Named after the hundred-eyed watchman of Greek myth, Argus watches the education landscape: spotting new opportunities, pressure-testing the ventures we're building, and tracing every read back to the real-world signals behind it.
The evidence library: the raw signals the pipeline is watching across the education ecosystem. Every idea is built from these.
arXiv:2606.02348v2 Announce Type: replace-cross Abstract: Information sharing among competing suppliers can improve decisions under demand uncertainty, but it may also intensify strategic interaction by aligning firms' beliefs. We study a Cournot oligopoly in which a platform designs an information-sharing mechanism using participation-contingent access, external platform information, and privacy-preserving noise. The central privacy-design challenge is that noise has two opposing effects: it limits how much a firm's report improves rivals' information, but it also reduces the value of the posterior signal released by the platform. In symmetric duopoly, privacy protection alone cannot implement sharing without an external platform signal. More generally, privacy can induce firms that would otherwise not share to participate only when combined with external platform information, which preserves an informational benefit independent of competitors' reports. The $n$-firm case adds a distin
arXiv:2605.16270v2 Announce Type: replace-cross Abstract: Accurately quantifying children's social interaction behavior is part of understanding their cognitive and emotional development, as well as mental health conditions. Kids-SIT is a web-based tool designed to computationally analyse children's behaviors by engaging them in a standardized video conversation while their responses are video recorded. In a pre-registered study with 21 healthy children and 12 children diagnosed with social anxiety disorder (SAD), aged 9-14 years, we assess its potential as an accessible paradigm for automated analysis of children's social interaction behavior. We evaluate whether the Kids-SIT can elicit naturalistic interaction patterns in healthy children, and how well automatic feature extraction methods can detect these patterns. We analyse children's subjective impressions, verbal responses, and non-verbal behaviors. Non-verbal behaviors were manually annotated and, independently, automatically ex
arXiv:2605.12757v2 Announce Type: replace-cross Abstract: Generative AI is rapidly reshaping STEM higher education. Not only are our educational practices changing, but how we think about educational transformation must adapt. Existing models of institutional change in STEM, aimed at interactive engagement, have largely followed an adoption logic: relatively stable, well-researched educational practices are evaluated and then scaled. These assumptions do not hold for generative AI, which is an arrival technology -- entering classrooms before a sufficient pedagogical evidence base could form. Building on recent decades of work on STEM institutional change, we propose a framework identifying six dimensions along which prior change models must be reconsidered in light of AI: three concerning the tools at the center of reform (the tool's evidence base, rate of change, and scope), and three concerning the people involved in change (faculty, change agents, and students). For each dimension,
arXiv:2605.08669v2 Announce Type: replace-cross Abstract: Standard rational actor models often attribute cooperation failures in social dilemmas to insufficient incentives, overlooking the destabilizing effects of continuous utility maximization. To address this, we propose a framework of ``will" defined as a mechanism that persistently pursues goals while ignoring local cost-benefit fluctuations. We formalize the Willed Agents as potential minimizers, distinguishing them from cumulative utility maximization. Dynamical analysis of infinite population demonstrates that willed agents shrink the feasible state space, acting as boundary constraints that accelerate convergence in canonical social dilemmas. Through multi-agent simulations in a spatiotemporal Stag Hunt Game, we show that willed agents function as ``cooperation catalysts", enabling groups to surmount high-risk thresholds where purely utility maximization fails. We find that heterogeneous will strength promotes cooperation, and
arXiv:2604.21637v2 Announce Type: replace-cross Abstract: Where and how language models (LMs) are deployed determines who can benefit from them. However, there are several challenges that prevent effective deployment of LMs in non-English-speaking and hardware constrained communities in the Global South. We call this challenge the last mile: the intersection of multilinguality and edge deployment, where the goals are aligned but the technical requirements often compete. Studying these two fields together is both a need, as linguistically diverse communities often face the most severe infrastructure constraints, and an opportunity, as edge and multilingual NLP research remain largely siloed. To understand the state of the art and the challenges of combining the two areas, we survey 232 papers that tackle this problem across the language modelling pipeline, from data collection to development and deployment. We also discuss open questions and provide actionable recommendations for differ
arXiv:2604.15267v2 Announce Type: replace-cross Abstract: It is increasingly important that LLM agents interact effectively and safely with other goal-pursuing agents, yet, recent works report the opposite trend: LLMs with stronger reasoning capabilities behave _less_ cooperatively in mixed-motive games such as the prisoner's dilemma and public goods settings. Indeed, our experiments show that recent models -- with or without reasoning enabled -- consistently defect in single-shot social dilemmas. To tackle this safety concern, we present the first comparative study of game-theoretic mechanisms designed to enable cooperative outcomes between rational agents _in equilibrium_. Across four social dilemmas testing distinct components of robust cooperation, we evaluate four families of mechanisms: (1) repeating the game for many rounds, (2) reputation systems, (3) third-party mediators to delegate decision making to, and (4) contract agreements for outcome-conditional payments between playe
