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:2606.26117v1 Announce Type: new Abstract: This paper introduces the Governance Inversion Hypothesis (GIH) to explain a growing paradox in artificial intelligence (AI) governance: under conditions of increasing regulatory expansion and technological complexity, organisations may become more formally governed while simultaneously experiencing a decline in operational control over AI systems. Existing AI governance frameworks generally assume that stronger regulation improves accountability, oversight, and organisational control. This paper challenges that assumption by arguing that governance formalisation itself may contribute to the erosion of control in AI-intensive environments. Drawing on institutional theory, organisational governance research, accountability scholarship, and emerging AI governance literature, the paper develops a conceptual framework explaining how regulatory expansion may weaken operational authority through four interconnected mechanisms: authority fragmen
arXiv:2606.26116v1 Announce Type: new Abstract: A brand whose customers use both ChatGPT and Claude for product recommendations faces a strategic choice: a single optimization playbook, or one per provider? Across 215 commercially-framed prompts in four measurement batches, the two providers disagree on which brands they recommend roughly two-thirds of the time (cross-provider recommendation Jaccard 0.35, below the 0.50-0.61 same-prompt rerun baseline). The picks diverge. But when neither provider recommends a brand, we classify the failure into one of three modes -- discoverability (the brand never reaches the model), compellingness (it reaches the model but isn't mentioned), or positioning (it's mentioned but not recommended) -- and on 7,763 such joint failures, both providers diagnose the same failure mode 95.1% of the time (clustered 95% CI [94.3%, 95.7%]). Agreement rises monotonically with falling brand prominence, from 81% [78.2%, 84.0%] on category leaders to 99.6% [99.3%, 99.9
arXiv:2606.26115v1 Announce Type: new Abstract: This paper proposes a multi-layer AI framework for information landscape analysis in the context of information disorder. Rather than treating misinformation detection as a binary fact-checking task, the framework analyzes political and media content across multiple dimensions, including source reliability, factual structure, framing, bias, emotional activation, manipulation patterns, and propagation dynamics. The goal is to move beyond isolated claim verification toward a structured representation of the informational environment surrounding an event, entity, or narrative. We argue that AI systems for media analysis should support epistemic mapping: a transparent, multi-dimensional account of how facts, interpretations, actors, and narratives interact over time. The paper presents the conceptual architecture, analytical layers, and methodological rationale of the framework, with the aim of supporting more nuanced, explainable, and critic
arXiv:2606.26114v1 Announce Type: new Abstract: We examine the structural transformation of creative industries under generative artificial intelligence, drawing on 374 primary sources spanning policy documents, industry data, creator surveys, and platform analytics. Beginning with the December 2024 release of OpenAI's Sora video model as a watershed event, we trace the historical pattern of creative resistance to technological disruption, then develop an analytical framework -- the Human-AI Agency Continuum for mapping the spectrum of human and machine collaboration in creative work. We present evidence for the "slop ceiling," an audience-imposed quality threshold that constrains AI-generated content to approximately 1--3% of platform streams despite comprising 44% of uploads. Analysis of the UK Government's 2025 consultation on AI and copyright (over 11,500 responses, 88% opposing expanded AI training rights) reveals deep structural tensions between technology firms and creative work
arXiv:2606.26111v1 Announce Type: new Abstract: Generative artificial intelligence (GenAI) has enabled users to synthesize music with text prompts, combining copyrighted lyrics, AI-composed melodies, and synthetic vocals that imitate real artists. This paper examines the legal and technical dimensions of AI-based music creation (e.g., Google Gemini's music tools) under U.S. copyright law. We analyze whether a user who inputs one artist's protected lyrics into a GenAI system, directs it to use another artist's voice or style, publishes the resulting song, and monetizes it violates 17 U.S.C. Section 106's exclusive rights [3]. The analysis integrates Title 17 doctrine (rights of reproduction, derivative works, distribution), 17 U.S.C. Section 114's narrow sound recording protection [4], and the new voice-cloning laws emerging at the state level [20]. We argue that unauthorized lyric copying poses a high risk of infringement of the musical composition, whereas mere AI-generated voice imit
