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:2608.03038v1 Announce Type: new Abstract: Statistical reasoning is multidimensional, yet evaluations of large language models (LLMs) typically emphasize response accuracy while overlooking how models construct and communicate statistical explanations. This study demonstrates the value of a multidimensional evaluation by combining response accuracy, response behavior, structural topic modeling, and lexical similarity analysis. The framework is applied to explanations generated by 15 current-generation LLMs responding to 90 questions drawn from four statistics examinations spanning high school, undergraduate, and graduate levels. Accuracy varied substantially across models, ranging from 55\% to 78\%. In contrast, structural topic modeling revealed a common conceptual organization of statistical reasoning across all models, while lexical similarity analysis identified modest but consistent vendor-specific differences in explanatory style. Models developed by the same vendor (e.g. An
arXiv:2608.03035v1 Announce Type: new Abstract: Prior work has shown that LLMs encode the truth of factual propositions along linear directions in activation space. It's unclear how these representations extend to contextual truth: propositions whose truth is determined by in-context evidence rather than world knowledge. We show that LLMs maintain a linear representation of contextual truth that persists across structurally different output policies, even when the output doesn't require the model to determine a proposition's truth, and show causal evidence via steering experiments. Using the transcripts from a collaborative vision-language task that requires two LLMs to maintain a shared common ground, we show that truth representations of a proposition are significantly swayed by partner assertions about that proposition, even when the LLM has enough evidence to determine its truth. We find evidence that propositions near the decision boundary are more susceptible to having their trut
arXiv:2608.02999v1 Announce Type: new Abstract: Statistical regularities are routinely offered as evidence that undeciphered sign systems encode language; the Indus script debate is the canonical example. Any such inference rests on specificity: the reported outcome must be unusual among plausible structured non-languages. We test that premise constructively with SIGIL, a purpose-built generative emblem system whose 3,000-text core corpus carries explicit compositional meanings although no sign has a phonological value. A literature registry compiled in advance of evaluation records 54 methods and admits a method to exact scoring when both the published Indus outcome and a source-defined decision rule can be reproduced. SIGIL receives the same category as the Indus corpus on every criterion scored this way, across repetition, directional-asymmetry, and lexical-distribution tests. Declared reconstructions of entropy, frequency, positional, predictive, classifier, and network measures re
arXiv:2608.02975v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated impressive performance in MQM-based translation quality (TQ) evaluation, and recent advances in large reasoning models (LRMs) promise even greater improvements. However, both LLMs and LRMs are computationally expensive to deploy at scale, while small language models (SLMs)---though much more efficient---struggle with the complex reasoning required for evaluation tasks. In this work, we present an extensive empirical study benchmarking SLMs, LLMs, and LRMs across a wide range of TQ evaluation setups, providing a comprehensive view of the current landscape and establishing best practices. To address the scalability challenge, we introduce TQLite, a novel distillation framework that enables SLMs to approach the MQM evaluation performance of the best LRM-based evaluators. Our approach leverages a multi-LRM jury to generate high-quality synthetic training data via practical data curation technique
arXiv:2608.02971v1 Announce Type: new Abstract: Language models often complete an underspecified reference to a city with unstated assumptions about urban size, form, infrastructure, environment, and function. We measure those assumptions without naming places. Ten open-weight checkpoints rate anonymized profiles derived from real morphological urban centres across 40 audited indicators and seven domains. The design combines constrained probability-based ratings, prespecified reliability screens, lineage-aware aggregation, multiple population weightings, an independent replication sample, and whole-profile validation. The clearest shared tendency favours urban profiles with larger developed area, faster recent growth, greater mapped infrastructure and non-residential capacity, and less sparse form. Most eligible directions recur in the replication data, and direct ratings of complete profiles show moderate agreement with the indicator-wise construction. Geographic differences shrink af
arXiv:2608.02966v1 Announce Type: new Abstract: Most multiple-choice question (MCQ) benchmarks evaluate Large Language Models (LLMs) only by whether they select the correct answers. This binary scoring treats all incorrect responses alike, even though an LLM's preferences among incorrect options may contain systematic and useful information about its behavior and ability. We introduce the LLM Nominal Response Model (LLM-NRM), an option-aware psychometric framework that models the full distribution over answer choices to jointly estimate LLM ability and option-level item characteristics, while separating model-specific response calibration sharpness, positional preference, and difficulty-dependent fallback behavior. Across 189 LLMs and 31,554 items from 14 benchmarks, LLM-NRM predicts held-out LLM-item interactions more accurately than binary Item Response models and conventional nominal-response baselines, and its ability estimates achieve the strongest Spearman correlation of 0.920 wi