arXiv:2604.07285v2 Announce Type: replace-cross Abstract: Debates about artificial intelligence (AI) in education often portray teaching as a modular and procedural job that can increasingly be automated or delegated to technology. This brief communication paper argues that such claims depend on treating teaching as more separable than it is in practice. Drawing on recent literature and empirical studies of large language models and retrieval-augmented generation systems, I argue that although AI can support some bounded functions, instructional work remains difficult to automate in meaningful ways because it is inherently interpretive, relational, and grounded in professional judgment. More fundamentally, teaching and learning are shaped by human cognition, behavior, motivation, and social interaction in ways that cannot be fully specified, predicted, or exhaustively modeled. Tasks that may appear separable in principle derive their instructional value in practice from ongoing context
arXiv:2604.02677v2 Announce Type: replace-cross Abstract: Large language models are changing not only the kind of assistance people receive, but also how that assistance is organized. Instead of working with a single general-purpose chatbot, people can now receive help from systems arranged as peers, specialists, or multiple agents with distinct roles. However, it remains unclear how these forms of plural LLM assistance affect human performance, confidence, and diversity of thought. We conducted two controlled experiments involving 562 participants to examine the effects of using multiple LLMs on mathematical problem-solving and writing. In a math task, participants worked with no LLM, an expert assistant, peer-like agents that surfaced common errors, or both an expert and a peer-like assistant. The expert-plus-peer condition produced the strongest unassisted post-task performance. In a writing task, participants wrote with no LLM, a single generalist assistant, or a pair of role-speci
arXiv:2603.22730v2 Announce Type: replace-cross Abstract: Pfeffer, Kr\"ugel, and Uhl (2025) report that OpenAI's reasoning model o1-mini produces more utilitarian responses to the trolley problem and footbridge dilemma than the non-reasoning model GPT-4o, and they raise the question whether growing reasoning capabilities bring about a "utilitarian turn" in LLMs. I extend their exploratory study in a direction they call for: with four current OpenAI models and systematic prompt variation. On the trolley dilemma, the hypothesized utilitarian turn is not confirmed. GPT-4o's low utilitarian rate reflects safety refusals triggered by the prompt's advisory framing rather than a deontological commitment; on reformulated prompt variants -- for instance, agent-neutral "Is it morally permissible...?" instead of advisory "Should I...?" -- all four models, reasoning or not, converge on utilitarian answers. The footbridge finding is partially confirmed: reasoning models tend to give more utilitaria
arXiv:2601.15485v3 Announce Type: replace-cross Abstract: Federal research funding shapes the direction, diversity, and impact of the US scientific enterprise. Large language models (LLMs) are rapidly diffusing into scientific practice, holding substantial promise while raising widespread concerns. Despite growing attention to AI use in scientific writing and evaluation, little is known about how the rise of LLMs is reshaping the public funding landscape. Here, we examine LLM involvement at key stages of the federal funding pipeline by combining two complementary data sources: confidential National Science Foundation (NSF) and National Institutes of Health (NIH) proposal submissions from two large US R1 universities, including funded, unfunded, and pending proposals, and the full population of publicly released NSF and NIH awards. We find that LLM use rises sharply beginning in 2023 and exhibits a bimodal distribution, indicating a clear split between minimal and substantive use. Acros
arXiv:2601.15291v2 Announce Type: replace-cross Abstract: Independent navigation is central to social participation and health for vulnerable populations. While historic cities such as Edinburgh often feature well-established public transport systems, urban accessibility challenges remain and are exacerbated by complex landscapes, especially for groups with multiple vulnerabilities such as the visually impaired elderly. With limited research examining how real-time data feeds and artificial intelligence in this context, we address this gap through a mixed-methods approach. Our spatio-temporal analyses make use of statistical and machine learning techniques to investigate network coverage, service patterns, and density profiles through live-recorded data. This is combined with a qualitative thematic analysis of semi-structured interviews with the target group, as well as links to spatial cognition theory. The results demonstrate the highly centralised nature of the city's transport syst
arXiv:2510.19098v2 Announce Type: replace-cross Abstract: Strategic classification examines how decision rules interact with agents who strategically adapt their features. Most existing models focus on maximizing predictive performance, assuming agents best respond to the learned classifier. However, real decision-making systems are rarely optimized solely for accuracy: ethical, economic, and institutional considerations often make some feature changes more desirable than others. At the same time, principals may wish to incentivize these changes fairly across heterogeneous agents. While prior work has studied causal structure between features, notions of desirability, and information disparities in isolation, this work initiates a unified treatment of these components within a single framework. We frame the problem as a constrained optimization problem that captures the trade-offs between optimality, desirability, and fairness. We provide theoretical guarantees on the principal's optim
arXiv:2506.23845v2 Announce Type: replace-cross Abstract: While sparse autoencoders (SAEs) have generated significant excitement, a series of negative results have added to skepticism about their usefulness. Here, we establish a conceptual distinction that reconciles competing narratives surrounding SAEs. We argue that even if SAEs may be less effective for \textit{acting on known concepts}, SAEs are especially powerful tools for \textit{discovering unknown concepts}. This distinction separates existing negative results from positive results, and suggests several classes of SAE applications. Specifically, we outline use cases for SAEs in (i) ML interpretability, explainability, fairness, auditing, and safety, and (ii) social and health sciences.
arXiv:2506.16898v2 Announce Type: replace-cross Abstract: Diffusion-based text-to-image models are increasingly used for urban analysis and scenario generation, but their geographic knowledge and representational biases remain poorly understood. We evaluate FLUX 1-schnell and Stable Diffusion 3.5-Large in the United States by generating 150 street-view images for each state, each state capital, and a generic "USA" prompt. Images are embedded with DINO-v2 ViT-S/14 and compared with Fr\'echet Inception Distance (FID). Pairwise FID clustering shows that geographically proximate states and capitals often group together, indicating implicit geographic structure. However, the generic ``USA'' prompt collapses this diversity into a metropolitan stereotype: frontier, desert, tropical, rural, and small-city environments are underrepresented or distant in FID space. These results show that diffusion models can encode fine-grained geography while still reproducing narrow national-scale visual ster
arXiv:2504.08152v2 Announce Type: replace-cross Abstract: Collective discourse and action are driven by collective minds. These shared semantic representations and related processes shape societal responses to critical societal challenges such as climate change and political upheavals. In online communities, collective minds are susceptible to the influences of editorial practices and community dynamics, making them vulnerable to manipulation. However, understanding these influences is difficult because of the limits of experimenting with and predicting complex social systems. Here, we develop a computational model of collective minds, calibrated and validated with data from 400 million comments across five U.S. online news platforms and a survey. Our model enables us to quantitatively describe and experiment with different editorial agenda-setting practices and aspects of community dynamics to understand how they shape the collective mind. We find that some editorial influences can be
arXiv:2605.30169v3 Announce Type: replace Abstract: As autonomous language model agents proliferate, forming an emerging agentic web with real-world consequences, what credibility signals can you use to decide whether to trust an unfamiliar agent in the wild and delegate to it? A natural governance intuition is to extend human identity verification and reputation mechanisms, from "Know Your Customer" and credit scores to "Know Your Agent" regimes. However, we argue that this analogy is fundamentally incomplete. Reputation mechanisms function both as social signals and as corrective feedback that sustain an equilibrium of trustworthy behavior, presuming a persistent identity associated with behavioral continuity, sanction sensitivity, and costly non-fungibility. Yet language model agents are ontologically dissociative: they are essentially an assemblage of mutable modules--foundation models, system prompts, tool-access policies, external memory, and, in some cases, a multi-agent system
arXiv:2603.29278v2 Announce Type: replace Abstract: There have been various attempts at token standards on numerous blockchain platforms today to fundamentally change the way assets are traded in the traditional capital markets, but there is a lack of research and resolution on regulatory issues that become the common foundation for interoperability and reusable standards. Our proposal, Regulatory Compliance Protocol (RCP), is based on the regulations and reports of 15 global financial institutions and standardizes recommendations and guidelines involving the overall asset tokenization of TradFi and DeFi into five regulatory groups: Traceability, Privacy, Enforceability, Finality and Tokenizability, compiling them into 31 items and presenting a benchmark for technology and standards as an underlying protocol. To review the legality and effectiveness of RCP, it was validated based on three tokenization and trading scenarios, and by benchmarking existing asset-tokenization standards (ERC
arXiv:2602.06371v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly deployed in multilingual contexts, yet their consistency across languages on politically sensitive topics remains understudied. This paper presents a systematic bilingual benchmark study examining how 17 LLMs respond to questions concerning the sovereignty of the Republic of China (Taiwan) when queried in Chinese versus English. We discover significant language bias -- the phenomenon where the same model produces substantively different political stances depending on the query language. Our findings reveal that 15 out of 17 tested models exhibit measurable language bias, with Chinese-origin models showing particularly severe issues including complete refusal to answer or explicit propagation of Chinese Communist Party (CCP) narratives. Notably, only GPT-4o Mini achieves a perfect 10/10 score in both languages. We propose novel metrics for quantifying language bias and consistency, includin
arXiv:2511.15620v2 Announce Type: replace Abstract: Robustness is a key requirement for high-risk AI systems under the EU Artificial Intelligence Act (AI Act). However, both its definition and assessment methods remain underspecified, leaving providers with little concrete direction on how to demonstrate compliance. This stems from the Act's horizontal approach, which establishes general obligations applicable across all AI systems, but leaves the task of providing technical guidance to harmonised standards. This paper investigates what it means for AI systems to be robust and illustrates the need for context-sensitive standardisation. We argue that robustness is not a fixed property of a system, but depends on which aspects of performance are expected to remain stable ("robustness of what"), the perturbations the system must withstand ("robustness to what") and the operational environment. We identify three contextual drivers--use case, data and model--that shape the relevant perturba