arXiv:2606.26109v1 Announce Type: new Abstract: Large language model (LLM)-based simulations of clinical patients are increasingly used for research and training, yet their validity requires persona stability: coherent maintenance of an assigned psychological profile across and within conversations. We evaluate this prerequisite using eating disorder personas grounded in five published case vignettes, a dual-assessment framework (self-report + independent observer ratings), and validated psychometric instruments (EDE-Q) with known ground-truth scores. Across six LLMs and two experiments (between-conversation stability (Exp. I) and within-conversation stability (Exp. II)), we find that LLMs are paradoxically too stable and too inaccurate: variability is negligible, yet all models systematically overshoot ground-truth severity by 12-30% of the scale range (0.7-1.8 points on a 0-6 scale). The mechanism is selective stereotyping: models differentiate cases on behavioural items (dietary res
arXiv:2606.26099v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in artificial intelligence (AI) governance analysis across national and international organisations. There is, however, growing evidence that such models produce significantly less accurate responses for countries that are underrepresented in their training data-a pattern described in existing literature as geographic bias. Existing studies examining this phenomenon are subject to three methodological limitations that together undermine their findings: (1) reliance on proprietary systems whose weights are not publicly released, which prevents independent replication; (2) evaluation of model knowledge about years that fall after data collection for model training had concluded, leading to geographic ignorance in addition to the natural limits of each model's knowledge; and (3) use of coarse binary response classification that cannot distinguish models' confident fabrication (HF) from t
Article URL: https://restofworld.org/2026/edtech-funding-collapse-k12-startups-ai-workforce/ Comments URL: https://news.ycombinator.com/item?id=47887985 Points: 2 # Comments: 0
Flint offers personalized learning, using AI, across a range of subjects.
Article URL: http://startupworks.co/blog/2015/01/23/will-2015-be-year-medical-and-children-education-apps/ Comments URL: https://news.ycombinator.com/item?id=8934536 Points: 2 # Comments: 0
By proactively handling negative individuals, school leaders can create a psychologically safe learning environment for everyone.
Article URL: https://www.medrxiv.org/content/10.1101/2022.12.19.22283643v2 Comments URL: https://news.ycombinator.com/item?id=34461264 Points: 2 # Comments: 0
Article URL: https://gizmodo.com/norway-says-ai-aint-for-education-2000774320 Comments URL: https://news.ycombinator.com/item?id=48603216 Points: 4 # Comments: 2
For many adult learners, logging into a hybrid or asynchronous course is not the beginning of their day. It may come after a full shift at work, after helping children with homework, after managing caregiving responsibilities, or after years away from formal schooling. The post Belonging by design: Practical ways to support adult learners in hybrid and asynchronous courses appeared first on eCampus News .
AI may make it easier to manipulate athletic performance, but students often underestimate how easily it can be exposed
Article URL: https://www.mdpi.com/2078-2489/16/8/653 Comments URL: https://news.ycombinator.com/item?id=44915580 Points: 2 # Comments: 0
Article URL: https://www.youtube.com/watch?v=SgxpxSjD8zA Comments URL: https://news.ycombinator.com/item?id=45222312 Points: 1 # Comments: 0
Artificial intelligence promises big gains for faculty in higher education, including greater efficiencies and elevated learning outcomes. To realize the wins, professors need to get up to speed on the tools. While many are experimenting on their own, some institutions are taking steps to accelerate that learning. At Ventura College, a California community college, leaders recently stood up communities of practice around AI use. A CoP brings together individuals with a shared interest in a topic or technology; in this case, AI. The group then works together to learn more about the topic or…
In a K–12 setting, deepfakes hold a lot of power. These falsified images or videos, virtually impossible to identify with an untrained eye, can be wielded to harm educators’ reputations, cyberbully vulnerable students, and blackmail individuals and schools. With artificial intelligence image generation, the problem is growing rapidly. Super-realistic images can be created quickly and deployed easily, creating a concerning scalability. Faced with the malicious use of AI-generated images — both of students and school officials — leaders must redouble their efforts around deepfake detection,…
Lately, school-related data breaches seem to keep coming. PowerSchool and Canvas made major headlines this year. Countless smaller incidents may not hit the news, but they disrupt instruction and expose sensitive student data just the same. For K–12 IT leaders, threats to their district are inevitable. The question is whether their teams will be ready when those threats materialize. After years of conducting maturity assessments, working alongside district security teams and witnessing the aftermath of incidents, we can say with confidence that most districts aren’t there yet — not because…
Innovative Leader Award - Kimberly Zajac discusses why digital accessibility is important beyond compliance
Key points: The demographic cliff higher education has been warned about for years isn’t coming; it’s already here. The post-2008 ... Read more The post Why the old enrollment playbook no longer works appeared first on eCampus News .
