Papers

This manuscript is an English translation and extended version of a paper originally published in Japanese (Otomo, 2024). With the advancement of information and communication technology (ICT) and data analysis techniques, handling massive datasets (big data) has become feasible in spatial information science. Consequently, infrastructure is being established to generate new utility value from spatial data. Furthermore, nationwide initiatives are actively promoting the use of open data - public information provided under terms allowing secondary usage. However, in developing regions and specific municipalities, local statistical data remain scarce, unreliable, or difficult to acquire. Additionally, long-standing concerns exist regarding the inherent limitations of standard macroeconomic indicators when performing cross-regional or international comparisons. Meanwhile, high-frequency satellite data has become widely accessible. Among various observational products, nightlight data has attracted significant attention due to its versatile applications. Generally, nightlight radiance correlates with urbanization. Prior work indicates that areas with larger populations and higher commercial development display higher radiance, whereas public infrastructure - such as sanitation systems and healthcare facilities - shows little correlation with nightlight intensity (Otomo, 2021). Building on these findings, this paper analyzes the relationship between nightlight data and the spatial distribution of sports facilities, the evolution of the fitness industry, and regional environmental disparities in sports access. The analysis confirms that the spatial distribution patterns of sports facilities differ significantly between the public and private sectors.

In medicine, claims remain valid when supported by empirical evidence grounded in stable biological reality. In law, by contrast, truth is contingent, defined by jurisdiction, temporal validity, and the hierarchy of authoritative sources. The recent success of large language models (LLMs) on medical licensing examinations has encouraged an expectation of comparable legal competence. This analogy, however, obscures a critical distinction between domains. Unlike in medicine, legal performance often depends less on inference than on determining when external authority is applicable, valid, and non-contradictory. We introduce a comparative diagnostic framework evaluating legal reasoning against medical baselines along four axes (knowledge recall, grounding, confidence, and robustness), uncovering a sharp domain asymmetry when applied to a new benchmark that encodes temporal validity and normative relationships. While medical LLMs reliably benefit from verified sources, legal LLMs struggle to assess when retrieved citations are useful or misleading, exhibiting overconfidence in perturbed contexts and sensitivity to superficial formatting cues. Increased model scale amplifies this tendency, revealing that stronger instruction following can coincide with weaker resistance to authoritative perturbations. These findings show that LLMs treat law as unstructured text rather than binding precedent, while revealing a tendency to over-trust authoritative but false information when external references conflict with a model's internal knowledge.

Student-generated metaphors about mathematics can provide insights into students' attitudes, beliefs, identities, and experiences, but expert human assessment through thematic coding of these semantically complex metaphor responses is labor-intensive and difficult to scale. This study examines whether Low-Rank Adaptation (LoRA)-based supervised fine-tuning of Large Language Models (LLMs) can improve their performance on codebook-guided coding tasks for student mathematics metaphors. We utilized a human-coded corpus of 2,265 Grade 6-8 responses to food- and animal-based metaphor prompts and evaluated LLMs on two tasks: valence-intensity coding of students' affective orientations toward mathematics and thematic coding of their metaphorical framings of mathematics. Two open-weight LLMs, DeepSeek-R1 1.5B and Mistral 7B, were evaluated before and after fine-tuning and compared with two proprietary LLMs, GPT-4o mini and GPT-5 mini. Results show that fine-tuning substantially improved the performance and run-to-run reliability of the open-weight LLMs across both tasks relative to their base versions, making the fine-tuned LLMs competitive with and often outperforming the proprietary LLMs. These findings suggest the potential of fine-tuned open-weight LLMs for scalable and automated AI-assisted measurement of students' metaphor responses with competitive performance while maintaining local controllability and privacy-conscious deployment.

Large language models (LLMs) increasingly mediate legal determinations over what human rights are realized, and how. Yet, no evaluation benchmark exists to assess whether they can reason correctly about human rights law. To this end, we report our efforts to develop a robust and scalable methodology for creating HumRightsBench: the first expert-validated, scenario-based benchmark for evaluating reasoning grounded in the obligation structure of international human rights law. We adapt the IRAC framework for legal reasoning to better suit the unique reasoning patterns of human rights work (substituting P, "proposing remedies," for C, "legal conclusion," yielding IRAP) to structure our evaluation heuristics. We also produce a pilot series of authentic scenarios designed to implicate the many dimensions of real-world human rights issues and annotated by human rights lawyers and professionals across the world. Ultimately, we find that model accuracy scores range considerably across legal reasoning tasks (overall model performance ranges from 0.339 to 0.577, task min-max ranges from 0.025 to 0.774), which strongly implies that HumRightsBench is a capable instrument for advancing this emerging subfield of AI evaluations science at a critical moment in its evolution.

