On the Divergence of Accuracy and Mechanism Consistency in Time Series World Models

arXiv:2610.01842 · cs.AI · Submitted 2026-10-01 · Read on arXiv

cs.AI

Submitted: 2026-10-01

Updated: 2026-10-01

Code: https://github.com/HaochenZhang717/TSWM-Official-Repo

Terminology

• Accuracy — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Cosmos World Foundation Model Platform for Physical AI
• GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation
• Chronos-2: From Univariate to Universal Forecasting
• ChronosX: Adapting Pretrained Time Series Models with Exogenous Variables
• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations
• Training and Evaluating Causal Forecasting Models for Time-Series
• Long-term Forecasting with TiDE: Time-series Dense Encoder
• CLARITY: Medical World Model for Guiding Treatment Decisions by Simulating Context-Aware Disease Trajectories
• Monash Time Series Forecasting Archive
• From Tables to Time: Extending TabPFN-v2 to Time Series Forecasting
• Medical world models: representing medical states, modelling clinical dynamics and guiding intervention policies
• Wastewater Treatment Plant Data for Nutrient Removal System
• A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
• Beyond Static Forecasting: Unleashing the Power of World Models for Mobile Traffic Extrapolation
• CoRA: Covariate-Aware Adaptation of Time Series Foundation Models
• DAG: A Dual Correlation Network for Time Series Forecasting with Exogenous Variables
• DoTime: A Synthetic Benchmark Generator for Interventional and Counterfactual Time Series
• From Observations to States: Latent Time Series Forecasting
• Learning Interactive Real-World Simulators

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