Modern technology may be distracting, but it can also help busy teachers and their students read more this summer.
“The premise that cybersecurity is a back-office or administrative expense and that something might not happen — that needs to be changed,” says Fadi Fadhil, field CIO and director of field strategy at Palo Alto Networks. “CISOs and CIOs can steer that change by engaging in simplified conversations with university leadership. It’s a strategic effort, helping them understand how the investment reduces institutional risk.” When it comes to budgeting for their cybersecurity programs, higher education CISOs must overcome some unique hurdles, ranging from the federated nature of university IT…
Raising your hand in class and patiently waiting until you’re called before speaking. Sharing with classmates in a group project. Understanding what you’re feeling and how best to express it safely. These are a few examples of what social-emotional skills look like in the classroom. Social-emotional learning (SEL) houses a variety of skills, all of which have always been embedded in the K–12 experience. As recent research points more directly to the value of weaving these learning moments into the K–12 curriculum, educational technology has risen to meet the demands. The Evidence for Social-…
Article URL: https://twitter.com/gergelyorosz/status/2062861559009820976 Comments URL: https://news.ycombinator.com/item?id=48411421 Points: 10 # Comments: 1
On any given Tuesday afternoon, a dean at Morgan State University can pull live enrollment trend data without submitting a ticket, waiting for a report or following up with the IT department. At most higher education institutions, that same request can take about three weeks. The difference isn’t the data platform, however. It’s how the historically Black college is prioritizing data literacy. Timothy Summers, vice president of IT and CIO at the Baltimore-based institution, is betting the university’s artificial intelligence strategy on employees’ ability to effectively interpret, question…
The landscape for specialized colleges and universities such as art schools is shifting as higher education continues to evolve to fit emerging job markets and student interest. Founded in 1882, Cleveland Institute of Art continuously challenges itself to stay modern and relevant. Years ago, the school’s leadership had the vision to partner with the city to revitalize an area due for reinvigoration. The result was the Interactive Media Lab, which brings together the university, the city and private industry into a satellite campus that gives students and the community a space to…
Innovative Leader Award - Lauren Harwood of Dighton-Rehoboth Regional School District shares how she focuses her efforts on AI, CTE program, and cybersecurity
The recent ransomware incident involving Canvas has renewed attention on one of the most difficult decisions schools and technology providers can face: how to respond when sensitive student, faculty, or institutional data is stolen and threatened with public release. The post The Canvas ransomware attack shows why schools must focus on containment, not just recovery appeared first on eCampus News .
Universities are attempting to adapt to artificial intelligence while considering mostly the wrong questions. The post Before students use AI, they should prove they don’t need it appeared first on eCampus News .
arXiv:2606.22737v2 Announce Type: replace-cross Abstract: Before letting an agent operate over real context, can you prove it used the right evidence? GroundEval turns that question into a deterministic test of what the agent searched, fetched, cited, and was permitted to access. In one case study, two frontier LLM judges scored a plausible agent response 0.85 and higher. But the trace told a different story: the agent had never retrieved the artifact its answer depended on, yielding a GroundEval score of 0.000. We introduce GroundEval, a judge-free framework for evaluating agents against grounded, time-bounded, and access-controlled evidence. GroundEval uses a domain configuration to generate questions, lets the agent choose how to answer, and then scores both the final answer and the recorded trajectory that produced it. The benchmark targets three failures that LLM-as-judge evaluation struggles to detect: whether an agent checked before claiming absence, reasoned only from evidence
arXiv:2606.07591v4 Announce Type: replace-cross Abstract: AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We present ResearchClawBench, a benchmark for evaluating autonomous scientific research across 40 tasks from 10 scientific domains. Each task is grounded in a real published paper, provides related literature and raw data, and hides the target paper during evaluation. Expert-curated multimodal rubrics decompose the target scientific artifacts into weighted criteria, enabling evaluation of target-paper-level re-discovery while leaving room for new discovery. We evaluate seven autonomous research (auto-research) agents under a unified protocol and seventeen native LLMs through the lightweight ResearchHarness. Current systems remain far from reliable re-discovery: the strongest autonomous agent, Claude Code, averages 21.5, and the strongest ResearchHarness LLM, Claude-Opus-4.7, averages 20.7,
