answers, reasoning answers, long-document queries, image and video generation, and coding agents. Each estimate records its functional unit, five measurement-boundary components, method, reported interval, and the location of the value in its source. A reproducible procedure scales estimates to a common server-plus-facility boundary and derives per-task reference values with ranges. The reference values span six orders of magnitude: 0
0
0
0
12
Computers and Society Papers@WGOV
Oct 30
Device-Induced Mobility Heterogeneity and Its Impact on Federated Next-Location Prediction

André Felipe Zanella, Paula Delgado de Santos, José Suárez-Varela, David Solans Noguero, Andra Lutu, Jesus Omaña-Iglesias
arxiv.org/abs/2610.39791 [𝚌𝚜.𝙲𝚈 𝚌𝚜.𝙽𝙸]
Predicting human mobility is central to network management, urban planning, and location-based services, yet privacy concerns are increasingly pushing such tasks toward federated learning. A key challenge in this setting is the strong heterogeneity of mobility data across users, which leads to non-IID data distributions and can significantly impact model performance and fairness. In this paper, we present a large-scale measurement study of device-level mobility heterogeneity using data from a major MNO in a dense European capital. Our dataset comprises mobility traces derived from network events, covering over 50,000 UEs across 178 smartphone models. We group devices into tiers based on their market segment and show that mobility characteristics, such as spatial range and regularity, vary systematically across these tiers, revealing a previously underexplored source of bias in mobility data. We investigate the implications of this heterogeneity on the use case of federated next-locatio
0
0
0
21
Computers and Society Papers@WGOV
Oct 30
GPU-Resident Speculative Decoding for In-Browser LLM Inference with WebGPU

Wei Song, Yuxin Cao, Ziqi Ding, Xiao Cheng
arxiv.org/abs/2610.39761 [𝚌𝚜.𝙲𝚈]
WebGPU enables private, offline LLM inference inside web pages, but browser dispatch, inter-process communication, synchronous readback and single-token kernels slow decoding and make conventional speculative decoding inefficient. We present a WebGPU runtime that addresses these browser-specific costs. Deterministic small-batch integer kernels accelerate multi-token verification while preserving exact agreement with greedy decoding in the same quantized runtime. A GPU-resident loop performs drafting, verification, acceptance and KV-cache maintenance without a per-token CPU decision. A draft-free context-mixing drafter reuses page content, conversation history and session memory, while a device-aware controller adapts the speculation width and the submission window to measured costs. Across seven models from 0.5B to 8B parameters, 11 tasks and three client GPUs, our runtime decodes 3.5 to 5.4× faster than WebLLM on a laptop GPU, 4.8 to 6.2× faster on an integrated GPU and 4.8 to 8.6× fa
0
0
0
55
Computers and Society Papers@WGOV
Oct 30
Data Provenance and Ethics in the Curricula of U.S. Health AI Education Programs

Raffaele Giancotti, Francesca Santucci, Amama Anjum, Monique de Villa, Rupsa Mitra, Soham Biren Katlariwala, Vishala Mishra, Leo Anthony Celi
arxiv.org/abs/2610.39606 [𝚌𝚜.𝙲𝚈 𝚌𝚜.𝙰𝙸]
Failures of deployed clinical artificial intelligence (AI) systems have often originated in how their training data were generated. Whether the programs that train the health AI workforce teach practitioners to examine data provenance is unknown. We conducted a cross-sectional analysis of the publicly advertised curricula of health AI education programs at U.S. universities, identified through a structured multisource web search between April and July 2026. Two investigators coded coverage of data provenance (structural, dataset limitations, or data management only), ethics, and sustainability; collaborative structure; technical prerequisites; and the disciplinary background and gender of named instructors. The primary outcome was provenance coverage at the structural or dataset-limitations level. Of 43 candidate entries, 36 programs at 25 institutional units in 21 universities were included. Ethics was covered by 29 programs (80.6%; 95% confidence interval [CI], 65.0 to 90.2), data pr
0
0
0
25
Computers and Society Papers@WGOV
Oct 30
Student-LLM Interactions During Math Learning: Limited Epistemic Proactivity Overall, but Within-chat Change Predicts Performance Without AI