arXiv:2608.02942v1 Announce Type: new Abstract: Diffusion language models (dLLMs) can predict many tokens in parallel, but accurate generation still requires many iterative denoising steps. Few-step distillation accelerates decoding by compressing multiple teacher steps into a single student transition. However, existing methods construct supervision on off-policy trajectories. At inference, the student's early parallel commitments alter the context of later predictions, so the states it actually visits drift away from the supervised ones--precisely when step compression is most aggressive. On-policy distillation is a natural remedy for this mismatch, but it leaves open how far each transition should advance: matching only the teacher's next action limits compression, while indiscriminately merging future actions can violate intermediate dependencies. To address this limitation, we propose OPTD, On-Policy Transition Distillation with consistency-guided adaptive compression. It samples
arXiv:2608.02941v1 Announce Type: new Abstract: We audit five frontier large language models on native Bangla derogatory speech (gali) across six protocols to test a single hypothesis: Comprehension-Containment Decoupling. We propose that contemporary safety alignment is bound to high-resource surface forms rather than harmful meaning, causing a model's capacity to comprehend a low-resource slur and its capacity to contain it to operate independently. Every protocol corroborates this hypothesis against a human-calibrated baseline (kappa = 0.84). At baseline, models exhibit a 7.92 percentage point comprehension deficit in Bangla while maintaining an identical 92.83% token leakage rate across both languages. Severity calibration tracks surface anatomical cues over compositional harm (+4.00 error on mild slang; -2.00 on threats), while apparent containment gains under orthographic perturbation prove to be a tokenizer-driven "containment mirage." Crucially, explicit Chain-of-Thought reason
arXiv:2608.02935v1 Announce Type: new Abstract: Arabic script uses 28 letters, many of which share a common base shape (rasm) and are distinguished only by dot placement. Because early Arabic manuscripts were written without dots yet remained interpretable, dot removal offers a natural test of whether these visual distinctions are functionally necessary. Prior work has shown that dotless Arabic can remain readable and effective for natural language processing (NLP), but it remains unclear whether this success depends on preserving the original rasm groupings or whether arbitrary but consistent remappings to the same reduced rasm set can achieve comparable performance. We address this question by comparing standard dotted and dotless Arabic with arbitrary character remappings constrained to the same 19 undotted rasms. We generated 2,000 random remappings under word- and character-level tokenization and selected four representative mappings with the highest and lowest entropy values. The
arXiv:2608.02919v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in complex, compound AI systems where performance hinges on the quality of prompts. Recent state-of-the-art optimizers like GEPA (Genetic-Pareto) have argued that reflective instruction evolution can outperform traditional reinforcement learning and few-shot optimization. In this work, we challenge this shift by introducing FLARE (Few-shot Learning-based Adaptive Reflective Engine), a framework that leverages advanced reflective mechanisms and a small set of few-shot reference examples to optimize instructions. We evaluate our method across a diverse suite of benchmarks -- spanning retrieval-augmented reasoning (HotPotQA, MedQA, 2WikiMultiHopQA), tool calling, and multi-label emotion classification (GoEmotions) -- using the GPT-5 series of models. Our results demonstrate that FLARE consistently outperforms GEPA, winning on every task-model pair: it achieves gains of up to +14.2 points
arXiv:2608.02867v1 Announce Type: new Abstract: Although reinforcement learning with verifiable rewards (RLVR) has improved the performance of large language models (LLMs) across a variety of reasoning tasks, there is significant debate as to whether RLVR expands the reasoning capability boundary, or just improves sampling efficiency. In this paper, we investigate the nature of test-time exploration in RLVR-trained LLMs by employing controlled maze-solving experiments and extracting a tree structure from mathematical reasoning traces (BODHI-Trees) based on semantic equivalence. This helps us delineate between entropy arising from stylistic variations and genuine inferential branching. Our findings demonstrate that the policy entropy collapse observed in RLVR models is not merely syntactic, and is accompanied by a significant reduction in semantic branching entropy. While RLVR improves adherence to environmental constraints and backtracking capabilities, it constricts the space of conti
arXiv:2608.02807v1 Announce Type: new Abstract: How can we better represent the impact of sociocultural structures on decision making in computational cognitive models? Modeling this impact requires traversing multiple levels of semantic representation, however it is not immediately clear to a modeler which levels of representation are most salient to a given situation. Though large language models and cognitively grounded corpus models can represent broad semantic associations through co-occurences, the role of self representations in memory should be accounted for to determine how cultural associations shape decision making. We propose a declarative memory system to be used in the ACT-R cognitive architecture that represents semantic associations at multiple levels via a vector-symbolic autoencoder. We use a simple HRR operation to encode episodic memories differently from semantic memory vectors extracted from text to produce a final chunk activation for a memory request. We use ACT