arXiv:2605.17450v2 Announce Type: replace-cross Abstract: As software systems grow increasingly complex, automated vulnerability repair (AVR) remains difficult because the materials available to a repair system are usually failure artifacts rather than repair guidance. Traditional analysis techniques can provide suspicious locations, reduced triggers, or constraints, but they are costly to configure across repositories and seldom directly actionable for patch generation. Recent LLM-based agents can edit and validate repository-level patches, and experience-based systems can reuse prior repair traces or demonstrations, but they still need current-instance evidence that turns a broad, symptom-level failure report into a concrete repair decision. We present ContraFix, an agentic AVR framework that constructs such evidence through contrastive runtime analysis. Starting from a failing witness, ContraFix generates nearby failing and non-failing variants, executes them through aligned probe s
arXiv:2604.26180v2 Announce Type: replace-cross Abstract: With recent semantic query processing engines, semantic aggregation has become a primitive operator, enabling the reduction of a relation into a natural language aggregate using an LLM. However, the resulting semantic aggregate may contain claims that are not grounded in the underlying relation. Verifying such claims is challenging: they often involve quantifiers, groupings, and comparisons over relations that far exceed LLM context windows and require a costly combination of semantic and symbolic processing. We present Evergreen, a system that recasts claim verification as a semantic query processing task with tailored optimizations and provenance capture. Evergreen compiles each claim into a declarative semantic verification query that can execute on the same query engine used to produce the aggregate. To reduce cost, Evergreen avoids unnecessary LLM calls through verification-aware optimizations, including early stopping, rel
arXiv:2604.21254v3 Announce Type: replace-cross Abstract: LLM architecture research generally aims to maximize model quality subject to fixed compute/latency budgets. However, many applications of interest such as edge and on-device deployment are further constrained by the model's memory footprint, thus motivating parameter-efficient architectures for language modeling. This paper describes a simple architecture that improves the parameter-efficiency of LLMs. Our architecture makes use of looped Transformers as a core primitive, which reuse Transformer layers across depth and are thus more parameter-efficient than ordinary (depth-matched) Transformers. We organize the looped Transformer into three blocks--begin, middle, and end blocks--where each block itself consists of multiple Transformer layers, and only the middle block is applied recurrently across depth. We augment the looped middle block with hyper-connections (Xie et al., 2026), which expand the residual stream into matrix-va
arXiv:2604.19775v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of reasoning, planning, and acting within interactive environments. Despite their growing capability to perform multi-step reasoning and decision-making tasks, internal mechanisms guiding their sequential behavior remain opaque. This paper presents a framework for interpreting the temporal evolution of concepts in LLM agents through a step-wise conformal lens. We introduce the conformal interpretability framework for temporal tasks, which combines step-wise reward modeling with conformal prediction to statistically label model's internal representation at each step as successful or failing. Linear probes are then trained on these representations to identify directions of temporal concepts - latent directions in the model's activation space that correspond to consistent notions of success, failure or reasoning drift. Experimental results on two si
arXiv:2604.14228v2 Announce Type: replace-cross Abstract: Claude Code is an agentic coding tool that can run shell commands, edit files, and call external services on behalf of the user. This study describes its architecture by analyzing the publicly available source code and comparing it with two independent open-source AI agent systems, OpenClaw and Hermes Agent, that answer many of similar or even the same design questions. Our analysis identifies five human values, philosophies, and needs that motivate the architecture: human decision authority, safety, security, and privacy, reliable execution, capability amplification, and contextual adaptability. We then trace them through thirteen design principles to implementation choices. The core of the system is a simple while-loop that calls the model, runs tools, and repeats. Most of the code, however, lives in the systems around this loop: a permission system with seven modes and an ML-based classifier, a five-layer compaction pipeline
arXiv:2604.09945v2 Announce Type: replace-cross Abstract: The rapid adoption of large vision-language models (LVLMs) in recent years has been accompanied by growing fairness concerns due to their propensity to reinforce harmful societal stereotypes. While significant attention has been paid to such fairness concerns in the context of social biases, relatively little prior work has examined the presence of stereotypes in LVLMs related to cultural contexts such as religion, nationality, and socioeconomic status. In this work, we aim to narrow this gap by investigating how cultural contexts depicted in images influence the judgments LVLMs make about a person's moral, ethical, and political values. We conduct a multi-dimensional analysis of such value judgments in nine LVLMs using counterfactual image sets, which depict the same person across different cultural contexts. Our evaluation framework pairs descriptive analyses (Moral Foundations Theory categorization, lexical analyses, and valu