Rania Abdelghani, Peter Kaiser, Kou Murayama
arxiv.org/abs/2610.38950 [𝚌𝚜.𝙲𝚈]
Large language models (LLMs) are increasingly used for learning, raising a key question: can learners remain epistemically proactive, retaining responsibility for the cognitive and regulatory activities through which learning is produced while working with AI? Because this responsibility may change as interactions unfold, we examine epistemic proactivity as a developing process. We conceptualize epistemic proactivity through self-regulated learning (SRL) moves, complemented by help-seeking strategies and manifestations of epistemic vigilance. We analyzed these behaviors in 880 substantive turns from 112 secondary-school students completing open-ended mathematical-modeling practice with a general-purpose LLM (Mistral). Overall, students showed limited observable epistemic proactivity: their interactions were strongly request-dominated, with planning, monitoring, and evaluation relatively rare, although low-quality AI responses elicited more explicit evaluation. Temporal analyses qualifi
0
0
0
10
Computers and Society Papers@WGOV
Oct 30
TrussTutor-Bench: Benchmarking large language models on solution accuracy, sycophancy, and error detection in statics

Evangelos Apostolakis, Erfan Hamdi, Sara Jahedazad, Emma Lejeune
arxiv.org/abs/2610.38917 [𝚌𝚜.𝙲𝚈 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]
💬Code: github.com/elejeune11/Tru…
Large language models (LLMs) have rapidly become a default source of help for students in science and engineering courses. In foundational engineering mechanics courses such as statics, students routinely use these tools to check answers, work through partial solutions, and ask for explanations. Effective tutoring in this setting requires more than a correct final answer. A model must also confirm correct work when a student doubts it, and identify errors in flawed work. Existing benchmarks evaluate LLMs primarily on final-answer accuracy, so it is unclear whether models that can solve mechanics problems also have the other technical capabilities that tutoring depends on. Here we introduce TrussTutor-Bench, a benchmark of 200 verified two-dimensional truss problems paired with automatically generated student solutions, and use it to evaluate thirteen LLMs on solution accuracy, sycophancy, and error detection. Baseline accuracy ranged from 64.5% to 97.0%. Every model detected nearly all
0
0
0
17
Computers and Society Papers@WGOV
Oct 30
Measuring the Inaccessible: Can AI Evaluate Accessibility in Heritage Tourism?

Sabrina Armenio, Manuele Leonelli
arxiv.org/abs/2610.38642 [𝚌𝚜.𝙲𝚈]
Accessibility assessment underpins the right to participate in heritage tourism, yet evaluation of archaeological sites remains artisanal: fieldwork does not scale, is often carried out without accessibility training, and is reported in forms that reach neither the sector nor disabled visitors. AI appears to offer a shortcut. We argue that assessment is measurement and inference under sparse, expert-mediated evidence: AI transforms how that evidence is captured and communicated, whereas evaluation, which turns evidence into defensible judgements, demands properties current generative systems lack. In a five-park field study in Spain and Italy, an AI desk audit scored only 66% of dimension-site combinations, could not observe embodied and organisational dimensions, and mirrored sites' online self-presentation. Simple Bayesian models instead quantify the confidence rankings deserve and calibrate desk evidence against fieldwork. We propose a separation of roles between AI and interpretabl
0
0
0
25
Computers and Society Papers@WGOV
Oct 30
The State of the Practice in Privacy Impact Assessments: Understanding the Professionals' Perspectives, Experiences, and Current Procedures

Samuel Wairimu, Leonardo Horn Iwaya, Ala Sarah Alaqra
arxiv.org/abs/2610.38543 [𝚌𝚜.𝙲𝚈 𝚌𝚜.𝙲𝚁]
Organisations frequently utilise Privacy Impact Assessments (PIAs), Data Protection Impact Assessments (DPIAs), or even Fundamental Rights Impact Assessments (FRIAs) to identify and evaluate potential risks and possible infringements of fundamental rights. While the adoption of PIAs and DPIAs has grown significantly in recent years, robust scientific evidence regarding their operational challenges, implementation strategies, and tangible benefits remains scarce. In particular, empirical research conducted post-enactment of the General Data Protection Regulation (GDPR) is notably limited – especially studies that directly interview professionals about their PIA/DPIA practices or their engagement with FRIAs. To do so, in this paper we leveraged semi-structured interviews to elicit privacy professionals' perspectives on PIA/DPIA activities and analysed the responses using reflexive thematic analysis. As a result, this work provides a comprehensive thematic framework for the field, offerin
0
0
0
11
Computers and Society Papers@WGOV
Oct 30
The Indian Financial Automated Advice Bias (IFAAB) Dataset: Auditing Socioeconomic and Demographic Disparities in LLM-Generated Financial Advice in India

