Find a story
Search Spins
Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.
8 results for “clustering”
Stochastic complexity of vectors containing cluster structure
A new arXiv preprint introduces a linear-time recursion formula to compute the Normalized Maximum Likelihood (NML) normalizing constant for clustered vectors, improving upon prior polynomial-time methods in Minimum Description Length (MDL)-based clustering.
Sep 2, 2026
Data-Driven Fire-Zone Segmentation for Improved Short-Term Wildfire Prediction
Researchers introduced a new unsupervised fire-zone segmentation method that redefines prediction units using historical ignition patterns instead of uniform grids, yielding consistent +3–6% mean IoU improvements across six French departments and six models.
Aug 11, 2026
On Hamming-Lipschitz Type Stability of the Subdominant (Minmax) Ultrametric: Theory and Simple Proofs
A theoretical paper introduces a new stability framework for the subdominant ultrametric — a tree-structured representation used in hierarchical clustering — by analyzing how sparse perturbations to dissimilarity matrices propagate through minimum spanning trees, yielding precise Hamming–Lipschitz bounds on ultrametric change.
Aug 6, 2026
Imbalanced Data Clustering via Targeted Data Augmentation Using GMM and LLM
A new unsupervised data augmentation method combining Gaussian Mixture Models and Large Language Models is proposed to improve clustering of underrepresented topics in imbalanced NLP datasets.
Aug 3, 2026
Breaking Structural Isolation: Scalable Graph Clustering via Community-Aware Sampling and Structural Entropy
A new unsupervised graph clustering framework called SCISE is introduced to address 'structural isolation' in mini-batch training by combining community-aware sampling and structural entropy constraints, showing improved performance on six benchmark datasets.
Jul 9, 2026
Learnable Weighting of Intra-Attribute Distances for Categorical Data Clustering with Nominal and Ordinal Attributes
A new clustering algorithm introduces a learnable distance metric that distinguishes nominal and ordinal categorical attributes, unifying their treatment while preserving ordinal order — advancing methodological rigor in unsupervised learning for structured categorical data.
Jul 9, 2026
GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance
A Hacker News thread titled 'GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance' contains user comments speculating about an unconfirmed, non-existent model version and its hypothetical technical behavior.
Jul 6, 2026
Structural Pattern Mining in Inka Khipus: Unsupervised Clustering, Provenance Classification, and a Computational Validation of the Santa Valley Match
Researchers develop machine-learning pipeline for analyzing Inka khipus.
Published Jul 2, 2026 · Analyzed Jul 5, 2026