arXiv:2511.06148v4 Announce Type: replace Abstract: As large language models (LLMs) are adopted into frameworks that grant them the capacity to make real decisions, it is increasingly important to ensure that they are unbiased. In this paper, we argue that the predominant approach of simply removing existing biases from models is not enough. Using a paradigm from the psychology literature, we demonstrate that LLMs can spontaneously develop novel social biases about artificial demographic groups even when no inherent differences exist. These biases result in highly stratified task allocations, which are less fair than assignments by human participants and are exacerbated in newer and larger models. In humans, emergent biases like these have been shown to result from exploration-exploitation trade-offs, where the decision-maker explores too little, allowing early observations to strongly influence impressions about entire demographic groups. To alleviate this effect, we explore a series
arXiv:2509.14088v3 Announce Type: replace Abstract: Modern computing students often rely on both natural-language prompting and manual code editing to solve programming tasks. Yet we still lack a clear understanding of how these two modes are combined in practice, and how their usage varies with task complexity and student ability. In this paper, we investigate this through a large-scale study in an introductory programming course, collecting 13,305 interactions from 355 students during a three-day lab activity. Our analysis shows that students primarily use prompting to generate initial solutions, and then often enter short edit-run loops to refine their code following a failed execution. Student reflections confirm that prompting is helpful for structuring solutions, editing is effective for making targeted corrections, while both are useful for learning. We find that manual editing becomes more frequent as task complexity increases, but most edits remain concise, with many affecting
arXiv:2508.06577v3 Announce Type: replace Abstract: Participatory budgeting is a democratic innovation that allows citizens to propose and vote on public investment projects. To help organizers manage large volumes of submissions, we design and test privacy-preserving methods for algorithmic shortlisting. These algorithms predict which projects are likely to be funded using only project features and anonymous historical voting data. We demonstrate the limitations of a naive approach that uses a large language model to rank projects based on past success and propose a vote-based pipeline that enables state-of-the-art LLMs to perform on par with classical machine learning. Our findings indicate that user preferences in participatory budgeting are stable enough to allow algorithmic shortlisting to approximate an initial selection of projects effectively.
arXiv:2506.18133v2 Announce Type: replace Abstract: The need for developing model evaluations beyond static benchmarking, especially in the post-deployment phase, is now well-understood. At the same time, concerns about the concentration of power in deployed AI systems have sparked a keen interest in 'democratic' or 'public' AI. In this work, we bring these two ideas together by proposing mechanisms for aggregated individual reporting (AIR), a framework for post-deployment evaluation that relies on individual reports from the public. An AIR mechanism allows those who interact with a specific, deployed (AI) system to report when they feel that they may have experienced something problematic; these reports are then aggregated over time, with the goal of evaluating the relevant system in a fine-grained manner. This position paper argues that individual experiences should be understood as an integral part of post-deployment evaluation, and that the scope of our proposed aggregated individu
arXiv:2506.13385v2 Announce Type: replace Abstract: Human mobility shapes access to resources, opportunities, and services, making movement data a powerful lens for studying spatial and social inequality. Yet despite the growing availability of official open mobility datasets, their research potential is rarely realized because the technical overhead of retrieving, harmonizing, and processing them often crowds out substantive analysis. To address this, we introduce pySpainMobility, a Python package that automates the retrieval and harmonization of Spain's open mobility data across spatial resolutions and demographic strata, streamlining national-scale, reproducible analysis. Using the package, we study income-stratified mobility inequality across Spain's inter-province network, drawing on district-level origin-destination flows for four representative weeks spanning the seasons of 2023. We construct income-specific mobility layers and show that socioeconomic stratification is deeply em
arXiv:2505.02519v2 Announce Type: replace Abstract: This paper explores the interplay of AI language technologies, sign language interpreting, and linguistic access, highlighting the complex interdependencies shaping access frameworks and the tradeoffs these technologies bring. While AI tools promise innovation, they also perpetuate biases, reinforce technoableism, and deepen inequalities through systemic and design flaws. The historical and contemporary privileging of sign language interpreting as the dominant access model, and the broader inclusion ideologies it reflects, shape AIs development and deployment, often sidelining deaf languaging practices and introducing new forms of linguistic subordination to technology. Drawing on Deaf Studies, Sign Language Interpreting Studies, and crip technoscience, this paper critiques the framing of AI as a substitute for interpreters and examines its implications for access hierarchies. It calls for deaf-led approaches to foster AI systems that