arXiv:2603.29466v2 Announce Type: replace-cross Abstract: Existing methods for quantifying predictive uncertainty in neural networks are either computationally intractable for large language models or require access to training data that is typically unavailable. We derive a lightweight alternative through two approximations: a first-order Taylor expansion that expresses uncertainty in terms of the gradient of the prediction and the parameter covariance, and an isotropy assumption on the parameter covariance. Together, these yield epistemic uncertainty as the squared gradient norm and aleatoric uncertainty as the Bernoulli variance of the point prediction, from a single forward-backward pass through an unmodified pretrained model. We justify the isotropy assumption by showing that covariance estimates built from non-training data introduce structured distortions that isotropic covariance avoids, and that theoretical results on the spectral properties of large networks support the appro
arXiv:2603.02112v2 Announce Type: replace-cross Abstract: Modern language models reason within bounded context, an inherent constraint that poses a fundamental barrier to long-horizon reasoning. We identify recursion as a core principle for overcoming this barrier, and propose recursive models as a minimal realization, where the model can recursively invoke itself to solve subtasks in isolated contexts. We prove that any computable problem admits a recursive decomposition of reasoning in which each subtask requires only exponentially smaller active context than standard autoregressive models; this strictly surpasses any context management approach confined to a single sequence, such as summarization. We further generalize our framework to modern agentic systems with arbitrary context processing and control flows, and prove that recursive models can achieve optimal power within this broader class. Experimentally, we test two settings: fine-tuning a pretrained base model for recursive SA
arXiv:2602.22897v3 Announce Type: replace-cross Abstract: Human intelligence naturally intertwines omni-modal perception -- spanning vision, audio, and language -- with complex reasoning and tool usage to interact with the world. However, current multi-modal LLMs are primarily confined to bi-modal interactions (e.g., vision-language), lacking the unified cognitive capabilities required for general AI assistants. To bridge this gap, we introduce OmniGAIA, a comprehensive benchmark designed to evaluate omni-modal agents on tasks necessitating deep reasoning and multi-turn tool execution across video, audio, and image modalities. Constructed via a novel omni-modal event graph approach, OmniGAIA synthesizes complex, multi-hop queries derived from real-world data that require cross-modal reasoning and external tool integration. Furthermore, we propose OmniAtlas, a native omni-modal foundation agent under tool-integrated reasoning paradigm with active omni-modal perception. Trained on trajec
arXiv:2602.20459v2 Announce Type: replace-cross Abstract: Can AI systems trained on the existing scientific record forecast the advances that will follow? We introduce PreScience, a dataset and benchmark for scientific forecasting built around 98K recent AI research papers, together with companion papers covering author publication histories and citation links, yielding 502K papers in total. The resulting paper records include titles, abstracts, disambiguated author identities, influential references, topic labels, citation trajectories, and metadata snapshotted to respect temporal cutoffs. We instantiate seven exemplar tasks: five paper-anchored tasks -- contribution generation, collaborator prediction, prior work selection, citation count prediction, and future combination prediction -- and two aggregate topic trend forecasting variants. We develop baselines ranging from simple heuristics and embedding methods to frontier language models and agentic systems, and introduce LACER, an L
arXiv:2602.07267v2 Announce Type: replace-cross Abstract: Evaluating the real-world capabilities of AI systems requires grounding benchmark performance in human-interpretable measures of task difficulty. Existing approaches that rely on direct human task completion time annotations are costly, noisy, and difficult to scale across benchmarks. In this work, we propose BRIDGE, a unified psychometric framework that learns a latent difficulty scale from model responses and anchors it to human task completion time. Using a two-parameter logistic Item Response Theory model, we jointly estimate latent task difficulty and model capability from model performance data across multiple benchmarks. We demonstrate that latent task difficulty varies linearly with the logarithm of human completion time, allowing human task completion time to be inferred for new benchmarks from model performance alone. Leveraging this alignment, we forecast frontier model capabilities in terms of human task length and i
