ABOUT THIS ISSUE

How this newsletter was synthesized?

Methodology

This newsletter is generated by an AI pipeline (leveraging Anthropic Sonnet 4.5 & Haiku 4.5) that processes the metadata and abstracts of every new arXiv HCI paper from the past week—124 this issue. Each paper is scored on three dimensions: Practice (applicability for practitioners), Research (scientific contribution), and Strategy (industry implications), with scores from 1-5. Papers passing threshold are grouped into topic clusters, and each cluster is summarized to capture what that body of research is exploring.

Selection Criteria

The pipeline builds a curated selection that balances high scores with topic diversity—and deliberately includes at least one 'contrarian' paper that challenges prevailing assumptions. This selection is then analyzed to identify key findings (patterns across multiple papers) and surprises (results that contradict conventional wisdom). A narrative synthesis ties the week's research together under a unifying frame.

Key Themes Discovered

Field Report: ai-interaction

Trust, Calibration, and Cognitive Alignment

This cluster examines how humans calibrate trust and maintain cognitive vigilance when interacting with AI systems. Core questions: When do users over-rely on AI outputs? How do explanations shape decision-making? What contextual factors enable appropriate reliance? Research spans high-precision engineering, healthcare, education, and social domains. Methods emphasize user studies, behavioral experiments, and physiological measurement. The work reveals systematic gaps between AI capabilities and human mental models, with implications for designing transparent, context-aware systems that preserve human agency and critical judgment.

1/10