arXiv:2608.02703v1 Announce Type: new Abstract: Weight-only quantization substantially reduces the storage of large language model (LLM) transformer blocks, but practical backends often retain the final language-modeling head (LM-head) in BF16 or FP16. Quantizing this projection naively can strongly perturb the vocabulary-logit distribution. We present ARCHead, a packed LM-head compressor that combines a quantized low-rank core, group-wise INT4 residuals, and a low-rank correction fitted in an activation-derived metric. ARCHead stores no dense BF16 head and reduces persistent LM-head storage by 3.7-3.9x. On Qwen3-8B-Base, it uses 25.6% of BF16 head storage while attaining 1.007 relative perplexity; storage-matched naive INT4 yields 1.14-1.16. Replacing the BF16 head left by AWQ or bitsandbytes adds only 0.006-0.007 cross-entropy, with less than 2% throughput change in our measurements. ARCHead therefore complements block quantizers by compressing the large output projection they can le
arXiv:2608.02694v1 Announce Type: new Abstract: Long-horizon video editing agents receive final-product feedback only after many interdependent decisions. Yet editing quality is subjective, admits multiple valid solutions, and is not meaningfully calibrated across heterogeneous requests, making a global scalar objective both ambiguous and temporally uninformative. Our key observation is that fixing the request, materials, and production constraints converts this subjective objective into an ordinal comparison among directly comparable alternatives. We introduce Group-Relative Preference Backpropagation (GRPB), which transforms same-task rankings into zero-sum advantages and redistributes them as bounded credit over semantic editing segments. A lagged allocator and guarded transmission prevent current judgments or unreliable estimates from directly shaping the same rollout group. We manually construct a project-disjoint, horizon-stratified suite of realistic editing tasks for training a
arXiv:2608.02689v1 Announce Type: new Abstract: We convert 21 of 28 full-attention layers of Qwen3-0.6B-Base into KDA (Kimi Delta Attention) linear-attention layers on a single consumer-grade GPU budget, and ask a simple question: what exactly does the conversion break? After surgery, hidden-state alignment and end-to-end KL distillation drive the student close to its teacher in perplexity, yet multiple-choice accuracy stays near random chance (25-29% vs. the teacher's 50.6% on C-Eval). Using a four-permutation diagnostic that rotates answer options while holding content fixed, we show the model sticks to option labels (predicting "A" 81% of the time; 106/161 questions keep the same label under all four rotations) rather than following answer content -- an interface injury that standard distillation metrics cannot see. A 1,000-step format-targeted completion-only KL stage repairs the interface (+12.48 points on C-Eval, label-stickiness roughly halved), after which persona SFT and one r
arXiv:2608.02625v1 Announce Type: new Abstract: Diffusion language models (DLMs) can revise tokens bidirectionally, but standard decoding procedures often adapt them to left-to-right generation by producing text block by block. We study a simple plug-and-play inference pattern: first generate a complete draft, then refine the full response using bidirectional diffusion. Using LLaDA2.1-Flash and LLaDA2.1-Mini, we evaluate two configurations. In Flash-Flash, the same Flash model serves as both drafter and refiner, testing whether an existing model can improve its own block-autoregressive output through global refinement. In Mini-Flash, inspired by speculative decoding, we introduce speculative correction: Mini drafts a full response, and Flash revises it as an editable initialization. Flash-Flash improves GSM8K-384 accuracy from 0.848 to 0.899 while running 1.20 times faster than the selected Flash block-autoregressive baseline, and improves MBPP-384 from 0.545 to 0.693. Latency-window-m
arXiv:2608.02621v1 Announce Type: new Abstract: Legal benchmarks typically score final answers even when models also state legal authority. We test whether answer correctness can serve as a proxy for authority grounding. Under ordinary reasoning prompts that did not request statutory citations, four LLMs spontaneously produced authority markers across 238 Taiwan bar-examination items. Because each item has a verified governing provision, we automatically audit answer correctness and authority grounding jointly. The two dimensions dissociate in both directions. In criminal law, 24.0--42.4\% of valid responses were answer-correct but missed the gold authority, while 15.2--21.7\% were answer-incorrect but cited it. A separate statutory-retrieval probe and a permissive citation-abstention intervention further show that answer and citation behavior can move separately at the output level. Because this mismatch arises without adversarial or inconsistency-inducing prompting, answer-only scori
arXiv:2608.02620v1 Announce Type: new Abstract: LLM-as-a-judge evaluation has become a dominant paradigm for ranking language models, yet the ecosystem remains fragmented: most benchmarks ship their own code base, hardcode a specific closed-model judge, and support a single evaluation protocol. This fragmentation makes it difficult to study how design choices--the benchmark, the judge model, the prompt, the inference backend--affect the conclusions we draw about model quality. We introduce JudgeArena, an open-source framework that unifies major LLM-judge benchmarks (AlpacaEval, Arena-Hard, MT-Bench, and m-Arena-Hard) under a single interface with swappable judges and comprehensive metadata logging for increased transparency in reporting and reproducibility. It enables systematic studies of judge choices, as any model accessible via vLLM, llama.cpp, or OpenRouter can serve as both candidate and judge. Furthermore, JudgeArena ships with tuned judge configurations for open models that mat
arXiv:2608.02617v1 Announce Type: new Abstract: We evaluate whether clinician pairwise preferences provide a reliable signal of clinical safety in large language model (LLM) evaluation using expert feedback from MOOVE (Massive Open Online Validation and Evaluation), a clinician-led platform collecting blinded pairwise preferences alongside multi-criterion rubric ratings. Clinicians assign scores on a discrete $[-2, +2]$ scale, where negative values indicate clinically unsafe or misleading content. Using 26{,}804 pairwise judgments across outputs from 13 LLMs, contributed by more than 736 clinicians across 28+ countries, we find that clinician preference is a poor proxy for safety-critical performance. Models ranking highly under pairwise preference can still exhibit substantial rates of clinically meaningful failures ($\leq -1$) on dimensions such as \emph{Harmlessness} and \emph{Accuracy}. These failures are unevenly distributed across specialties, creating domain-specific ``no-go zon
