archive
Every paper Pith has read. Search by title, abstract, or pith.
941 papers in cs.HC · page 1
-
Students treat AI as quick fix but want long-term cultural support companion
Understanding How International Students in the U.S. Are Using Conversational AI to Support Cross-Cultural Adaptation
-
AI prototypes match humans on usability but lag in originality
Usable but Conventional: An Empirical Study on the UX of AI-Generated Interface Prototypes
-
Agency in AI relocates from interfaces to conversations
After the Interface: Relocating Human Agency in the Age of Conversational AI
-
Cookie banners push users to consent against their preferences
Deceptive Cookies: Consent by Design -- A Mixed Methods Study
-
Viverra adds verified assertions to LLM-generated C code
Viverra: Text-to-Code with Guarantees
-
Sonification lifts eye surgery event detection from 61 to 83 percent
Physics-Based iOCT Sonification for Real-time Interaction Awareness in Subretinal Injection
-
Model-based curricula speed motor skill learning by 23%
Automated Curriculum Design for High-dimensional Human Motor Learning
-
Short concern texts track with activity drops and sleep issues
A Formative Study of Brief Affective Text as a Complement to Wearable Sensing for Longitudinal Student Health Monitoring
-
3B continuous critic outperforms 7B binary GUI models
Beyond Binary: Reframing GUI Critique as Continuous Semantic Alignment
-
Distill refines robot task specs to match true user intent
Distill: Uncovering the True Intent behind Human-Robot Communication
-
Three SRL strategies shape secondary students' online essay writing
Self-Regulated Learning in Essay Writing: Consistency of Strategies and Impact on Outcomes
-
Fourteen codes define needed content for local AI explanations
What Should Explanations Contain? A Human-Centered Explanation Content Model for Local, Post-Hoc Explanations
-
One Rust visualization runs in Python
Pluot: Towards 'write once, run everywhere' visualization software
-
Attention focus stabilizes drug-shortage decisions without full analysis
Modeling Bounded Rationality in Drug Shortage Pharmacists Using Attention-Guided Dynamic Decomposition
-
LLM facilitators nudge charity donations without raising group consensus
Real-Time Group Dynamics with LLM Facilitation: Evidence from a Charity Allocation Task
-
LLMs shorten idea generation in programming tasks
"Like Taking the Path of Least Resistance": Exploring the Impact of LLM Interaction on the Creative Process of Programming
-
AI boosts education performance without aiding real learning
Distinguishing performance gains from learning when using generative AI
-
Human in the loop phrase masks AI oversight shortfalls
Humanwashing -- It Should Leave You Feeling Dirty
-
Steering EEG model features exposes three encoding regimes
Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders
-
Non-human yet logically aligned AI draws elevenfold higher disclosure odds
Beyond Anthropomorphism: Exploring the Roles of Perceived Non-humanity and Structural Similarity in Deep Self-Disclosure Toward Generative AI
-
Students rate AI slides equal to instructor ones
AI-Generated Slides: Are They Good? Can Students Tell?
-
Retrained VMAF cuts error in teleoperation video ratings by 27 percent
Beyond VMAF: Towards Application-Specific Metrics for Teleoperation Video
-
DRAT predicts LLMs' scientific ideation better than prior tests
Assessing the Creativity of Large Language Models: Testing, Limits, and New Frontiers
-
Pooled preferences nearly match individual fine-tuning for personalization
PRISM-X: Experiments on Personalised Fine-Tuning with Human and Simulated Users
-
AI forecasts in period apps reshape how users read their own bodies
"It became a self-fulfilling prophecy": How Lived Experiences are Entangled with AI Predictions in Menstrual Cycle Tracking Apps
-
Screened Doppler prompts stabilize mmWave pose tracking
Doppler Prompting for Stable mmWave-based Human Pose Estimation
-
Distinctiveness ranking uncovers hidden categories in document sets
Discovery-Oriented Faceting: From Coverage to Blind-Spot Discovery
-
Pipeline turns Instagram filters into facial recognition blockers
AuraMask: An Extensible Pipeline for Developing Aesthetic Anti-Facial Recognition Image Filters
-
Thermal cameras fingerprint VR apps remotely
ThermalTap: Passive Application Fingerprinting in VR Headsets via Thermal Side Channels
-
Raw capacitive streams turn touchscreens into whole-hand controllers
Magical Touch: Transforming Raw Capacitive Streams into Expressive Hand-Touchscreen Interaction
-
Writers propose seed banks and co-ops for language model data
Seed Bank, Co-op, Stoop Swap: Metaphors for Governing Language Model Data for Creative Writing
-
This paper tested how 100 people perceived emotions from short videos of Reachy Mini
Emotional Expression in Low-Degrees-of-Freedom Robots: Assessing Perception with Reachy Mini
-
Second-order model lets agents fix humans' mistaken beliefs about the agent
What Do You Think I Think? Accounting for Human Beliefs Using Second-Order Theory of Mind
-
Extension quiets eye floaters by minimizing motion on screens
Quieting the Cobwebs: Browser Interaction for Visual Floaters
-
Participatory benchmark shows general AI safety tests miss disability harms
DisaBench: A Participatory Evaluation Framework for Disability Harms in Language Models
-
Multimodal AI picks top and bottom images correctly in 26% of tasks
Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty?
-
Alignment cuts regret in AI-assisted binary decisions to O(sqrt(H T log T))
Learning to Decide with AI Assistance under Human-Alignment
-
Organizational justice gives metrics for recommender fairness
Co-Designing Organizational Justice Indicators for Algorithmic Systems
-
Admins like AI help writing WhatsApp rules but fear trust breaches
Creating Group Rules with AI: Human-AI Collaboration in WhatsApp Moderation
-
AI in exams makes judging solutions the new measure of learning
Reimagining Assessment in the Age of Generative AI: Lessons from Open-Book Exams with ChatGPT
-
AI goals score higher on SMART but cut follow-through
Optimized but Unowned: How AI-Authored Goals Undermine the Motivation They Are Meant to Drive
-
AI goals improve quality but slash follow-through
Optimized but Unowned: How AI-Authored Goals Undermine the Motivation They Are Meant to Drive
-
Uncertainty visuals raise annotation quality and speed
From Model Uncertainty to Human Attention: Localization-Aware Visual Cues for Scalable Annotation Review
-
Framework embeds values in CPS human monitoring rules
HM-Req: A Framework for Embedding Values within CPS Human Monitoring Requirements
-
Robot execution and AI chat boost student code reflection
RoboBlockly Studio: Conversational Block Programming with Embodied Robot Feedback for Computational Thinking
-
AI turns space history into shareable future news
COSMIC 1001: Engaging Future Speculation on Space Exploration with Generative AI
-
AI Turns The Thinker into Eastern Ink Symbols
Ink Spiral: Symbolic Transformation from The Thinker to the Four Gentlemen
-
Small diverse recourse sets raise action willingness without added load
Psychological Benefits and Costs of Diversifying Algorithmic Recourse
-
Local system raises facial expression accuracy to 94.49 percent
MindMirror: A Local-First Multimodal State-Aware Support System for Digital Workers
-
GDPR access requests expose contracts of African content moderators
Auditing African Content Moderators' Working Conditions by Using the European General Data Protection Regulation (GDPR)