Multi-Scale Structural Descriptors for Governance-Relevant Patterns in Data Lineage Graphs

Fuente: Zenodo
Enregistré dans:
Détails bibliographiques
Auteur principal: Malempati Hari, Dineshkumar
Format: Recurso digital
Publié: Zenodo 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866901651847118848
author Malempati Hari, Dineshkumar
author_facet Malempati Hari, Dineshkumar
contents Code, anonymised data, and experiment scripts. v2.1.0 adds Experiment 7: cross-organisation governance prediction at node granularity on the DLG-DG-23 dataset (Chen et al., Visual Informatics 2024). Using expert-annotated core data asset labels (36 labels across 6 Huawei Cloud lineage graphs), node-level topological features predict core-asset status at leave-one-graph-out logistic-regression AUC = 0.897 +/- 0.099 against random baseline 0.546 (p = 0.0003). Sensitivity check excluding 3 shared core-asset IDs: AUC = 0.890.
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_20209148
institution Zenodo
language
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle Multi-Scale Structural Descriptors for Governance-Relevant Patterns in Data Lineage Graphs
Malempati Hari, Dineshkumar
data governance
lineage graphs
community detection
spectral graph theory
persistent homology
structural descriptors
network analysis
core data asset
cross-organisation validation
Code, anonymised data, and experiment scripts. v2.1.0 adds Experiment 7: cross-organisation governance prediction at node granularity on the DLG-DG-23 dataset (Chen et al., Visual Informatics 2024). Using expert-annotated core data asset labels (36 labels across 6 Huawei Cloud lineage graphs), node-level topological features predict core-asset status at leave-one-graph-out logistic-regression AUC = 0.897 +/- 0.099 against random baseline 0.546 (p = 0.0003). Sensitivity check excluding 3 shared core-asset IDs: AUC = 0.890.
title Multi-Scale Structural Descriptors for Governance-Relevant Patterns in Data Lineage Graphs
topic data governance
lineage graphs
community detection
spectral graph theory
persistent homology
structural descriptors
network analysis
core data asset
cross-organisation validation
url https://doi.org/10.5281/zenodo.20209148