arXiv:2504.18236v4 Announce Type: replace Abstract: Explainability and its emerging counterpart contestability have become important normative and design principles for trustworthy AI as they enable users and subjects to understand and challenge AI decisions. However, realizing these principles is difficult, as they assume different meanings in technical, legal, and organizational dimensions of AI regulation. To resolve this conceptual polysemy, in this paper, we present the findings of an interview study with 14 experts to examine the intersection and implementation of explainability and contestability, and their understanding in different research communities. We outline differentiations between descriptive and normative explainability, judicial and non-judicial channels of contestation, and individual and collective contestation action. We further describe the main points of friction in the realization of both principles, including the alignment between top-down and bottom-up regula
arXiv:2501.14750v3 Announce Type: replace Abstract: Carbon emissions significantly contribute to climate change, and carbon credits have emerged as a key tool for mitigating environmental damage and helping organizations manage their carbon footprint. Despite their growing importance across sectors, fully leveraging carbon credits remains challenging. This study explores engineering practices and fintech solutions to enhance carbon emission management. We first review the negative impacts of carbon emission non-disclosure, revealing its adverse effects on financial stability and market value. Organizations are encouraged to actively manage emissions and disclose relevant data to mitigate risks. Next, we analyze factors influencing carbon prices and review advanced prediction algorithms that optimize carbon credit purchasing strategies, reducing costs and improving efficiency. Additionally, we examine corporate carbon emission prediction models, which offer accurate performance assessme
arXiv:2607.05203v1 Announce Type: cross Abstract: The rise of social media financial influencers (finfluencers) has transformed how financial information is disseminated to broad and often inexperienced audiences. While these creators may contribute to financial literacy, concerns remain regarding the reliability of their content and the adequacy of risk disclosures. Using data collected through TikTok's Research API, we analyze UK finfluencer content, engagement dynamics, disclaimer practices, audience sentiment, and network structure. The primary dataset comprises 13,215 videos and 104,097 comments posted by 71 UK-based finfluencers between April and September 2024, while a follow-up dataset covering October 2025 to March 2026 enables longitudinal analysis of disclaimer practices, engagement trends, and hashtag usage. Using topic modeling, we identify four dominant themes: Entrepreneurship \& Side Hustles, Property Investing, Active Trading, and Saving \& Budgeting. Sentiment analysi
arXiv:2607.05113v1 Announce Type: cross Abstract: Imagine two users interact with the same LLM. One has been told it is the cutting-edge flagship model; the other, an older, weaker model. They walk away with markedly different ratings of its usefulness and intelligence, yet they used the same model. In a controlled study, 162 participants each used one of six LLMs from two families across three collaborative tasks, after first viewing a landing page that matched, overstated, or understated their model's true capability. This pre-interaction framing shifted user opinions and interaction behavior while task performance did not. Oversold users rated the model more favorably and used more directive prompting, while Undersold users wrote longer, more collaborative prompts. The quality of what users and the model produced together depended only on the model's true capability, not on what users were told. Participants' change in model impressions after use, measured across two impression meas
arXiv:2607.05068v1 Announce Type: cross Abstract: As Generative AI (GenAI) becomes increasingly central to software development, CS education is integrating prompt-centered workflows where students describe intended program behavior in natural language to elicit code. However, professional practice requires careful review and verification of GenAI-generated code that may appear correct while containing subtle faults. This creates a challenge for CS1-level activities, where current models often solve tasks correctly and reduce students' incentive to closely inspect generated outputs. We investigate how prompt-centered programming activities can be adapted to better foster these practices. Specifically, we explore an approach where realistic, runnable bugs are injected into otherwise correct solutions, thus requiring students to read and repair generated outputs. We analyzed 2,636 sessions from 917 students, and examined behavior across instances of naturally occurring prompt-related fai
arXiv:2607.05052v1 Announce Type: cross Abstract: Human value detection is commonly formulated as sentence-level multi-label classification over the 19 refined Schwartz values, typically predicted as independent labels. Schwartz theory, however, describes them as a circular motivational continuum, in which adjacent values are compatible and opposing values are in tension. We ask whether this structure can be operationalized as an explicit output-space geometry and used as a soft bias rather than a hard constraint. On a DeBERTa-v3-base classifier, we compare two ways of injecting it: training-time geometry-aware objectives and a post-hoc Schwartz-aware energy decoder that scores whole label sets jointly. Across five seeds, training-time geometry gives only limited gains-no larger for the true continuum than for a random ordering-whereas the decoder makes label sets more coherent with the continuum-on theory-aware coherence metrics we introduce-at no cost to Macro-F1 or Micro-F1 (held fi
arXiv:2607.04708v1 Announce Type: cross Abstract: Agentic AI is shifting online shopping from search toward delegated purchasing, where autonomous buying agents monitor markets and decide when to buy on a consumer's behalf. We study the design of such strategic buying agents, which must decide when to purchase within a finite shopping window, translating price observations, the remaining time horizon, and beliefs about future price changes into a purchase policy. We formulate this problem across three information regimes: stationary, Bayesian, and robust, and treat the resulting optimal policies as a policy menu for implementation. In the stationary regime, price adjustments follow a Poisson arrival process with a known post-adjustment price distribution; the optimal policy is a dynamic purchase-threshold rule, with the threshold governed by an ordinary differential equation. In the Bayesian regime, the adjustment intensity is known, but the price-adjustment distribution is uncertain;