Humans are increasingly expected to interact with AI systems that observe and make inferences about them - but do these systems actually work? A standard approach to answering this question is AI auditing. Conducting an AI audit requires identifying how a system behaves (i.e., determining what types of inputs to audit it with and then observing and documenting actual system behavior) and contrasting that with how a system should behave (i.e., determining what the nominal outputs of a system should look like). We argue that this is best done through a contextual audit, which we introduce as a method for auditing measurements within the context of the practices that produce them. We show how contextual auditing enables the interrogation of assumptions implicit in the audit process and allows auditors to be explicit about what serves as ground truth, which we define as verifiable measurements about the real world against which systems are evaluated. We outline how the concept of symmetry from science and technology studies can enable audits when ground truth is unknown, unknowable, or contested. Finally, to demonstrate how contextual and symmetric audits can be conducted in practice, we present a case study of skeleton inference in motion capture and propose areas suggested by our case study as particularly fruitful for future audits of motion capture systems.

LLMs are increasingly deployed in settings that require collective reasoning on complex, value-laden problems. Confidence in these deployments rests largely on benchmarks for verifiable tasks (mathematics, coding, coordination games), yet many of these applications concern problems where no objectively correct answer exists and where decision quality instead depends on integrating pluralistic perspectives to find mutually acceptable solutions. We argue that LLM reasoning capacity on this class of problems cannot be fully inferred from verifiable-task benchmarks, and that procedural evaluations of LLM discourse (respectfulness, justification, engagement) are systematically insufficient. We apply the Deliberative Reason Index (DRI), a measure developed in political science and validated across citizen assemblies, as a tool for evaluating reliable group-level reasoning on pluralistic, non-verifiable problems. Synthesizing recent evidence across 1,980 five-agent LLM runs on 12 citizen-assembly topics across 11 frontier model configurations, we find that LLM groups produce discourse with procedural quality comparable to human deliberation, while gains in intersubjective consistency are small, topic-dependent, and concentrated on tractable rather than ethically contested questions. LLM groups exhibit roughly one-third the perspective diversity of human assemblies and reverse the human convergence pattern: human deliberation decreases dispersion as diverse views synthesise, whereas LLM deliberation increases it. Engineering diversity through persona prompting does not restore the human dynamic but inverts which component of deliberative reasoning is updated. Our conclusion is constraining rather than prohibitive: LLMs can function as tools supporting human reasoning on pluralistic problems, but current evidence does not license treating them as autonomous deliberative agents.

Computer vision saliency models predict where people will look, one map per image, and a billion-dollar predicted-attention industry sells those maps in place of measuring real viewers. I test the leading models from the audience side, against 11.4 million webcam gaze points from 3,023 US adults recruited to national quotas, viewing circulating news photographs. I show that an untrained central marker outperforms every trained network, because the content the networks add on top of the center falls where these audiences never look. What accuracy remains is systematically biased, favoring younger, White, and moderate viewers over older, Black, and ideologically extreme ones. I propose a way forward and build on what a group's own gaze reveals about whether a model can learn that group at all, and I apply it across every demographic axis this sample supports. Ultimately, I show how systems that decide what people see can learn to see everyone, and this study supplies the standard by which such a claim should be judged.

Bias evaluations often move too quickly from evidence that a model encodes a social association to claims that the same association will alter consequential decisions. We test whether that inference is warranted using Chilean surnames as controlled socioeconomic probes. We evaluate eight frozen model-provider cells on 1,032 prompts each, yielding 8,256 verified primary responses. The design separates forced latent association from matched consequential decisions across academic selection, professional hiring, research fellowship selection, and legal-aid intake. Elite-coded surnames received higher forced high-status probability mass than common surnames in seven of eight models and higher mass than rare-frequency controls in all eight. Yet elite-minus-common decision effects were close to zero for most systems. Five models were statistically equivalent within a predeclared (Plus-Minus)0.10 standard-deviation margin, while the remaining three were imprecise or borderline, with no consistent elite advantage. Association strength did not reliably predict decision leakage across models (r = 0.201, p = 0.633) or across frozen surname-pair-by-model cells (r = 0.065, p = 0.565). The central result is a measurement dissociation: latent social association and consequential treatment are empirically distinct constructs. Evaluations should measure the transition from association to action directly.

