STRAND treats persistence diagrams as survival data to derive a calibrated two-sample test, interpretable effect sizes, and a 1-Wasserstein-stable feature vector from one representation.
https://arxiv.org/abs/2410.11042
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Persistent homology analysis of LLM activations shows most topological reorganization occurs early in fine-tuning, with a transient peak followed by stabilization and distinct trajectories for different alignment objectives.
Introduces the Patnaik-Pearson intrinsic dimension estimator, proves some of its properties, relates it to HTSR/SETOL for Pareto spectra, and applies it to track embedding dimension evolution in BERT-base and DeepSeek-R1-Distill-Qwen-1.
citing papers explorer
-
From Persistence to Survival: Hypothesis Testing, Effect Sizes and Vectorisation for Topological Features
STRAND treats persistence diagrams as survival data to derive a calibrated two-sample test, interpretable effect sizes, and a 1-Wasserstein-stable feature vector from one representation.
-
Tracking Representation Dynamics in Large Language Models with Persistent Homology
Persistent homology analysis of LLM activations shows most topological reorganization occurs early in fine-tuning, with a transient peak followed by stabilization and distinct trajectories for different alignment objectives.
-
Patnaik-Pearson intrinsic dimension for internal representations of neural networks
Introduces the Patnaik-Pearson intrinsic dimension estimator, proves some of its properties, relates it to HTSR/SETOL for Pareto spectra, and applies it to track embedding dimension evolution in BERT-base and DeepSeek-R1-Distill-Qwen-1.