arXiv:2607.04576v1 Announce Type: cross Abstract: LLM agents increasingly answer questions against knowledge bases they help maintain. A common intuition holds that progressive disclosure, a compact catalog plus a one-line summary per page so the agent loads only what it needs, should make this cheaper than consulting a large monolithic index. We test that on a real 709-page markdown wiki maintained by an LLM. We retrofit it for progressive disclosure and run a preregistered ablation in which four versions of the corpus differ only in how the agent reaches the content: page bodies are byte-identical across arms, frozen as immutable git tags, so any measured difference is due to access structure alone. We cross the arms with three access conditions (a protocol-constrained agent, a free self-routing agent, and a catalog-preload regime) and grade answers blind against verified gold references with a cross-family judge. A pilot upended the premise: a capable tool-using agent never loads th
arXiv:2607.04510v1 Announce Type: cross Abstract: Emergent misalignment (EM) -- the broad misbehaviour a language model acquires after fine-tuning on narrow harmful data -- is mediated in Qwen2.5 models by a latent persona direction, and that direction is causal in open weights. Transplanting it into a model that shares only pretraining with its source induces broad EM (2.83 +/- 0.26% misaligned against a random-direction floor of ~1.1%), and ablating a model's own direction roughly halves an overt inducer's broadcast (21% to 10%). The transplant doubles as a measurement method, causally assaying directions that a source model represents but cannot itself express. Whether a fine-tune recruits this persona depends on method and capacity, and since low-rank PEFT is the cheaper regime at scale, the recruiting method is also the economical one. On Qwen2.5-32B, low-rank LoRA on insecure code recruits it (3.4% misaligned) while full SFT on identical data does not (0.3%) and moves against the
arXiv:2607.04381v1 Announce Type: cross Abstract: Research-based digital health interventions are often presented as potential solutions for extending health care in the real world. Yet the vast majority of these interventions fails to move beyond controlled studies. Existing frameworks offer valuable guidance for intervention development and testing, but provide less concrete support for translating these evidenced intervention mechanisms into sustained real-world applications. This paper introduces the ABC framework, referring to Accessibility, Buildability, and Continuity, as a practical model for a successful translation. Accessibility captures whether diverse users can find, understand, and begin using an application with minimal friction. Buildability refers to the development of an app that supports the iteration, integration, and personalization of features. Continuity describes both sustained user engagement and the operational capacity to maintain an application over time wit
arXiv:2607.04282v1 Announce Type: cross Abstract: Classic models cast information seeking as iterative foraging: formulate a keyword query, scan results, reformulate, gather across sources, synthesize. We ask what happens when a conversational assistant is inserted into that episode. Linking real conversations with major assistants to the same users' searches and browsing in an opt-in cross-surface panel, and reconstructing the full episode rather than a single query, we find conversational AI changes the shape of information seeking, not merely its volume. AI episodes do not uniformly collapse; they bifurcate. Most terminate in place, with no onward search or content step in the observed trace, while roughly a third scaffold into longer multi-step journeys. Which shape occurs is governed less by task type than by articulation: collapse is statistically indistinguishable across lookup, learning, and comparison episodes, yet falls monotonically with opening-ask length, from 72% at one-t
arXiv:2607.04010v1 Announce Type: cross Abstract: Bangladesh has an estimated 1.17 mental-health professionals per 100,000 population and only six child psychiatrists nationwide. No Bengali-language, culturally adapted tool exists for early screening of abuse-related psychological trauma in children. We present ShishuRaksha AI, a decision-support (not diagnostic) framework that fuses four screening modalities: validated questionnaires (SDQ, CPSS), Bengali narrative text, House-Tree-Person (HTP) drawing features, and facial affect. The fusion is training-free and clinically weighted, uses cross-modal attention, and includes a single-modality override rule. Every risk score is explained through clinically weighted, perturbation-based additive attribution and rendered as a bilingual (Bangla/English) report with referral routing to national child-protection services (OCC, DSS, NMHH) under the Children Act 2013. No clinical dataset of abused children can be collected ethically at this stage
arXiv:2607.03591v1 Announce Type: cross Abstract: Recent studies on multimodal traffic accident understanding have mainly relied on infrastructure-camera footage, satellite imagery, or structured crash records. However, such data sources are costly to deploy and maintain at large scale, and they cannot objectively capture what the driver was actually able to observe before the accident. In contrast, ego-view accident videos directly represent the driver's visual perspective, making them suitable for reasoning about avoidability and driver responsibility. In this paper, we introduce responsibility distribution estimation for ego-view traffic accident videos, a new task in which a model predicts the percentage of responsibility assigned to each involved agent. We construct an LLM-assisted responsibility annotation pipeline and fine-tune multimodal large language models under multiple input settings, including raw frames, segmentation-enhanced input, and textual descriptions. Experimental