arXiv:2601.22710v2 Announce Type: replace-cross Abstract: Modern LLMs are increasingly accessed via black-box APIs, requiring users to transmit sensitive prompts, outputs, and fine-tuning data to external providers, creating a critical privacy risk at the API boundary. We introduce AlienLM, a deployable API-only \cradd{exposure-reduction layer that reduces plaintext exposure} by translating text into an Alien Language via a vocabulary-scale bijection, enabling lossless recovery on the client side. Using only standard fine-tuning APIs, Alien Adaptation Training (AAT) adapts target models to operate directly on alienized inputs. Across four LLM backbones and seven benchmarks, AlienLM retains over 81\% of plaintext-oracle performance on average, substantially outperforming random-bijection and character-level baselines. Under adversaries with access to model weights, corpus statistics, and learning-based inverse translation, recovery attacks reconstruct fewer than 0.22\% of alienized toke
arXiv:2601.02813v3 Announce Type: replace-cross Abstract: Aligning language models to qualitative behavioral traits, such as human-likeness, remains difficult because they are hard to define, measure, and optimize. As a result, improvements in human-like behavior are largely driven by scale or broad supervised training, rather than targeted alignment. We introduce Human Aligning LLMs (HAL), a framework for aligning language models to conversational human-likeness using an interpretable, data-driven reward. HAL derives explicit conversational traits from contrastive dialogue data, combines them into a compact scalar score, and uses this score as a transparent reward signal for alignment with standard preference optimization methods. Using this approach, we align models of varying sizes without affecting their overall performance. In large-scale Chatbot Arena-style human evaluations, a model aligned with HAL is more frequently perceived as human-like in conversation. Because HAL operates
arXiv:2512.07843v2 Announce Type: replace-cross Abstract: Scaling inference-time computation has enabled Large Language Models (LLMs) to achieve strong reasoning performance, but their inherently sequential decoding incurs substantial latency, motivating parallelization of the generation process. However, existing parallel reasoning approaches suffer from performance degradation compared to their sequential counterparts, and often rely on specialized inference engines. We introduce ThreadWeaver, a framework for adaptive parallel reasoning that matches the accuracy of comparably sized sequential reasoning models while significantly reducing inference latency via three key innovations: 1) a two-stage parallel trajectory generator that produces high-quality parallel chain-of-thought data for supervised fine-tuning; 2) a trie-based rollout design that enables parallel reasoning on any off-the-shelf autoregressive inference engine; and 3) a parallelization-aware reinforcement learning frame
arXiv:2511.10687v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) in multi-agent systems (MAS) have shown promise for complex tasks, yet current training methods lack principled ways to connect system-level evaluation with agent- and message-level learning. We propose a theoretical framework that unifies cooperative game-theoretic attribution with process reward modeling to transform system evaluation to agent credit to response-level signals. Unlike prior approaches that rely only on attribution (Shapley) or step-level labels (PRM), our method produces local, signed, and credit-conserving signals. In success cases, Shapley-based credit assignment fairly allocates outcomes across agents and is refined into per-message rewards that promote cooperation while discouraging redundancy or sabotage; in failure cases, first-error localization yields repair-aware preferences that penalize harmful steps while rewarding corrective attempts. The resulting signals are bounded,
arXiv:2510.04391v5 Announce Type: replace-cross Abstract: Mental imagery vividness is a stable individual trait, yet whether imagined scenarios share relational structure across human and synthetic large language model (LLM) populations remains unknown. We applied psychological network analysis to vividness ratings from two validated questionnaires: the Vividness of Visual Imagery Questionnaire (VVIQ-2) and the Plymouth Sensory Imagery Questionnaire (PSIQ), across geographically and linguistically distinct human samples (Florida, Poland, and London; total N = 2,743) and six large language models (LLMs; Gemma3-12B/27B, their quantization-aware counterparts, Llama3.3-70B, and Llama4-16x17B). Imagination networks were constructed as regularized partial correlation graphs, with node centrality and community structure compared across populations using Pearson correlations and the Adjusted Rand Index (ARI). Human networks showed robust cross-population centrality correlations for expected in
arXiv:2508.16674v2 Announce Type: replace-cross Abstract: Medical report understanding from real-world document images is essential for generating patient-facing explanations and enabling structured information exchange in clinical systems. Existing VLMs and LLMs have shown strong performance on document understanding, but structured understanding of medical reports remains insufficiently benchmarked. Therefore, we introduce MedRepBench, a benchmark with 1,925 de-identified Chinese medical report images spanning diverse departments, patient demographics, and acquisition formats. In MedRepBench, we mainly focus on report-grounded interpretation rather than evaluating diagnostic reasoning, treatment recommendation, or the integration of patient history. The interpretation is defined as structured extraction of report fields (e.g., item, value, unit, reference range, abnormal flag) plus a patient-facing explanation grounded strictly in the report content. The benchmark primarily evaluates