Soft skills shape collaboration among ML engineers, data scientists, and software engineers building ML-enabled systems, yet what we know about them comes almost entirely from the demand side. Job advertisements, surveys, and hiring manager interviews capture what employers ask for. How candidates themselves articulate these competencies has not been studied, and existing CV-mining work is both keyword-based, so it cannot see skills conveyed through narrative, and descriptive, reporting frequency rankings without testing whether group differences exceed sampling variation. We close both gaps. Using a balanced corpus of 300 curated CVs spanning the three roles, we extract explicitly listed and implicitly narrated soft skills with an LLM-based pipeline validated against a human-annotated ground truth, a distinction that existing extractors were not designed to make. We then convert the demand-side literature's claims into 13 falsifiable hypotheses about role signatures, seniority progression, and disclosure style, and test them with effect sizes under family-wise error control, so that candidate-side data can corroborate or contradict the demand-side account rather than merely illustrate it. Eleven hypotheses are supported, one partially, and one refuted. Candidates disclose soft skills through narrative rather than keyword lists by roughly three to one, and most so for the competencies employers value most: leadership, coordination, and mentoring (88-96% narrative). Seniority nearly triples the odds of articulating leadership. That competency, assumed universal in prior work, is articulated by software engineers at half the rate of their peers. Technical candidates do articulate soft skills, but a keyword-based screening systematically misses them.

Ball possession is the most-cited and most-misleading number in football: 60% recycled in one's own half is not 60% spent pinning the opponent back. Existing event-based possession-value frameworks (expected threat, VAEP, on-ball value) price on-ball actions but ignore the off-ball question a sterile possession poses: did holding the ball create space, or was the circulation dead? We answer this in two layers. First, an event-side junk-possession index prices each possession sequence by its peak threat gain under an expected-threat grid and – after reconstructing the live scoreline to exclude lead-protecting circulation – flags low-threat sequences in tied-or-losing states. On the 2026 FIFA World Cup (103 matches, 206 team-matches) the flag correlates negatively with points (r=-0.37) and xG difference (r=-0.51, partly index-coupled). It is not a repackaging of on-ball value: with team offensive VAEP and field tilt held fixed, the junk flag stays strongly negatively associated with points (p<0.0001, also match-clustered) while VAEP is not significant – in this same-match (descriptive) regression it adds information beyond this on-ball action-value model. Second, for a flagged window we resolve whether it was spatially dead or space-creating by projecting broadcast video to pitch coordinates and measuring a Space-Creation Index (SCI): a net pitch-control change capturing whether the possession seized space or pushed the opponent's block back. Across 31 of 35 flagged windows from nine World Cup matches (a purposive sample), 74% are spatially non-space-creating, 19% weak progression, and 6% space-creating windows the event flag alone would score as failure – including a side with 73% of the ball that exited on penalties (two non-creating windows). The two layers separate space-creating-but-unconverted from sterile possession, a distinction event-only on-ball value cannot make.

Large language models (LLMs) are increasingly used to perform subjective evaluations traditionally made by humans, yet their validity as social judges remains unclear. This paper examines whether LLMs can assess social attraction from theory-grounded persona profiles constructed from ten psychological and relational constructs and organized into three tiers: socially attractive, socially mixed, and socially unattractive. We examine LLM ratings in two studies and compare them with human judgments in a third study. In Study 1, 34 LLMs rated 12 profiles across three repeated runs. Although some models tended to give higher or lower ratings overall, they showed strong stability across runs, consistent three-tier ordering, and high agreement in relative profile ordering. Study 2 examined sensitivity to gender presentation using six matched name-and-pronoun profile pairs and a separate pronoun-only test with a gender-neutral name, finding no significant effects in either analysis. In Study 3, 198 human participants evaluated the six matched profiles from Study 2. Their ratings reproduced the three-tier structure and followed a profile ordering consistent with that of the LLMs. However, LLMs rated attractive profiles more positively and unattractive profiles more negatively than humans, while neither group showed a significant overall effect of gender presentation.