arXiv:2607.03516v1 Announce Type: cross Abstract: Enterprise artificial intelligence is moving from isolated experimentation toward operational dependency across copilots, retrieval-augmented generation systems, autonomous agents, and AI-enabled business workflows. As this transition accelerates, the primary enterprise challenge is no longer only model access or inference scale. It is governed intelligence operations: the ability to enforce authorization, preserve contextual lineage, control persistent memory, detect stale or conflicting knowledge, constrain agentic execution, and produce audit-ready evidence across distributed AI estates. This paper introduces AGL-1, the Enterprise AI Governance Layer, as a vendor-neutral reference model for the control plane that should operate across foundation models, retrieval systems, orchestration frameworks, enterprise memory, policy engines, observability systems, tools, APIs, and business applications. Building on governed knowledge-system pr
arXiv:2607.03510v1 Announce Type: cross Abstract: Enterprise artificial intelligence is moving from experimentation into operational workflows. Early programs focused on model access and retrieval-augmented generation, but enterprises are now beginning to deploy agents that plan, retrieve, remember, call tools, update systems, and coordinate work across applications. This changes the evaluation problem. Leaders are no longer asking only whether an answer is accurate or fluent. They need to know who authorized an action, which policy applied, whether evidence was current, whether memory was valid, whether a tool call was permitted, whether the decision can be replayed, and whether the agent can be stopped before it creates business impact. This paper introduces CAGE-1: Control, Assurance, and Governance Evaluation for Enterprise Agentic AI. CAGE-1 is an evaluation framework for deciding whether enterprise agents are ready for deployment. It evaluates authority, policy enforcement, retri
arXiv:2607.03394v1 Announce Type: cross Abstract: Real time location data derived from mobile applications is a powerful tool for addressing various urban challenges, including tourism planning, parking management, bus route optimization, and resource allocation. Besides, it offers invaluable insights for shaping strategic decisions in commercial domains such as location based services, market share analysis, and behavioral profiling. In this expansive study, we aim to address all of the aforementioned challenges by investigating the behaviors and patterns of smartphone users within urban environments, particularly in the domains of tourism, transportation, and retail. Our approach encompasses the development of a sophisticated data platform from inception to implementation, which includes the formulation of use cases, architectural design, and implementation of modules. We employ state of the art techniques and technologies, including data anonymization, ETL pipelines, and utilizing G
arXiv:2607.03091v1 Announce Type: cross Abstract: Silicon sampling-using large language models (LLMs) to simulate human survey respondents-has emerged as a promising approach for augmenting traditional survey research. However, most evaluations rely on distributional comparisons rather than individual-level prediction, which risks conflating pattern matching with coherent respondent-level prediction. We propose cross-survey transfer, a more rigorous evaluation framework in which an LLM is given a respondent's answers to one set of questions and must predict their answers to entirely different questions from the same survey. Using data from the Taiwan Election and Democratization Study (TEDS) 2024, three open-weight LLMs (27B-120B parameters), and supervised machine learning baselines, we find that: (1) zero-shot LLMs achieve 52% accuracy on genuinely unseen items, closing to within 6 percentage points (pp) of a supervised random forest trained on same-population data; (2) a stable cons
arXiv:2607.03023v1 Announce Type: cross Abstract: User experience (UX) designers face barriers when creating data visualizations due to limited domain expertise in visualization or unfamiliarity with specialized tools. This highlights a clear need for effective methods to build visualization literacy. To address this, we evaluated three visualization onboarding techniques -- static, scrollytelling, and chatbot -- in an experimental study with 25 UX designers and students. We measured visualization comprehension and guideline adherence during a visualization creation task, followed by surveys and interviews to capture preferences and experiences. Compared to static onboarding, the pooled interactive condition (scrollytelling or chatbot) was associated with significantly higher guideline-adherence scores during visualization creation; both interactive techniques also received higher engagement ratings. Instruction clarity ratings were significantly higher when the two interactive conditi
arXiv:2607.03001v1 Announce Type: cross Abstract: We present CAF\'E, a learning platform designed to introduce computer science students to Formal Methods (FM). CAF\'E aims to scaffold students' structural thinking (in contrast with operational thinking) by promoting the practice of Graphical Loop Invariant Based Programming (GLIBP). In the GLIBP approach, students solve loop-based problems by first constructing a Graphical Loop Invariant (GLI) before deriving the corresponding code. The GLI is an informal diagrammatic representation of the loop invariant. It illustrates the variables involved in the loop, their properties, and the relationships between them. To enable automated feedback, students complete a blank GLI, a box-based version of the GLI. Beyond evaluating the code students submit, CAF\'E provides personalized feedback on students' GLI and its alignment with the code. In this demo, we walk through CAFE from both a student's and a teacher's perspective. We show how the tool
