New papers on Human–computer interaction
106 new papers on human–computer interaction in the last 7 days, within Computing. These are the 50 Pipette rates most worth reading, with the main result in the authors' own words.
The best of the week
AESSI: An Around-Ear Silent Speech Interface for Cross-Day Online Reuse without Test-Day Calibration
With six participants' complete final recordings held out, AESSI achieved 92.24 percent mean accuracy without test-day calibration.
PreprintReal-world useThe Impact of Deep Care Isa on Reducing Musculoskeletal Disorders and Enhancing Productivity Among Office Employees: A Comprehensive Study
Utilizing data from over 2,300 participants across 50 corporations, the study demonstrates significant improvements in ergonomic practices, physical activity, hydration habits, and overall productivity, with notable reductions in MSD-related sick leave.
PreprintReal-world useEasy to readCan I Trust My Body? A Three-Year Autoethnography of ChatGPT's Place in My Support System for Panic Attacks
We propose trajectory-level safety during and after panic: usable advice (Fit), a stopping point for repeated checking and reassurance seeking (Closure), and useful understanding and human support that remain available over time (Continuity).
PreprintReal-world useScalable AI-based clinical communication training and automated assessment
We developed SOPHIE 2.0, a browser-based, self-service platform integrating embodied AI-patient interactions, personalized feedback, and automated assessment across 24 clinical scenarios.
PreprintReal-world useWhen the Strike Zone Becomes Algorithmic: Umpire Judgment and Player Challenge Decisions under AI Review
It reshapes human judgment, adaptation, and strategic behavior around an algorithmic authority.
PreprintBroad interestEasy to readDeflecting the Value Compass: Interacting with Large Language Models Temporarily Shifts Human Value Priorities Toward Personal Focus
Each LLM condition temporarily shifted value priorities toward personal focus relative to the control (d=0.37-0.51), primarily through increased Self-Enhancement.
PreprintBroad interestA Procedure for Classifying Attachments and Affective Social Bonds in Human-Robot Dyads
By replacing the divergent operationalisations with a unified, criterion-based classification, this paper gives HRI practitioners a standardised basis for evaluating, classifying, and comparing human-robot relationships, and sets out the experimental rigour that each classification demands.
Preprint"MeBo Leaves a Piece of You Behind": Designing a Relational Voice-Based Memory Companion for Older Adults
In a mixed-methods evaluation with 20 older adults, participants found MeBo exceptionally usable (SUS = 87.75), enjoyable, sociable, emotionally responsive, and trustworthy.
PreprintReal-world use"What I See is What I Hear": Deepfake Detection Across Diverse Hearing Abilities
Our work systematically characterizes how deepfakes affect DHH populations, highlighting the asymmetric risks audiovisual manipulations may pose to groups with different hearing abilities and the need for accessible, tailored defenses that support all users.
PreprintReal-world useHeating in human-HVAC interaction for smart homes: An interdisciplinary overview
Based on 541 studies from these fields, this review integrates interdisciplinary research on Heating in Human-HVAC Interaction in smart homes.The resulting synthesis is conceptualized through the Situated Interaction Dynamics of control and feedback between users and systems.
Preprint with a published versionReal-world useBeyond Driving: Envisioning Activities in Future Autonomous Vehicles through Experience-Centered Design
Our findings lead us to conceptualize NDRAs not as isolated instances of "travel time use," but as dynamic sequences of interrelated activities deeply shaped by pre- and post-journey contexts.
PreprintAI-Generated Email Drafts Shift Culturally Distinctive Communication Styles in Professional Email
But AI drafts shifted participants' emails toward the draft's style, with larger shifts when the draft was culturally misaligned: Japanese drifted most under low-context drafts, Americans most under high-context drafts.
PreprintReal-world useEasy to readPassthrough Rigidity: The Behavioral and Visuomotor Costs of Mediated Perception
We conclude that current passthrough implementations induce a measurable shift from flexible exploration to motor caution, where task performance is preserved at the cost of user comfort and biomechanical efficiency.
PreprintReal-world usePeople escalate against a competitor labelled human and hold back against one labelled an optimising machine
This shows that describing an AI competitor is not behaviourally neutral.
PreprintWhen AI Tutors Speak: Evidence from a Randomized Field Experiment
Structure mattered: tutored students gained 6.63 points more than ability-matched peers (p=.007), and the gain was concentrated in written reasoning, where the share of answers reaching relational quality rose from 8% to 49% in the tutored arm against 8% to 27% in the holdout.
PreprintReal-world useAssembling, Breaking, and Refusing the Mask: Agency in AI-Mediated Self-Presentation in Livestreaming
We conceptualize masking as a sociotechnical assemblage in which agency lies in preserving, disrupting, and reconfiguring relations rather than controlling a single interface.