National planning counts population, human capital, and artificial-intelligence preparedness in separate ledgers. Demographic accounting has advanced from headcount to skills-adjusted stocks and still debates how much age structure retains once skills are modeled, yet no existing unit carries the conditions under which preparedness becomes productive capacity. This study introduces the Effective Cognitive Population (ECP), a decomposable unit that weights population by capability and by the conditions under which capability is deployed, anchored to the World Bank Human Capital Index Plus (HCI+) and the non-overlapping dimensions of the IMF AI Preparedness Index. The architecture is portable in principle; the case tested here is artificial intelligence, which has a published preparedness index. For 144 countries, HCI+ becomes a productivity level, AI opportunity uses digital infrastructure and innovation integration, conversion governance uses regulation and ethics, and the benchmark is ECP = N H(1 + AC). Against 2024 total output on identical population bases, ECP raises criterion R-squared from 0.849 for the HCI+-adjusted stock to 0.882 and lowers leave-one-country-out RMSE from 0.723 to 0.641, with the working-age comparison identical and bootstrap intervals excluding zero. Eighty-nine of 144 countries move at least ten rank positions from headcount, mostly through the human-capital adjustment itself. Results are stable across denominators, vintages, aggregation forms, and a 27-rule multiverse. The direct A by C interaction is not statistically supported, so the conjunction is a planning rule rather than causal complementarity. ECP is a diagnostic ledger whose scope excludes forecasts of population decline and estimates of AI's causal productivity effect.

Theory of Mind (ToM) is essential for agent interactions, yet existing evaluations either rely on static scenarios that oversimplify mental-state reasoning or interactive settings that provide limited diagnostic insight. We present Avalon-ToM-Bench, a fine-grained benchmark that operationalizes ToM through the asymmetric-information mechanics of The Resistance: Avalon. Rather than evaluating end-to-end gameplay, it decomposes ToM into a 2$\times$2 taxonomy – epistemic versus motivational reasoning crossed with inference versus action – using human-crafted, perspective-constrained queries. Benchmarking 28 LLMs reveals three insights: 1) Reasoning, not knowledge. Models show strong game-rule comprehension but markedly weaker ToM abilities, isolating failures to social reasoning rather than missing domain knowledge. 2) Expression, not representation. Mechanistic analyses via linear probing and activation steering show that models frequently represent correct mental-state inferences in their hidden states but fail to express them during generation – linear probes recover 77-82% accuracy versus 62-70% from the models' own chain-of-thought. 3) Policy, not deliberation. Dedicated reasoning training yields substantial improvements whereas test-time chain-of-thought provides only marginal gains (+11.0 versus +1.1 points on average), suggesting that robust ToM depends on a learned reasoning policy rather than increased inference-time deliberation.

Large language models are increasingly deployed in education as tutors, teaching assistants, and content generators. These roles place demands that ordinary question answering does not: a usable education-facing model is supposed to be accurate, safe under sensitive prompts, instructionally useful, and aligned with pedagogical goals at the same time. Existing benchmarks evaluate these requirements largely in isolation, so none assesses education-facing suitability as an integrated profile. We introduce ELBench, the first benchmark to evaluate all four requirements (General Capability, Safety and Trustworthiness, Basic Education, and High-Level Cultivation) on the same models under a common protocol, combining curated public sources with newly synthesized safety and cultivation data. We evaluate nine models, seven frontier general-purpose systems and two education-specialized variants, and report three findings. First, module-level profiles are more informative than a single aggregate: the top six models are statistically indistinguishable on overall score, yet their module leaders differ substantially, and safety is anti-correlated with practical teaching (r = -0.83). Second, the Chinese-developed models lead the safety module, the most discriminative in the suite; this advantage is largest on region-specific normative content and narrows, but does not vanish, on universal-harm content. Third, the two education-specialized models lead neither education module, and on High-Level Cultivation all models share a systematic blind spot: on the structured judgment task they converge on the same non-reference option, favoring pedagogical style over fit to the stated goal, so the module scores uniformly low and does not separate models. This raises, but does not resolve, whether domain post-training keeps pace with frontier systems on education tasks.