arXiv:2607.02900v1 Announce Type: cross Abstract: On social media, many users actively push back against false claims. Understanding who pushes back and how they do so matters, as this corrective activity is central to how misinformation is contested. We study this counter-misinformation ecosystem at scale: applying a domain-specific NLI model from our prior work to a large corpus of COVID-19 tweets, we classify 264,737 posts as supporting or opposing false claims and compare 23 user- and text-level features across the two groups. Contrary to the dominant assumption that negative emotion is a signature of falsehood, we find that anti-misinformation posts are more emotionally negative than pro-misinformation posts, with higher levels of anger, disgust, and sadness. These differences are modest in magnitude but consistent in direction across the negative emotions. We also find that posts opposing misinformation tend to come from more established users, i.e., older accounts, more follower
arXiv:2607.02814v1 Announce Type: cross Abstract: Personal agents will increasingly negotiate on behalf of users: splitting costs with other personal agents, appealing platform decisions, escalating support disputes, requesting refunds, changing subscriptions, and negotiating deadlines or reimbursements. Existing negotiation benchmarks emphasize agreement, surplus, or strategic competence, but a user-owned agent can reach an agreement while harming the user through privacy leakage, consent violation, unsupported advocacy, over-concession, failed escalation, or poor auditability. We introduce SovereignNegotiation-Bench, a trace-level multi-turn benchmark for delegated personal-agent negotiation under private utilities, disclosure constraints, evidence requirements, and institutional asymmetry. The benchmark separates agent-visible observable state from evaluator-only labels and evaluates agreement success jointly with user utility, privacy, consent, evidence grounding, concession discip
arXiv:2607.02724v1 Announce Type: cross Abstract: Reliable internet access is essential for modern education, yet millions of school-aged children especially in developing regions remain offline due to unconnected schools. The Giga Initiative aims to connect every school to the internet, but doing so at scale requires efficient methods to map schools and assess surrounding connectivity infrastructure without relying on sparse or noisy third-party datasets. In this work, we propose a scalable, vision-only framework that uses high-resolution satellite imagery and transfer learning to address both tasks simultaneously. By adapting pre-trained object detection models to new geographical regions with minimal labeled data, we detect schools and cell towers directly from space. We then analyze the spatial relationship between detected schools and nearby towers as a proxy for connectivity availability. This purely imagery-driven pipeline enables large-scale infrastructure mapping, reduces depe
arXiv:2607.02723v1 Announce Type: cross Abstract: Generative artificial intelligence (GenAI) systems such as ChatGPT, Claude, and Gemini have made information seeking faster, more conversational, and more cognitively comfortable. These affordances can support learning and productivity, but they can also encourage a repetitive pattern in which users continue querying AI systems for explanations, summaries, comparisons, plans, and reassurance without converting those interactions into durable understanding, decisions, or finished work. This conceptual paper proposes the term doom researching to describe this AI-mediated pattern of repetitive information seeking without proportional synthesis or output. Building on research on doomscrolling, information seeking, cognitive offloading, transactive memory, human-AI interaction, productivity loss, and the illusion of knowing, the paper develops a framework in which fluent AI responses reduce cognitive effort, inflate perceived knowledge, and
arXiv:2607.02672v1 Announce Type: cross Abstract: Local pairwise comparisons are a standard tool for learning how people want decision rules to work, e.g., in participatory design or alignment. However, their use builds in two strong assumptions: that local comparisons are sufficient evidence about how a person wants an automated decision rule to behave, and that people can always answer those comparisons decisively. We investigate how these assumptions may be compromised under internal pluralism: the idea that an individual evaluates decision rules according to multiple authoritative priorities about how the rule should behave. We provide a formal model of such pluralistic preferences over decision rules, which then lets us identify two distinct failures of forced local pairwise comparison data. First, priorities such as proportionality, egalitarianism, and equal treatment are inherently global: what they imply in one case can depend on what happens elsewhere, so local comparisons may
arXiv:2607.02580v1 Announce Type: cross Abstract: Classroom behavior monitoring plays a vital role in evaluating student engagement and improving teaching effectiveness. Traditional observation methods remain subjective and lack scalability. This study introduces a real-world dataset of classroom videos collected at the Banking Academy of Vietnam (BAV-Classroom dataset), annotated with nine distinctive behavioral categories. State-of-the-art Computer Vision models were evaluated and compared, with YOLOv11 achieving the best performance. Experimental results indicate that students' concentration often decreases notably during the final part of lectures, highlighting challenges in sustaining engagement. Our findings demonstrate the feasibility of applying computer vision for automated classroom monitoring, providing valuable insights for academic quality management.