arXiv:2608.02616v1 Announce Type: new Abstract: We present the first independent, systematic evaluation of OpenAI's Privacy Filter (OPF), a 1.5B-parameter bidirectional PII detector, across 42 synthetic benchmarks spanning 22 languages and 5 domains. Zero-shot, OPF achieves F1=0.855 on AI4Privacy and 0.464 on SPY medical, outperforming Presidio (0.431, 0.273) and XLM-RoBERTa (0.269, 0.111) on PII-annotated benchmarks; on multilingual NER, XLM-RoBERTa leads OPF on all 13 Indic and non-Latin languages. GPT-4o leads on medical, legal, and financial PII (SPY: 0.643 avg, Gretel: 0.527), while OPF leads on structured synthetic PII (0.71 avg) and customer support (0.60). OPF degrades sharply when PII is embedded in narrative prose: F1=0.04--0.57 on NER benchmarks and collapse for non-Latin scripts (Arabic: 0.04, Cyrillic: 0.03). Error analysis shows OPF is strongest on structurally regular PII types (email: 0.78, phone: 0.76) and weakest on culturally variable ones (person: 0.40, address: 0.4
arXiv:2608.02615v1 Announce Type: new Abstract: Cancer diagnosis and characterization require integrating complementary evidence from radiology, pathology, genomics, and clinical metadata. However, most medical large language model (LLM) and vision-language model (VLM) benchmarks focus on isolated modalities or narrow image-text tasks, leaving patient-level oncology assessment across multiple evidence streams largely untested. We introduce OncoTriad-QA, a patient-level radiology-pathology-genomics benchmark for pan-cancer question answering. OncoTriad-QA contains 86.1k semantic questions across 9,281 TCGA patient cases from 32 cancer cohorts, aligning CT/MRI radiology, whole-slide histopathology, somatic mutations, copy-number alterations, DNA methylation, bulk RNA-seq, and clinical metadata. Case-specific annotations are constructed through a source-grounded LLM-assisted pipeline using curated labels, diagnostic reports, molecular profiles, and modality-derived evidence as primary sou
arXiv:2608.02613v1 Announce Type: new Abstract: Edge-deployed personal memory assistants must handle private interpersonal conversations on-device with open-weight models. Yet, existing memory benchmarks often under-test the combination of activity-dense interaction, ego-centric perspective, and coherent multi-session worlds. MemArena fills these gaps with a single-world conversational benchmark built with its MASim agent simulator, for 50 agents over 15 days (10.3M dialog-text tokens, 24.1K text-only ego-observed tokens/agent/day). With the interaction history, it co-generates ground truth over six recall, reasoning, and trustworthiness evaluation dimensions. We evaluate five open-weight readers with Vanilla context, BM25-RAG, Oracle retrieval, Memobase, and MemSearch as memory backends. Three results stand out: (1) Memory-backend choice matters more for content accuracy: At Qwen3-0.6B, Memobase-to-MemSearch gains +32.5/+19.2 pp, exceeding MemSearch reader scaling (+10.6/+6.8 pp). (2)
arXiv:2608.02612v1 Announce Type: new Abstract: Formulating an optimization problem strongly affects the quality of the final solution, yet good formulations usually require substantial expertise. Recent studies have therefore examined how to automatically derive optimization problems from natural-language descriptions, but existing benchmarks focus on settings where objectives and constraints can be written explicitly as mathematical expressions. Many practically important problems are naturally treated as black-box optimization (BBO) problems, in which only objective values are observable, and the functional form is unavailable. In BBO, the search space design, a part of the problem formulation, and the selection of the optimization algorithm are crucial for problem-solving. Automating these processes with large language models (LLMs) is a significant challenge. This paper introduces Black-Box Optimization Word Problems (BBOWP), a novel problem setting in which a system must infer bo
arXiv:2608.02609v1 Announce Type: new Abstract: Half a million cuneiform clay tablets survive in museums worldwide, yet modern users can neither read nor write in the world's oldest writing system, leaving a 4,000-year cultural barrier that existing NLP tools have only partially addressed. Prior work enables one-way, scholar-oriented translation from Akkadian to English, but offers no path in the reverse direction: non-specialist users cannot compose new content in cuneiform, and therefore remain passive consumers of ancient culture rather than active participants. We present TabletCraft, the first open-source system that enables bidirectional interaction with Mesopotamian writing. Users can read ancient tablets (Akkadian to English) and compose new messages as cuneiform clay tablets (English to Akkadian to cuneiform to rendered tablet). The system integrates a ByT5-based translation model trained on 116K bidirectional samples, a cuneiform sign converter with 14,240 mappings (95.3% cov
arXiv:2608.00868v2 Announce Type: replace-cross Abstract: Many open educational resources are lacking in accessibility, especially in-depth image descriptions. In subjects like Science and Mathematics, however, it can be particularly difficult to write image descriptions since there can be many complicated expressions and names depending upon the course level. To help fill that gap in a small way, we introduce Math Image Descriptions for Accessible Learning (MIDAL), a math image-description dataset of 2,020 mathematical images spanning multiple educational levels, to aid in training vision language models to create image descriptions following accessibility best practices. We hope MIDAL is a valuable resource in enhancing the conversation and innovation regarding accessibility of STEM content in higher education. This dataset is however not just limited in math description generation but can also be used to fine-tune language models that can have improved mathematical reasoning and ans