Research values, properties with a distinctive normative dimension, often affect how technological research is performed in both direct and indirect ways by influencing how technical decisions are made. In machine learning for medical imaging, understanding these values can be important for understanding why particular researchers justify the decisions made in their publications and explain why certain technologies become ubiquitous (or not) in the scientific literature and in the clinic. This article explores one of these technologies, foundation models, finding detailed justifications both for their use and abstention from their use. By taking a Socratic approach to research values arising from this specific technical decision, this article aims to better illustrate how foundation models fit into the philosophy of machine learning in medicine.

Multidimensional item response theory relies on calibrated item parameters, such as discrimination and category threshold values, which are usually estimated from large samples of human test responses. This study investigates whether the directional loadings of these parameters can be recovered directly from item text using pre-trained sentence embeddings, avoiding the need for initial item calibration. Using the open-source IPIP Big-Five dataset ($n=19{,}719$; 50 items), we built a multidimensional computerized adaptive testing (CAT) simulation using D-optimal item selection. We compared three item loading sources: fitted graded response model parameters, semantic text embeddings, and a lexical baseline. In simulation, semantic embeddings recovered latent trait profiles almost as accurately as fitted parameters (correlation $0.825$ vs. $0.857$), performing noticeably better than simple word overlap ($0.752$). However, the embedding-based model produced inflated posterior variance, showing nearly four times higher measurement uncertainty despite accurate point estimates. We attribute this to collinearity across dimensions, as embedding-derived loadings pointed in similar directions across traits (condition number $137$ vs. $1.0$; mean trait cosine $0.90$). This outcome reflects the shared vocabulary common in personality items. We propose a simple diagnostic metric based on the loading matrix condition number to evaluate whether an item bank is suitable for text-derived loadings prior to testing.

Large language models are increasingly deployed as general-purpose educational and technical assistance systems, but their underlying infrastructure does not treat languages equally. One underexamined source of disparity is tokenization: semantically equivalent content can require substantially different token counts across languages, affecting API cost, latency, and usable context length before a model is invoked. We introduce the Tokenization Equity Audit (TEA), a reproducible benchmark for measuring tokenization premiums in technical tutoring content. TEA evaluates three widely used tokenizers, GPT-4o's o200k base, Qwen2.5-7B, and Mistral-7B, on a 120-item Python debugging corpus translated from English into Bengali, Hindi, Arabic, Tamil, and Yoruba. Bengali and Hindi serve as the primary validated cases, while the remaining languages provide exploratory cross-script and cross-family comparisons. Across this corpus, Bengali requires (1.56\times) as many GPT-4o tokens as English, reducing a nominal 128k-token context window to an effective 82k-token English-equivalent capacity for the same semantic content. With the Qwen2.5 and Mistral tokenizers, Bengali requires up to (4.5\times) the English token count. Yoruba, despite using the Latin script, exhibits the highest GPT-4o tokenization premium at (2.37\times), indicating that tokenization inequity cannot be explained by script family alone. These results demonstrate that tokenization can create measurable economic and functional barriers, highlighting the need to treat tokenization as an equity-relevant infrastructure layer for underserved language communities, particularly where educational systems depend on low-cost or offline-capable AI tools.

Prior research often finds that AI creativity is limited: single systems rarely outperform humans, and human-AI collaboration does not exceed human output. We argue these conclusions underestimate AI's potential because most studies do not allow iterative, multi-agent exchanges that mirror the social processes underpinning human creativity. We conducted an experiment comparing four conditions: (i) AI-AI co-creation with complementary generator-evaluator roles, (ii) AI-AI co-creation with identical roles, (iii) single-AI creation, and (iv) human-human co-creation. Across three open-ended tasks, 1,212 ideas were rated by trained judges on creativity, novelty, and usefulness. Both AI-AI co-creation conditions consistently outperformed single-AI creation and human pairs on creativity and novelty. Usefulness varied by task: complementary roles yielded the most useful solutions in the broadest and most socially complex task, suggesting role differentiation is advantageous when problems require both imaginative ideation and practical refinement. Human pairs performed worst, consistent with production losses in group creativity. These findings indicate that structured, iterative multi-agent AI co-creation can exceed single-AI and human-human ideation.