PreprintIdentity Continuity in Long-Term Embodied AI Relationships: From Agent-Specific Identity Representation to Identity-Continuity Appraisal
This article proposes a user-side framework in which long-term embodied AI is represented through an agent-specific identity representation organized by at least three open identity-content domains: embodied-perceptual, psychological-behavioral, and relational-autobiographical.
PreprintTouvigation: Embodied Adaptive Object Acquisition for Blind and Low-Vision Users in Unfamiliar Indoor Environments
Touvigation achieved 100% task success, compared with 58% for the multimodal assistant and 85% for unassisted search, while reducing completion time and cognitive workload.
PreprintReal-world useForced Yet Free: What Magicians' Forcing Reveals Beyond Intentional Binding
Authorship binding does not denote a new implicit measure; rather, it refers to the constructive relation through which a choice whose formation has been directed by external factors can nevertheless be experienced as originating from the self.
PreprintEMooly: Supporting Autistic Children in Collaborative Social-Emotional Learning with Caregiver Participation through Interactive AI-infused and AR Activities
Compared with a baseline, a controlled study with 24 autistic children and their caregivers showed EMooly significantly improved children's emotion recognition skills and its novel features were preferred and appreciated.
Preprint with a published versionReal-world useEasy to readWorking with Agentic `Teammates': When a New Organizational Actor Collides with the Human Ecosystem of Work
Our findings reveal the boundaries of the human-agent workplace are actively in flux, triggering breakdowns and negotiations across: 1) tacit rules of collaborative human workflows, 2) the relational boundaries of this new non-human actor, and 3) the redistribution of trust and human agency.
PreprintAnnie, Are You Okay? How Style- and Context-Based Personalization Shape AI-Assisted Decision-Making
Participants perceived both forms of personalization, but only context-based personalization reliably changed ranking behavior: it increased reconsideration and moved rankings toward the AI's assigned recommendation.
PreprintReal-world useBeyond Reactive Assistance: PV-Care Using Low-Density EEG and AI to Provide Proactive, Context-Aware Help for MCI
This paper presents PV-Care, a proactive AI-driven assistance scheme that integrates wearable electroencephalogram (EEG) sensing with visual environmental perception to provide real-time, context-aware voice assistance for MCI users.
PreprintBold claims, read criticallyReal-world useGenerative Tutorial: Towards Live Contextualized Visual Instructions for Physical Tasks
We introduce Generative Tutorial, a conceptual framework for live visual instruction that depicts intended outcomes and actions within the user's environment and task flow.
PreprintReal-world useDepressive symptoms are reflected differently across digital contexts
Our findings suggest that characterizing how depressive symptoms are reflected in digital behavior requires attending to what people do online and where, not only how much screens are used.
PreprintEasy to readUnderstanding Human Perception of Representation in Citizens' Assemblies: An Empirical Study
We find that demographic attributes matter for perceived representation, but political alignment and context-specific attributes such as climate concern exert a stronger influence.
PreprintSurgGaze: Implicit Calibration for Accurate Gaze Analysis in Operating Rooms with Wearable Eyetrackers
We introduce SurgGaze, an implicit calibration method that corrects these errors using high-confidence surgical moments.
PreprintReal-world useWhen Disability Disclosure Travels: Memory, Privacy, and Contextual Integrity in Conversational AI
Using contextual integrity as an analytic lens, we found that participants disclosed by need rather than by name, translating disability into task-scoped instructions; that the same disclosure was judged against two recipients, a non-judging interlocutor and a data-holding company, producing opposite norms; and that memory features relieved the burden of repeated disclosure while letting disability information drift into contexts where it did not belong.
PreprintReal-world useNotrix: Understanding Machine Learning Solutions Across Computational Notebooks at Scale
In this paper, we present Notrix, an interactive visual analytics tool for profiling hundreds of notebooks as one collection.
PreprintReal-world useAI-Assisted Social Story Intervention for Special Education: The Design of AdaptED Stories
We present AdaptED Stories, a practitioner-guided system for authoring, personalizing, and delivering Social Stories in special-education contexts.
PreprintReal-world useEasy to readHuman learning is an understudied but promising lever for boosting human–AI synergy
Our reanalysis suggests that the current literature underestimates the potential of human-AI collaboration because it predominantly relies on paradigms that do not facilitate human learning, thus hindering humans from effectively adapting their collaboration strategies.
Peer-reviewed journalDoes AI Save Time on Product Design? A Randomized Controlled Experiment of AI Prompt-to-Design Workflows
Among participants who completed the study tasks, access to Figma Make was associated with approximately 20% shorter completion times, with larger gains among product managers.