arXiv:2603.20381v2 Announce Type: replace-cross Abstract: Understanding the fundamental mechanisms governing the production of meaning in the processing of natural language is critical for designing safe, thoughtful, engaging, and empowering human-agent interactions. If meaning is constituted rather than retrieved, then the search for context-independent features or circuits in the pursuit of mechanistic interpretability may be fundamentally limited. Experiments in cognitive science and social psychology have demonstrated that human semantic processing exhibits contextuality more consistent with quantum logical mechanisms than classical Boolean theories, and recent works have found similar results in large language models---in particular, clear violations of the Bell inequality in experiments of contextuality during interpretation of ambiguous expressions. In this work, we explore the CHSH $|S|$ parameter---the metric associated with the inequality---across the inference parameter spac
arXiv:2502.11140v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have become a cornerstone for automated visualization code generation, enabling users to create charts through natural language instructions. Despite improvements from techniques like few-shot prompting and query expansion, existing methods often struggle when requests are underspecified in actionable details (e.g., data preprocessing assumptions, solver or library choices, etc.), frequently necessitating manual intervention. To overcome these limitations, we propose VisPath: a Multi-Path Reasoning and Feedback-Driven Optimization Framework for Visualization Code Generation. VisPath handles underspecified queries through structured, multi-stage processing. It begins by using Chain-of-Thought (CoT) prompting to reformulate the initial user input, generating multiple extended queries in parallel to surface alternative plausible concretizations of the request. These queries then generate candidate visua
arXiv:2605.00240v2 Announce Type: replace Abstract: Thermal referral enables thermal sensations in locations lacking thermal actuators--this is achieved using vibrotactile actuators to redirect a nearby thermal sensation to where a tactile sensation is applied. However, we found that its reliance on vibration introduces critical limitations: it struggles to produce cold referral, and the inherent strong tactile "buzz" makes it unsuitable for simulating non-contact thermal events, such as the chill of an open freezer in VR (in contrast to contact-based thermal events like touching the freezer's cold handle). To improve this, we propose a shift from vibrotactile to electrotactile-based thermal referral. We evaluated in two user studies--a psychophysics experiment (N=22) and a VR deployment (N=20)--where we contrasted electrotactile with vibrotactile-based thermal referral. Our results reveal key advantages of the electrotactile based thermal referral: (1) increases the referral rate for
arXiv:2507.20720v3 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) are beginning to enable new user experiences from generated content across a range of media, including images, text, speech, and video. These capabilities have the potential to enrich learning by enabling users to interact with information using a variety of modalities, but little is known about how \textit{educators} envision how MLLMs might shape the future of learning, what challenges they encounter when using these models, and what practical needs should be considered for future implementation in educational contexts. We investigated educator perspectives through workshops with 12 K-12 educators, where participants brainstormed learning opportunities, discussed practical concerns, and prototyped MLLM learning applications using Claude 3.5 and its Artifacts feature. Through this work, we uncover how educators imagined MLLMs as a way for themselves and their students to author multimedia cont
arXiv:2608.03464v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have made significant progress in chart understanding, generation, and editing, but their ability to annotate existing charts remains underexplored. Annotating charts is a common yet challenging communicative task, requiring models to infer intended messages, interpret chart semantics, and place appropriate textual or graphical elements. To address this gap, we introduce ChartAnno, a benchmark for evaluating MLLMs on chart annotation generation. It contains 1,200 real-world charts with paired code and annotation instructions across three levels of instruction specificity. We evaluate 10 representative MLLMs under two primary input settings: (1) chart code alone and (2) both chart code and chart image, and further include a chart image-only ablation study. Results show that proprietary models remain stronger overall, although large-scale open-source models narrow the gap. More specific instruction
arXiv:2608.03462v1 Announce Type: cross Abstract: Context: The growing adoption of AI-assisted development tools is changing how software teams collaborate, share knowledge, and coordinate, yet its consequences for team social dynamics remain largely unexplored. Gap: It is unclear whether AI adoption is associated with an increase or reduction in community smells,socio-technical anti-patterns reflecting coordination and communication breakdowns,and through which mechanisms. Method: Grounded in Transactive Memory Systems (TMS) theory, we validate instruments for HumanAI and HumanHuman interaction along two TMS dimensions, Specialization and Coordination, and test five PLS-SEM models on survey data from 152 software professionals using AI tools. Community smell constructs were derived from the literature and validated through expert surveys and factor analysis. Results: AI adoption relates to community smells not in a single way, but through mechanisms depending on the work. In specializ