As generative AI increasingly becomes a common source of daily decision-making, including financial choices, it is critical to understand how people evaluate AI-generated financial advice. We conducted a preregistered vignette experiment (N = 285) in which substantive financial content—including facts, numerical values, recommendation direction, and core reasoning—was held constant while communication style varied across AI Financial Assistant (AI), Certified Financial Planner (Expert), and Online Community Forum (OC) advice. Displayed source attribution was independently manipulated through correctly labeled, unlabeled, and mislabeled conditions, allowing us to separate attribution effects from source-specific communication cues. Expert advice was rated more favorably than AI advice on 9 of 10 outcomes (|d|=0.20–0.47), and this advantage remained visible without source labels, where Expert advice outperformed AI advice on 8 of 10 outcomes (up to d=0.60). Correct labels added limited differentiation, whereas mislabeling increased ratings of AI advice for situational fit and overall quality (d=0.42 for each) and attenuated the Expert advantage in situational fit (d=-0.36). Descriptive analyses further showed that AI advice was most responsive to displayed attribution and, conversely, that advice-style differences were most visible under an AI label. These findings show that financial-advice evaluations are shaped jointly by displayed attribution and message-level communication cues. We position disclosure not as a neutral transparency mechanism, but as an interpretive frame whose accuracy and interaction with message cues can shape trust and reliance.

This paper explores the potential of integrating e-textiles as part of the approach to delivering computing in UK secondary schools. As one of the few UK-based exploratory studies of teachers experiences, it investigates how e-textile platforms such as the SewSimple maker kit and the BBC micro:bit can be incorporated into Key Stage 3 computing education (ages 11-14), taking into account both English national curriculum requirements and the realities of classroom practice. Our research question is: How do teachers perceive the potential of including e-textiles as part of computing education in English secondary schools? In summary, our research contributes to secondary computing education in three ways. First, we examine teachers direct, cross-disciplinarity experiences in two participatory design workshops using a newly designed e-textile platform and extend the limited discussion on supporting the BBC micro:bit in e-textile education. Second, we specifically identify opportunities, barriers, and challenges across three dimensions: school planning, national curriculum guidance, and practical e-textile implementation. Third, we offer insights into best practices for supporting maker technology adoption and pedagogical practices within existing institutional structures to maximize students' benefits for secondary school computing education.

Foundation models tutor, assess, and instruct at population scale, requiring externally defined measures of educational competence. Existing benchmarks emphasize difficult academic problems or isolated synthetic educational tasks rather than authentic teacher-entry standards. We introduce EDU 1.0 (Educational Due Diligence for Foundation Models), which uses teacher-entry assessments as proxies for educational competence rather than substitutes for human qualification. EDU 1.0 comprises 10,012 questions from teacher certification and recruitment examinations in the United States, China, and India, including the U.S. Praxis series, China's National Teacher Qualification Examination, and India's Kendriya Vidyalaya Sangathan examinations. It covers foundational literacy and knowledge, pedagogical principles, and subject-specific pedagogical expertise across language arts, mathematics, science, social science, and education practice. Across 36 foundation-model variants, the strongest proprietary model reaches a response-balanced score of 96.5%; the leading open-weight model trails by 2.1 percentage points, while the leading system deployable on a single accelerator reaches 92.2%. These aggregates conceal a shared limitation: all three systems score higher on general pedagogical principles than on assessments requiring pedagogy to be applied within a discipline. Their subject-assessment scores span 4.1-8.8 points, and their shortfall relative to general pedagogy widens from 2.6 to 4.1 points as capability declines. The outstanding requirement is therefore pedagogical content knowledge, the capacity to make particular subject matter teachable to particular learners, rather than general pedagogy or model scale.

Māori data sovereignty (MDSov) has established important principles for recognising Māori rights and interests in data. Relatively little attention has been given to how these principles can be operationalised within research institutions who, as a function of their operations, collect and use Māori data. This paper introduces the concept of Māori Research Data Sovereignty (MRDSov), extending existing understandings of MDSov into the specific context of research data and the research data lifecycle. Drawing on Indigenous Data Sovereignty scholarship and research data management literature, we define Māori research data and position MRDSov as the application of MDSov principles to research data produced by, about, or for Māori. We argue that operationalising MRDSov requires three interdependent elements: data findability, data governance, and community engagement. Data findability enables Māori research data to be identified and contextualised; governance provides mechanisms through which Māori authority over research data can be exercised; and community engagement grounds both in enduring relationships with Māori communities. We further demonstrate how these elements collectively enact the principles of MDSov within institutional research settings, providing a practical pathway for aligning research data practices with Te Tiriti o Waitangi obligations and Indigenous data governance expectations. The paper contributes a conceptual framework for universities and other research organisations seeking to embed Māori authority, accountability, and relationships throughout the research data lifecycle.