Kriti Mahajan
arxiv.org/abs/2610.38239 [𝚌𝚜.𝙲𝚈 𝚌𝚜.𝙰𝙸]
Large language models are increasingly used for financial guidance, yet little is known about whether their advice changes across social identities in Global South contexts. We introduce the Indian Financial Automated Advice Bias (IFAAB) benchmark, a counterfactual audit dataset of 31,734 GPT-4o-generated financial-advice responses for synthetic Indian personas varying by gender, caste, education, employment, residence, age, and district. Holding the underlying request fixed, we evaluate disparities in LLM-implied wealth, income, savings, projected gains, textual similarity, advice topics, and qualitative bias judgments. In the gender-only audit, male-labelled profiles receive 60.1% higher initial total resources and 46.8% higher post-advice total resources than comparable female-labelled profiles; in the caste-augmented audit, the post-advice total-resource gap remains 49.4%. Adding district information reduces the aggregate post-advice total-resource gender gap to 7.9%, revealing str
0
0
0
22
Computers and Society Papers@WGOV
Oct 30
IKTRACE: A Natural Language Processing Framework for Identifying Indigenous Knowledge Representation in Academic Literature

Tara Azin, Christy Caudill, Mako Sorensen, Peter Pulsifer
arxiv.org/abs/2610.38186 [𝚌𝚜.𝙲𝚈]
As artificial intelligence systems increasingly rely on vast textual data, respectful and accurate representation of Indigenous Knowledge has become critical. This paper introduces IKTRACE, a natural language processing framework for identifying, analyzing, and organizing Indigenous Knowledge representations in academic literature while adhering to Indigenous Data Sovereignty (IDsov) principles. We present a community-informed taxonomy co-developed with Inuit partners, comprising nine knowledge domains grounded in Indigenous Data Sovereignty principles. Building on this taxonomy, we implement a multi-method Knowledge identification pipeline using complementary natural language processing approaches. Outputs are integrated into a knowledge graph to support future expert and community validation. Applied to a corpus of Canadian Arctic research documents, IKTRACE demonstrated high accuracy and strong community relevance in expert validation. Our framework provides a scalable, ethically gr
0
0
0
35
Computers and Society Papers@WGOV
Oct 30
From the Gettier Machine to Justified True Output: A Three-Step Account of Rational Trust in Generative AI

Tevfik Uyar
arxiv.org/abs/2610.38112 [𝚌𝚜.𝙲𝚈 𝚌𝚜.𝙰𝙸]
As generative artificial intelligence (AI) settles into everyday practices of inquiry, an old epistemological question returns in a new guise: when does a proposition a user takes from an AI output become something the user knows, and when is it rational to trust it as such? This paper argues that the characteristic failures of AI-mediated inquiry are precisely those that the justified-true-belief (JTB) tradition and its post-Gettier anti-luck refinements were built to diagnose, and it advances three claims. First, AI outputs inherit neither the presumptive warrant of testimony nor the reliabilist warrant of deterministic tools: unaudited trust in a calculator rests on a type-level reliability record, and for general-purpose generative models there is no type-stable process to which such a record could attach – a practical form of the generality problem. Second, use that stops at obtaining an output turns generative AI into a Gettier machine: the user's fluency-based seeming of justifi
0
0
0
17
Computers and Society Papers@WGOV
Oct 30
From Needs Assessment to Legal-Digital Empowerment: A Community-Based Framework for Indigenous Enterprises in Higher Education Extension Programs

Marilou O. Espina, Sales G. Aribe, Mark Ian M. Mukara, Joseph L. Abella, …
arxiv.org/abs/2610.38030 [𝚌𝚜.𝙲𝚈 𝚌𝚜.𝚂𝙸]
IPOs contribute significantly to local economies, cultural preservation, and sustainable livelihoods within their ancestral communities. However, many IPOs remain marginalized in digital economies due to limited digital competencies, inadequate access to technology, and insufficient legal awareness related to online enterprise participation. This study examined the marketing practices, digital competencies, and legal-literacy needs of IPOs in the Philippines and developed a legal-digital empowerment framework for higher education extension and community engagement initiatives. Using a sequential mixed-methods design, data were collected through surveys and focus group discussions involving IPO members engaged in community-based enterprises. The study assessed existing marketing practices, identified competency and legal-awareness gaps, and determined capacity-building needs related to digital enterprise participation. Findings revealed that IPOs continue to rely heavily on traditional
0
0
0
13
Computers and Society Papers@WGOV
Oct 28
Extending the W3C Data Privacy Vocabulary to Cover the German Health Data Use Act - Lessons Learned