arXiv:2608.03176v1 Announce Type: cross Abstract: Imagined handwriting offers a temporally rich paradigm for non-invasive neural decoding, yet reliable recognition across unseen participants remains difficult because scalp EEG is noisy and internally generated stroke sequences vary across individuals. The Multimodal Brain-Computer Interface Grand Challenge provides synchronized EEG and fNIRS for four-class subject-independent handwriting-trajectory classification. We propose FRED, a task-adapted system that models imagined handwriting as a multi-second motor sequence and trains a compact multi-scale temporal network on three complementary EEG frequency views. With three seeds per view, cross-band members produce substantially less-correlated errors than same-band replicas, yielding a clean nine-member ensemble accuracy of 0.8076/0.7242/0.7492 on the public/private/overall test partitions without test-set adaptation or output constraints. The submitted pipeline further incorporates tran
arXiv:2608.03151v1 Announce Type: cross Abstract: Contactless keystroke inference via WiFi sensing highlights severe privacy threats, yet its real-world feasibility is hindered by two fundamental physical and deployment bottlenecks: the strict requirement for network privileges to acquire stable sensing streams, and the inherent "waveform fusion" ambiguity of pure WiFi signals during rapid, muscle-memory typing. To overcome these limitations, we propose AirKey, a novel cross-modal sensing framework that achieves highly stealthy, zero-training PIN eavesdropping. First, to bypass network deployment barriers, AirKey exploits fundamental IEEE 802.11 mechanisms to predictably elicit Acknowledgment (ACK) responses from unmodified target devices. By passively harvesting Channel State Information (CSI) from these ACKs using a low-cost microcontroller, AirKey secures a continuous spatial sensing stream entirely without network association. Crucially, to resolve the WiFi waveform fusion bottlene
arXiv:2608.03039v1 Announce Type: cross Abstract: Self-Sovereign Identity (SSI) promises to decentralize digital identity, but widespread adoption remains hindered by integration complexity and tooling immaturity. This paper investigates the Developer Experience (DX) of open-source SSI tooling through an exploratory probe study. Nine developers with prior knowledge of decentralized identity concepts, representing early integrators building SSI applications, attempted core credential lifecycle tasks using Walt.id, Traction, and MetaMask. Our goal was to surface recurring integration barriers through qualitative thematic analysis of open-ended developer reports, complemented by task-level difficulty ratings. Our findings reveal a critical abstraction gap: while passive operations like credential receipt are relatively mature, active construction tasks, particularly schema customization, expose significant architectural friction. We identify that these barriers stem from inadequate API ab
arXiv:2608.02780v1 Announce Type: cross Abstract: In robot teleoperation, haptic feedback can be used to help human operators accomplish dexterous manipulation tasks. However, existing haptic feedback methods try to replicate high-fidelity sensory haptics that are felt in real world interactions, which are constrained by the sensing and feedback hardware capability and may lead to higher workload. To addresses these limitations, this work introduces semantic haptics for teleoperation, which uses abstract haptic patterns to convey critical information about robot states. We categorize robot states into "Confirmations" and "Exceptions", implement a modular haptic rendering pipeline in robot simulation, and deliver semantic haptic feedback to operators through pneumatic and vibrotactile wristbands. This simplifies hardware requirements and enables one-to-many mappings between haptic patterns and robot states. Through three evaluation studies, we identify the most effective semantic haptic
arXiv:2608.00289v1 Announce Type: cross Abstract: Recognizing Human-Object Interactions (HOI) is essential for intelligent systems, underpinning applications in virtual and augmented reality, embodied AI, and assistive robotics. However, vision-based HOI methods face challenges in privacy concerns and poor light conditions. In this work, we introduce RF-HOI, the first framework that only uses radio frequency (RF) signals for HOI recognition. A key challenge of RF-HOI is that single-modality RF sensing is insufficient to recognize both actions and the objects being interacted with. RF-HOI addresses this through a novel modality fusion that combines mmWave radar and RFID, enabling simultaneous action recognition and target identification. Another challenge is limited training data across diverse setups, which impairs the generalizability of the recognition model. To overcome this, we develop a simulator that synthesizes multimodal RF data for diverse HOIs at scale, allowing us to fine-tu
arXiv:2608.04006v1 Announce Type: new Abstract: LLMs are reshaping educational technology, yet evaluating their responses for pedagogical alignment remains underexplored, relying heavily on the expertise of learning engineers building the technology. To bridge this gap, we explore trustworthiness as a structured lens for evaluation, leveraging existing measures of LLM trustworthiness to systematically identify potential pedagogical disruptions. Through a longitudinal co-design process with learning engineers developing an LLM-powered digital textbook, we: (1) co-constructed five trustworthiness metrics comprising 20 measures tailored to pedagogical use; (2) designed visualizations that map trustworthiness violations onto LLM responses; and (3) evaluated how these tools help learning engineers make A/B comparisons of LLM responses. Making trustworthiness explicit increased inter-rater reliability while helping learning engineers resolve conflicting objectives and produce more consistent
arXiv:2608.04002v1 Announce Type: new Abstract: We present Semantic Bundling, a visual analytics technique for making sense of text documents represented as knowledge graphs (KGs). Representing a document corpus as a KG makes relationships between entities explicit, making KGs useful both to analyze directly and in computational workflows including ML pipelines and generative AI backends. However, as KGs grow they become difficult to interpret and visualize for specific tasks (e.g., the ``hairball problem''), with the meaning of each relationship often buried in dense source text. Semantic Bundling uses large language models (LLMs) to support user-driven bundling of nodes and edges in a KG into higher-level graph structures: super nodes, which collapse and summarize a region of the graph, and super edges, which summarize the connection between two entities. Results are linked to underlying triples and source documents, grounding summaries in evidence. We implement Semantic Bundling in
arXiv:2608.03804v1 Announce Type: new Abstract: Geospatial foundation models (GeoFMs) offer transformative potential for environmental monitoring, yet adoption among ecologists is uneven. Most evaluations are model-centric, focusing on architecture and benchmark accuracy, which overlooks whether the systems are usable by their intended audiences. To address this gap, we first conducted a pilot expert elicitation survey with ecology and conservation scientists that helped us identify misalignments between current GeoFM development priorities and their needs. Informed by these findings and based on HCI theory, we created a seven-dimension evaluation covering Access & Deployment, Interaction & Customization, Trust & Transparency, Community & Support, Scientific Permanence, Multilingual Support, and Offline Usability. Then, two raters applied this rubric to 89 GeoFMs. We found distinct accessibility gaps where nearly a third provide no support to practitioners beyond their source code. Dim
arXiv:2608.03533v1 Announce Type: new Abstract: Dynamic consent can promise end users with greater control, but little is known about how older adults with chronic conditions navigate the tradeoff between control and burden in granular consent mechanisms in health data life-cycles. Using a two-stage design process we evaluated this tradeoff. An expert workshop (n=5) informed the design requirements for granular dynamic consent prototype. We evaluated single step vs multi-step granularity in dynamic consent using prototypes with cardiac patients (n=7) using a mixed-methods study. Quantitative measures showed no significant differences between low- and high-granularity consent screens in usability, workload, perceived information control or willingness to share data. However, qualitative findings revealed a control-burden paradox and trust-dependent engagement with granularity. Participants sought greater transparency and control over AI-mediated data processing. We contribute implicatio
arXiv:2608.03433v1 Announce Type: new Abstract: Sonic seasoning research has shown that listeners attribute systematic gustatory and emotional meaning to sound, and text-to-music generative artificial intelligence has recently been used to render gustatory prompts as musical stimuli. Whether the taste-sound correspondences acquired by such models hold beyond the cultural context in which they were validated remains untested. We extended a single-country study to a three-country online experiment conducted in Argentina, Italy, and Japan (N = 361). Participants first indicated their preference between base and fine-tuned MusicGen excerpts generated from four taste prompts (sweet, sour, bitter, salty), and then rated fine-tuned excerpts on twelve taste, emotion, and thermal descriptors. Preference for the fine-tuned model was confirmed in Argentina and Italy but not in Japan, and the salty prompt yielded the weakest correspondence in all three cohorts. Ratings differed substantially betwe
arXiv:2608.03251v1 Announce Type: new Abstract: Commercial wearable devices continuously capture rich physiological data (e.g., heart rate, respiration), opening new possibilities for monitoring health conditions, notably around stress. Despite their promise, turning raw wearable physiological data streams into visualizations that surface stress-related insights in daily activities, and that ultimately foster reflection, awareness, and better stress management, remains a significant challenge. The data are noisy and context-dependent: the same spike in heart rate can come from sprinting, a tense presentation, or laughing with friends. To address these challenges, we propose a framework that combines user annotations with wearable data to support better stress management. We introduce a web framework offering interactive visualizations that layer daily activities, stress events, and interventions onto raw physiological streams, enabling users to reflect and identify trends. In a four-we
arXiv:2608.03168v1 Announce Type: new Abstract: The optimal sensor position on a computer mouse can improve pointing performance, but existing calibration methods require time-consuming repetitions of pointing tasks. In this paper, we propose a novel calibration approach that dramatically reduces the time and effort required to determine a user's optimal mouse sensor position. Our method simulates cursor trajectories for different sensor positions using a dual-sensor mouse, eliminating the need for repetitive measurements with multiple sensor placements. By analyzing the straightness of the simulated paths, quantified by the mean absolute error (MAE) relative to an ideal straight-line path, we estimate the sensor position that would yield the most efficient pointing motion for the user. Our preliminary results indicate that the proposed simulation-based calibration method could reduce the calibration time from an hour to just five minutes, while providing a better identification of the
arXiv:2608.03152v1 Announce Type: new Abstract: Collecting richly labeled wearable activity data in everyday settings remains difficult because retrospective annotation is costly and often imprecise. Prior data collection apps rely on a labor-intensive self-reporting strategy and primarily treat participants as crowd labelers. We present Pebbl, a feasibility-stage system that incentivizes in-situ labeling through opportunistic crowdsensing. Pebbl lets users author trigger-action recipes on a smartphone and receive just-in-time reminders for beneficial actions when a trigger is detected. In the prototype, triggers are a limited set with four common audio cues, while actions are described in open-vocabulary natural language. Each confirmed execution yields a short sensor window with explicit start/end boundaries and a user-authored action label. We evaluate Pebbl through an expert workshop with wearable Human Activity Recognition (HAR) researchers (N = 6), a within-subject in-lab study (