Rapid urbanization has increased the need for surveillance systems that can monitor multiple public safety risks at the same time. Traditional systems often use separate solutions for facial recognition, vehicle identification, fire detection, and behavioral analysis, resulting in fragmented infrastructure and multiple interfaces for operators to manage. This paper presents City Sentinel, a unified AI-based surveillance framework that integrates six detection capabilities into one scalable platform: facial recognition, automatic number plate recognition (ANPR), fire and smoke detection, weapon and knife detection, violence detection, and road accident detection. The system combines a Next.js operator dashboard, FastAPI backend, cloud-based PostgreSQL event storage, InsightFace and YOLOv8 vision models, and EasyOCR for plate recognition. Camera streams are processed through dedicated inference workers using RTSP. On a workstation equipped with an NVIDIA RTX 3060 GPU, the system achieves a median end-to-end latency of 743 ms and supports four concurrent RTSP streams within a two-second latency limit. It achieves a 91.2% face-match rate, 85.7% plate-reading accuracy, and mAP@0.5 scores of 0.846 to 0.889 across the fire, knife, and weapon detection modules. In user-acceptance testing, operators could enroll a new identity in under one minute and identify a flagged person from live footage in an average of 12 seconds. The results demonstrate that a modular, open-source, multi-model architecture can provide broad surveillance coverage, cloud-based auditability, and flexibility for adding new detection capabilities while maintaining practical real-time performance.

AI agents can now solve problems, answer like subject experts, and generate long-form multimodal content. However, whether they can adapt a lesson to fit a specified learner, which education calls Pedagogical Content Knowledge (PCK), has not been benchmarked. To measure it, we introduce the Teaching Monster Challenge, the first instructional video generation benchmark to treat the learner persona as an explicit evaluation criterion. Each system is given a topic and a learner persona and must generate a complete instructional video. Every video is screened by an LLM-judge, ranked by crowd pairwise voting, and finalized by an expert panel. The first edition shows that today's systems handle the content well but are far weaker at presenting it and adapting it to the learner. The same process exposes a limit of automatic judging. The LLM-judge separates a clear low-performing tail but ranks the strongest systems poorly. The strongest systems receive nearly identical scores from the judge, so its ranking of them does not match human preference. Progress therefore requires not only better teaching systems but also better automatic judges, and we release the benchmark, rubric, and human judgments as a testbed for both.

This implementation report explores Rowan University's effort to automate the process of freshman course placement and registration. Historically, Freshman Instructional Guides (FIGS) at Rowan was manually executed, requiring significant time from Testing Services, University Advising, and the Registrar's Office to evaluate placement needs and assign students to courses. Given the 57% surge in first-time degree-seeking student enrollment over a decade, the manual processes became increasingly unsustainable. In response, a cross-departmental team developed a comprehensive automated process to integrate data from Banner (Student Information System), Google Sheets maintained by Advising, and other sources. This automated process classifies students based on program groupings, determines primary and secondary course placements, checks for real-time availability and constraints in Banner, and completes course registration for freshmen in bulk. The resulting system processed over 3500 incoming students with over 350 hours in annual time savings, reduced the potential for human error, and enabled staff to shift focus from administrative work to strategic advising. This report outlines the implementation context, design architecture, technical integration, assessment methods, lessons learned, and practical implications for institutions with similar challenges.

Reinforcement learning (RL) seeks to optimize sequential decisions to maximize population-level benefits over time. However, when deployed in high-stakes settings such as healthcare, RL decisions might systematically restrict some subpopulation's access to valuable services in a manner contrary to the values and goals of stakeholders. Counterfactual fairness (CF) offers a promising framework to address this problem based on causal reasoning. This paper develops a data preprocessing algorithm that, when used in tandem with policy learning, enables CF in RL. Our algorithm relies on a novel quantile distribution mapping method for sequentially estimating the counterfactual states and rewards in the data preprocessing step, subsuming common additivity assumptions used for counterfactual prediction as a special case. We theoretically prove that the per-step level of counterfactual unfairness and infinite-horizon suboptimality gap can be bounded under mild regularity conditions. We also empirically test our algorithm in numerical experiments as well as in application to a real-world interventional digital health dataset.