Julian Flake, Christian Henke, Alessandra S. Kuntz, Matthias Löbe, Harshvardhan J. Pandit, Christian Draeger
arxiv.org/abs/2610.37527 [𝚌𝚜.𝙲𝚈]
Finding, sharing, and reusing data requires common interoperable vocabularies to adequately describe machine-actionable data policies. Semantic Web standards are a proven way to express such information describing data access and reuse. Narrative descriptions get a stable and agreed meaning by formal definitions of terms that have a globally unique identifier. The Data Privacy Vocabulary (DPV) represents a community standard for privacy, data protection, and related topics. DPV uses modular namespaces to define jurisdictions, such as "EU", and to represent concepts from laws within that jurisdiction, such as the General Data Protection Regulation (GDPR) and the European Health Data Space (EHDS). In this work, we present the creation of a DPV extension representing the German Health Data Use Act (Gesundheitsdatennutzungsgesetz (GDNG)) that has been set into force in March 2024. The GDNG regulates sharing and using health data for secondary use, such as research purposes and policymaking
0
0
0
15
Computers and Society Papers@WGOV
Oct 28
Neighborhood Deprivation Shapes Post-Flood Population Losses in Pune and Bandung

Sukie Xiuqi Yang, Guangyuan Weng, Shiyue Cui, Zhicong Chen, Catherine Chen
arxiv.org/abs/2610.37418 [𝚌𝚜.𝙲𝚈 𝚙𝚑𝚢𝚜𝚒𝚌𝚜.𝚜𝚘𝚌-𝚙𝚑]
💬Code: github.com/turtleman99/po…
Disaster research in high-income settings shows that better-resourced communities see population inflows and faster recovery, while disadvantaged communities suffer prolonged population loss. Whether this pattern holds in rapidly urbanizing cities of the Global South remains unclear. Here we show, using mobile phone data from Pune, India, and Bandung, Indonesia, how neighborhood-level changes in phone presence, a proxy for short-term population movement, relate to flooding and neighborhood deprivation. We combine satellite-derived flood maps with phone records to compare flooded and non-flooded areas over the 30 days around each flood. In both cities, less deprived neighborhoods see phone presence rise after flooding, while more deprived neighborhoods see it fall, consistent with resource-seeking interpretations documented in North American and European disaster research. The cities differed, however, in how deprivation relates to flood exposure: in Pune, more deprived flooded neighbor
0
0
0
29
Computers and Society Papers@WGOV
Oct 28
Uneven Use, Similar Trust Generative AI in Denmark and Romania

Iulian Lucau, Adelin-George Voicu, Simon Munk Christensen
arxiv.org/abs/2610.37348 [𝚌𝚜.𝙲𝚈]
Generative AI (GenAI) has spread unevenly across Europe, and it is unclear whether higher use brings higher trust. This paper compares Denmark and Romania, the EU's highest and lowest GenAI users, and asks whether the difference in public and institutional trust between them corresponds to the difference in trust in AI. Drawing on trust, technology-acceptance and digital-divide theory, it is a descriptive, contrasting-case analysis of harmonised data: GenAI usage comes from Eurostat, trust in AI more generally from the KPMG/Melbourne global study and public and institutional trust from the Standard Eurobarometer. In 2025, 48.4% of Danes aged 16-74 had used GenAI in the past three months, against 17.8% of Romanians. Use falls with age and rises with education in both countries, and the relative gaps are far larger in Romania; the patterns remain visible within the published age-by-education categories. Trust in AI does not follow usage: Romanians trust AI as much as Danes or slightly mo
0
0
0
24
Computers and Society Papers@WGOV
Oct 28
Conditional Values: The Contingent Foundations of Attitudes toward Artificial Intelligence

Sam Flanders, Melati Nungsari
arxiv.org/abs/2610.37197 [𝚌𝚜.𝙲𝚈]
How do broader values shape whether people judge artificial intelligence (AI) as good or bad for humanity? This article analyzes provisional World Values Survey Wave 8 data from 40,960 respondents in 24 country samples using pooled and national prediction models, outcome-independent respondent profiles, and groups of countries. The analysis reveals a cross-country anchor: general optimism about science and technology is the strongest pooled predictor of favorable AI evaluation and recurs among the leading predictors in every national sample. Expert authority, education and information access, selected forms of trust, openness, and demographic position provide nationally distinctive patterns. Eleven value profiles formed without AI attitudes span 49.1% to 62.2% favorable evaluation. Most evaluative variation occurs within these profiles, making them useful contexts for identifying how the same values distinguish favorable from unfavorable evaluators in different social configurations. I
0
0
0
21
Load more