Wall-clock leaky-integrator monitors on variable-cadence agent streams exhibit a sharp cliff between constant-alarm and silent regimes, while sample-time CUSUM monitors remain invariant; transition detection avoids the trap.
Title resolution pending
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
roles
dataset 1polarities
use dataset 1representative citing papers
A tuning-parameter-free self-normalized test detects changes in the marginal distribution of object-valued time series under weak dependence, with first nonparametric consistency results for multiple change-point estimation via wild binary segmentation.
Soft-MSM is a smooth, gradient-enabled version of the context-aware MSM distance for time series alignment that outperforms Soft-DTW alternatives in clustering and nearest-centroid classification.
QATS is a new polylog-time approximate decoding procedure for HMMs that builds admissible state sequences by locally maximizing likelihoods over paths with at most three segments via adaptive ternary segmentation and cumulative sum storage.
Machine translation preserves embedding similarity structure for ten languages but distorts it for four in the Manifesto Corpus, via a new non-inferiority testing framework.
Ensemble voting strategies for change point detection improve F1-score by 11% over Mozilla's T-test method on a new ground-truth dataset of 174 performance time series annotated by practitioners.
A hierarchical screening protocol using PBE phase diagrams, ML interatomic potentials, and SCAN refinement reduces 894 computationally stable materials to 25 high-confidence experimental synthesis targets.
Trajectory mining produces readable skill clusters with high purity but GRPO training on them improves skill-step accuracy only from 18.5% to 20.5% and underperforms frequency priors.
citing papers explorer
-
Quick Adaptive Ternary Segmentation: An Efficient Decoding Procedure For Hidden Markov Models
QATS is a new polylog-time approximate decoding procedure for HMMs that builds admissible state sequences by locally maximizing likelihoods over paths with at most three segments via adaptive ternary segmentation and cumulative sum storage.