TRACE-TS: Attribution-Grounded and Traceable Sensor-Language Reasoning for Human Activity Understanding
Sparsh Rastogi, Tanmay Kumar, Baiyu Chen, Jatin Bedi, Zechen Li, Flora D. Salim
cs.AI, cs.CL, cs.ET, cs.LG
Submitted: 2026-07-31
Comments: 24 pages, 9 figures, 24 tables
Code: https://github.com/SparshRastogi/TRACE-TS
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Towards Efficient and Evidence-grounded Mobility Prediction with LLM-Driven Agent
- MantisV2: Closing the Zero-Shot Gap in Time Series Classification with Synthetic Data and Test-Time Strategies
- The Llama 3 Herd of Models
- Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
- Large-scale Training of Foundation Models for Wearable Biosignals
- Gemma 4 Technical Report
- Chronos-2: From Univariate to Universal Forecasting
- Foundation Models Defining A New Era In Sensor-based Human Activity Recognition: A Survey And Outlook
- Towards Generalizable Human Activity Recognition: A Survey
- CAPTURE-24: A large dataset of wrist-worn activity tracker data collected in the wild for human activity recognition
- AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild
- LLM-as-a-Judge for Time Series Explanations
- LSM-2: Learning from Incomplete Wearable Sensor Data
- Enhancing LLM Reasoning for Time Series Classification by Tailored Thinking and Fused Decision
- OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data
- GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring
- CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining
- gpt-oss-120b & gpt-oss-20b Model Card
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems