SVAR-FM uses simulator clamping to produce interventional distributions and flow matching to identify time series causal structures, with an error bound that predicts sign reversal of causal effects below a simulator accuracy threshold.
Chinese diabetes datasets for data-driven machine learning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3representative citing papers
MetaboNet-Bench provides an extensible open-source framework for comparing multimodal glucose forecasting models in T1D and finds that adding insulin and carb data benefits depend on model complexity.
MetaboNet is a consolidated dataset of 3135 subjects with 1228 patient-years of CGM and insulin pump data for Type 1 Diabetes research.
citing papers explorer
-
Intervention-Based Time Series Causal Discovery via Simulator-Generated Interventional Distributions
SVAR-FM uses simulator clamping to produce interventional distributions and flow matching to identify time series causal structures, with an error bound that predicts sign reversal of causal effects below a simulator accuracy threshold.
-
MetaboNet-Bench: A Multi-modal Benchmark for Glucose Forecasting in Type 1 Diabetes
MetaboNet-Bench provides an extensible open-source framework for comparing multimodal glucose forecasting models in T1D and finds that adding insulin and carb data benefits depend on model complexity.
-
MetaboNet: The Largest Publicly Available Consolidated Dataset for Type 1 Diabetes Management
MetaboNet is a consolidated dataset of 3135 subjects with 1228 patient-years of CGM and insulin pump data for Type 1 Diabetes research.