PreprintReal-world useEasy to readVisibility Design and Strategic Reasoning
Together, our findings highlight that who an agent sees, and not only how deeply it reasons, shapes strategic behavior, and point to visibility as a design lever.
PreprintBeyond Screen Time: Demonstrating the Value of App Activity Logs to Understand User Behavior Further
We argue that event-level app activity logs should form the backbone of research on actual rather than recalled smartphone use.
PreprintGricea: An Open Science Platform for Conversational AI Research
We present Gricea, an open-science platform representing studies as configurable, deployable research artifacts that researchers can run, inspect, share, and reuse.
PreprintValue-Sensitive Delegation in Everyday AI Agent Use: Evidence from OpenClaw
Supporting human values requires attention not only to what an agent accomplishes, but to the conditions users set around delegation, including cost, access, and oversight.
PreprintEvaluative Dynamics of AI Integration and Expert Performance under Epistemic Dependence across Heterogeneous Stakes
Overall, performance-related recalibration appeared comparatively portable, while integration-structure effects were more selective and context-sensitive.
PreprintReal-world useMaking Fragmented Reports Legible: Finding Patterns and Perceptions of Sexual Violence in Bangladesh
We contribute an uncertainty-aware framing for HCI research using sensitive, low-resource news data and identify design requirements for provenance, privacy, validation, and responsible communication.
PreprintCan LLMs identify and repair ruptures? Comparison between clinician practices and LLM behaviors
Overall, LLMs showed higher agreement with predefined labels in identification, but not in resolution where experts rated their responses only moderately effective, with consistent limitations in timing, depth, and contextual sensitivity.
PreprintReal-world useAdaptive Scaffolding Needs Contingency: An AI Tutor That Escalates and Fades on What the Learner Does
CoMeT matched the question-only tutor's demand, delivered artifacts twice as often as the assistant, and frustrated learners less than the question-only tutor, with delegation and load unchanged.
PreprintReal-world useElicitive User Interfaces: Designing How Users Shape Generative Interfaces
We propose Elicitive User Interfaces, a design approach to GenUI that generates elicitation techniques as part of the interface itself.
PreprintReal-world useATCion: Exploring the Design of Icon-based Visual Aids for Enhancing In-cockpit Air Traffic Control Communication
In a comparative study of ATCion, text-based visual aids, and no visual aids, we found that our design improved readback accuracy and reduced memory workload, without negatively impacting flight operations; most participants preferred ATCion over text-based aids, citing their clarity, low cognitive cost, and fast interpretability.
Preprint with a published versionReal-world useEasy to readThink Before You Accept: Can Written Justification Reduce Uncritical Uptake of AI Writing Suggestions?
Students required to provide written justifications were 24 percentage points less likely to adopt flawed suggestions (65% vs. 41%), with no reduction in acceptance of sound suggestions (81% vs. 86%).
PreprintCoBranchMR: Supporting Parallel Design and Conflict Resolution in Mixed Reality
By adopting branch-and-merge workflows for embodied spatial collaboration, CoBranchMR introduces a new collaborative interaction model that supports parallel design, conflict resolution, and negotiation in remote creative work.
Preprint with a published versionReal-world useWhose Facts Count? A Culturally Responsive Audit of LLM Evaluation Benchmarks
The paper proposes a practical CR evaluation framework.
PreprintBold claims, read criticallyAI Persona, Service Consumption, and User Intent Entropy: Field Experimental Evidence from an LLM Platform
The relational persona increases interactions (sessions, +8.1%; duration, +10.6%; chat rounds, +24.2%; intent entropy, +5.8%) and outputs (files, +12.3%; distinct goals, +12.1%).
PreprintReal-world use"You Can't Just Automate It": Negotiating and Sustaining a "Good" Family Life Through Energy Practices
We offer theoretical and design directions for more adaptive, participatory, and contestable family IoT.
PreprintReal-world useStructure-Aware Rendering: How Code Reveal Shapes Programmers' Visual Attention
Our findings show that rendering alters visual attention and reading behavior: dynamic rendering induces fewer but longer fixations and more sustained focus, while structured rendering further guides attention toward semantically meaningful units and supports high-level understanding.
PreprintReal-world use"I Talked an AI Chatbot, So What's Next?" How U.S. Young Adults Imagine Responsible AI for Emotion Coping
This study contributed a relational perspective of responsible AI in emotion coping.
PreprintReal-world useGUIDE: Designer-in-the-loop Authoring of Conformant Generative User Interfaces
We introduce GUIDE (GenUI Development Environment), a system that lets designers continuously inspect and refine GenUI behavior as they create and edit interfaces.
PreprintReal-world use