LLMs routinely produce unsupported causal stories for personal sensing anomalies, and richer evidence or constrained prompts do not reliably eliminate this epistemic overreach.
Epstein, An Ping, James Fogarty, and Sean A
9 Pith papers cite this work, alongside 493 external citations. Polarity classification is still indexing.
9
Pith papers citing it
493
external citations · external index
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
TimeSRL uses semantic abstractions from time-series data optimized via reinforcement learning to achieve better cross-dataset generalization than standard ML or LLM baselines in mental health prediction.
AI-authored goals produce higher SMART quality scores but lower psychological ownership, commitment, importance, and goal-directed behavior than self-authored goals, with ownership as the mediating mechanism.
Urban Indians practice health tracking as collective family care, and personal health informatics should be redesigned around agency, elicitation, and engagement to support proactive shared care.
A 9-week mixed-methods study with 12 families found home displays significantly increased mood and goal tracking frequency over smartwatches alone, with multi-device setups accommodating diverse family routines and preferences.
LLM-powered conversational voice sleep diaries achieved higher adherence and richer contextual reports than text-based diaries, with a noted trade-off in structured field completeness.
Extends unsupervised eye contact detection for mobile scenarios, reporting significant performance gains on two datasets and new attention metrics.
Presents an LLM-mediated architecture for continuous adaptation of health dashboards by synthesizing explicit feedback, spatial reorganization, and attention signals via structured prompt engineering.
PSI uses a shared personal-context bus to publish state and write-back affordances, turning isolated AI-generated modules into synchronized, chat-accessible instruments.
citing papers explorer
-
Causal Stories from Sensor Traces: Auditing Epistemic Overreach in LLM-Generated Personal Sensing Explanations
LLMs routinely produce unsupported causal stories for personal sensing anomalies, and richer evidence or constrained prompts do not reliably eliminate this epistemic overreach.
-
TimeSRL: Generalizable Time-Series Behavioral Modeling via Semantic RL-Tuned LLMs -- A Case Study in Mental Health
TimeSRL uses semantic abstractions from time-series data optimized via reinforcement learning to achieve better cross-dataset generalization than standard ML or LLM baselines in mental health prediction.
-
Optimized but Unowned: How AI-Authored Goals Undermine the Motivation They Are Meant to Drive
AI-authored goals produce higher SMART quality scores but lower psychological ownership, commitment, importance, and goal-directed behavior than self-authored goals, with ownership as the mediating mechanism.
-
Unpacking "Personal" Health Informatics for Proactive Collective Care
Urban Indians practice health tracking as collective family care, and personal health informatics should be redesigned around agency, elicitation, and engagement to support proactive shared care.
-
Evaluating Glanceable Multi-Device Family Health Tracking with Smartwatches and Home Displays
A 9-week mixed-methods study with 12 families found home displays significantly increased mood and goal tracking frequency over smartwatches alone, with multi-device setups accommodating diverse family routines and preferences.
-
Better Adherence, Richer Context: A Field Evaluation of LLM-Powered Conversational Voice Diaries for Sleep
LLM-powered conversational voice sleep diaries achieved higher adherence and richer contextual reports than text-based diaries, with a noted trade-off in structured field completeness.
-
Accurate and Robust Eye Contact Detection During Everyday Mobile Device Interactions
Extends unsupervised eye contact detection for mobile scenarios, reporting significant performance gains on two datasets and new attention metrics.
-
Continuous Behavioral Synthesis for Adaptive Health Dashboards: An LLM-Mediated Architecture Integrating Explicit Preference, Spatial Reorganization, and Attention Allocation Signals
Presents an LLM-mediated architecture for continuous adaptation of health dashboards by synthesizing explicit feedback, spatial reorganization, and attention signals via structured prompt engineering.
-
PSI: Shared State as the Missing Layer for Coherent AI-Generated Instruments in Personal AI Agents
PSI uses a shared personal-context bus to publish state and write-back affordances, turning isolated AI-generated modules into synchronized, chat-accessible instruments.