Digital twinDigital twin speeds up reinforcement learning for lab robotsarXiv API — полнотекстовый поиск "digital twin" · yesterdayDigital twinDataset for deciding between evidence gathering and action in control-system incidentsarXiv — Computational Engineering, Finance, and Science (cs.CE) · yesterdayDigital twinSparse stochastic twins can outperform exact digital twinsarXiv — Computational Engineering, Finance, and Science (cs.CE) · yesterdayModellingPluralism of rival models in network models of sciencearXiv — Multiagent Systems (cs.MA) · yesterdayForecastingEstimation and MPC for balancing a wheel-legged robot under unknown disturbancesarXiv — Systems and Control (eess.SY) · yesterdayDigital twinConsolidating dispersed DSO data into a digital twin of the distribution gridarXiv API — полнотекстовый поиск "digital twin" · 2dDigital twinIntegrating ML and uncertainty quantification for real-time decisions in digital twinsarXiv API — полнотекстовый поиск "digital twin" · 2dDigital twinBiases in end-to-end digital twins built from chained modelsarXiv API — полнотекстовый поиск "digital twin" · yesterdayDigital twinDistributed Bandits for Freshness-Aware Data in MEC-Enabled Digital TwinsarXiv API — полнотекстовый поиск "digital twin" · 2dModellingAn agent-based model of knowledge transfer across scientific communitiesarXiv — Multiagent Systems (cs.MA) · 2dDigital twinSemantic interoperability in federated digital twins: a systematic reviewarXiv — Systems and Control (eess.SY) · 2dDigital twinCalibrating persona-based digital twin simulation against real dataarXiv — Computers and Society (cs.CY) · 2d
When Measurement Conventions Masquerade as Calibration Gains in Cardiac Digital Twins
US & West ·
This paper shows that apparent calibration improvements in cardiac digital twins may be artifacts of measurement conventions. Comparison of four models on a shared backbone revealed that CAMUS bias removal is explained by a +6.30 point difference between single-plane and biplane ejection fraction measurements, not by actual improvement. Replicating EchoNet-Dynamic with extractor aligned to the apical four-chamber plane removed overestimation and reversed the ranking.
Why it matters
Highlights the importance of rigorous validation and consideration of measurement conventions when evaluating models, which is critical for the reliability of digital twins in medical and industrial applications.
Original headline
When Measurement Conventions Masquerade as Calibration Gains in Cardiac Digital Twins
TwinBridge builds digital twins from 3D Gaussian splatting and physics simulation to supply policy initialization and dense visual rewards for real-world online learning of a laboratory robot. Simulator task events and geometric progress yield rewards for pretraining, distilled into a visual reward model and combined with execution history during human-in-the-loop refinement.
The authors present TE-GvA, a counterfactual decision dataset for fault-driven incident response on the revised Tennessee Eastman process: 9,908 decision points from 1,990 simulated incidents, each with 4–35 candidate actions labelled via branched rollouts. With labels computed under the true hidden cause, gathering evidence is the best choice in only 1.1–1.3% of decisions.
The study shows that keeping weakly dependent or auxiliary degrees of freedom raises the dimensionality of learning and control problems, so a sparse stochastic surrogate can beat an exact high-dimensional model. It introduces a method for dependence discovery at the level of the full conditional law, combining conditional generative modeling, Gaussian-process distillation and kernel mode decomposition.