arXiv:2608.03132v1 Announce Type: new Abstract: Immersive Computational Notebooks (ICoN) extend traditional notebook environments into immersive spaces, enabling analysts to interact with multimodal artifacts, including code, narratives, data tables, and visualizations. By integrating multimodal artifacts into a single immersive workspace, ICoN enables analysts to transition between analytical tasks seamlessly. Meanwhile, understanding organizational strategies is critical for designing effective interactions to further support analysts. However, prior research on immersive computational notebooks has primarily examined organizational strategies centered on single-modality artifacts. Systematic investigations of how analysts spatially organize the complex relationships among multimodal artifacts in a single immersive workspace remain underexplored. To address this gap, we conducted a user study to examine organizational strategies for multimodal artifacts in immersive computational not
arXiv:2608.02784v1 Announce Type: new Abstract: Across cohorts of older adults and generations of technology, (dis)trust has continued to shape the acceptance of technologies for aging. Yet, we still know little about if or how to design for older adults' distrust in technology. Towards this, we reviewed empirical studies in which older adults discussed trust and distrust in relation to technology. Our analysis shows that (dis)trust is constituted in three key ways: emerges when material arrangements of digital systems become illegible, such as when older adults cannot determine where information is stored or trace its movement; is temporally constituted and fluid, building and shifting through prior experience and breakdowns, and at times distrust can operate as boundary work through which individuals limit technology's reach into their autonomy, relationships, and everyday lives. Our work yields design directions for supporting trust across different phases of technology use and by d
arXiv:2608.02749v1 Announce Type: new Abstract: We introduce Sensus Pond, an interactive system that reconfigures water not merely as a static natural element but as an active sensing medium for registering more-than-human traces. In response to the limitations of anthropocentric approaches in interaction design, we propose a methodological framework of observation without translation, resisting the tendency to stabilize, decode, or humanize nonhuman presence. Drawing from critical theories of more-than-human design and ecological entanglement, Sensus Pond is a materially embedded and site-specific system that employs Swept Frequency Capacitive Sensing and an Artificial Neural Network to detect ephemeral interactions between the pond's surface and surrounding life forms. Rather than classifying or interpreting these events, the system visualizes temporal accumulations of overlapping traces, producing a layered archive of spatial and temporal entanglements. This approach emphasizes attu
arXiv:2605.20956v2 Announce Type: replace-cross Abstract: Conformal triage converts predictive scores into deployment actions that either release a case, flag it for urgent attention, or defer it to human review. Under an observed change in target-event prevalence, however, marginal coverage and human-review rate can miss whether patients who experience the target event are released without review. To address this gap, we introduce a leakage-aware deployment audit for release-side conformal triage. It first assigns target subjects to three non-overlapping roles: prevalence correction, conformal calibration, and held-out release-side evaluation. This separation then lets the audit evaluate release directly: how many event-positive patients are cleared without review, whether the pilot has enough event labels for calibration, and how the release-review trade-off shifts. Applying this audit to a retrospective non-small-cell lung cancer (NSCLC) target cohort shows why lower review can be m
arXiv:2512.20775v3 Announce Type: replace-cross Abstract: In this paper, we introduce Sark, a reference architecture for transferring unforgeable, stateful, oblivious (USO) assets. We describe the motivation, design, and implementation of the core subsystems of Sark, Porters, which accumulate and roll-up commitments from Clients, and Sloop, a permissioned, crash fault-tolerant (CFT) blockchain system. We analyse the operation of the system using STRIDE threat analysis, and the `CIA Triad': Confidentiality, Availability, and Integrity. We then introduce the concept of \textit{local centrality} and use it to address design trade-offs related to decentralization. Finally, we point to future work on Byzantine fault-tolerance (BFT), and mitigating the local centrality of Porters.
arXiv:2408.02677v2 Announce Type: replace-cross Abstract: This study proposes a novel, integrative framework for patient-centered data science in the digital health era. We developed a multidimensional model that combines traditional clinical data with patient-reported outcomes, social determinants of health, and multi-omic data to create comprehensive digital patient representations. Our framework employs a multi-agent artificial intelligence approach, utilizing various machine learning techniques including large language models, to analyze complex, longitudinal datasets. The model aims to optimize multiple patient outcomes simultaneously while addressing biases and ensuring generalizability. We demonstrate how this framework can be implemented to create a learning healthcare system that continuously refines strategies for optimal patient care. This approach has the potential to significantly improve the translation of digital health innovations into real-world clinical benefits, addr