SAGE decomposes univariate time-series anomaly detection into four specialized LLM analyzers plus an evidence-grounded detector and supervisor, achieving the highest average performance on three benchmarks while using only normal data for in-context examples.
Oliffson Kamphorst, and David Ruelle
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Recurrence-based biomarkers from vocal dynamics classify depression with mean cross-validated AUC 0.689, outperforming static acoustic baselines and other dynamic features with p=0.004.
citing papers explorer
-
Detecting Time Series Anomalies Like an Expert: A Multi-Agent LLM Framework with Specialized Analyzers
SAGE decomposes univariate time-series anomaly detection into four specialized LLM analyzers plus an evidence-grounded detector and supervisor, achieving the highest average performance on three benchmarks while using only normal data for in-context examples.
-
Recurrence-Based Nonlinear Vocal Dynamics as Digital Biomarkers for Depression Detection from Conversational Speech
Recurrence-based biomarkers from vocal dynamics classify depression with mean cross-validated AUC 0.689, outperforming static acoustic baselines and other dynamic features with p=0.004.