The EU AI Act uses a risk-based approach to regulate AI systems, calibrating the intensity of regulation according to the risks they pose. While the term 'risk' implies quantification, resulting from the combination of the probability and severity of harm, the AI Act refers to risks to fundamental rights, thereby engaging a qualitative perspective. In this piece, we address this puzzle using a two-step framework under which the EU AI Act balances risks with the protection of fundamental rights, the legitimate purposes of providers and deployers, and the impacts of regulatory measures on providers, deployers, and regulators. We discuss this framework against the backdrop of potential approaches to quantifying risks, with a specific focus on defining and measuring the main components of the concept of risk: probability, severity, and their combination. We suggest that the protection of fundamental rights and risk quantification can be aligned by incorporating quantification methodologies into the proposed framework. In particular, the AI Act implies a balancing analysis that uses a severity-first approach to classify and quantify the risks posed by AI systems. The integrated framework not only helps to clarify the AI Act's risk-based approach, but can also inform technical and implementation choices. Finally, we conclude that if the risk quantification methodology or its application to the protection of fundamental rights is left to providers and deployers, there is potential for 'risk hacking', which could lead to the underclassification of AI systems and subsequent regulatory shortcuts.

Higher education stands at a turning point. In an era where knowledge is increasingly accessible and which is, more often than not, mediated by advanced Artificial Intelligence (AI), the value of traditional curricula models warrants reconsideration. This does not imply that one should replace thorough academic studies. Universities remain essential in providing foundational knowledge, theoretical depth and conceptual grounding. The challenge is to extend these educational facets with learning environments that foster creativity, interdisciplinary integration, hands-on experience, and especially long-term development. In this paper, we introduce a lifelong learning framework that integrates academic, professional, and personal learning, centered on a new concept that we term learnity graphs, a structured representation of learning as interconnected units of knowledge, skills, experience, and actual artifacts, coupled with a method for presenting, and leveraging it.

Logics of abstraction in computational AI research often push important forms of knowledge and reflection aside: dominant standards of legitimacy separate from lived experience of harm; the goals of work misalign with the practices that operationalize them; and career demands crowd out critical reflection. Even as prior academic and community-oriented efforts have sought to recontextualize and challenge common practices, exposure to sociotechnical harms and epistemic injustice persists. As three early-career critical AI researchers, we experienced this as alienation: feeling like outsiders in our research communities. This alienation has involved having some aspects of our backgrounds overlooked and others tokenized. We argue our alienation occurred through mechanisms that mirror abstraction by creating distance from relevant material realities. Beyond abstraction's role in computational AI research as a foundational practice structuring complex computational tasks, we have encountered it as a social norm in computational research spaces, illustrated through an autoethnographic inquiry into our alienation. We narrate three vignettes describing how we encountered and resisted alienation in our research communities. By analyzing themes across these accounts, we construct an interpretive framework of alienation categorizing its preconditions, mechanisms, and harms. Finally, we identify affect abstraction, one of the mechanisms of alienation we describe, as a high-leverage mechanism that is resistible by staying attuned to our affective responses, and collective action as a way to reduce risk and isolation when engaging in resistance. To assist others with similar reflection, we present our framework as a hermeneutic resource. Critical self-reflection and meaning-making are necessary steps toward challenging exclusionary disciplinary norms and cultivating more inclusive forms of AI research.

Smart city and digital twin concepts hold considerable potential for improving local governance and planning, yet practical implementations have almost exclusively focused on large metropolitan areas. Small towns and rural regions face a distinct set of challenges – limited data availability, constrained budgets and lower digital capacity – that make a direct transfer of urban approaches infeasible. This article presents results from the ongoing project "Smart Cities and Digital Twins in Lower Austria", which adapts digital twin concepts for small-town and rural contexts following a design science research approach. Based on stakeholder workshops with municipalities in Lower Austria, three use cases were identified and implemented as prototype digital twins: traffic flow planning (emphasising data integration), population growth (emphasising simulation) and shared spaces (emphasising visualisation). We describe the design and implementation of each prototype and report on a technical evaluation of their feasibility. Our findings highlight both the potential and the specific limitations of digital twins in resource-constrained settings and offer practical guidance for municipalities, policymakers and researchers working in non-urban contexts.