Turning Citation Networks Inside Out: Studying Science Using Content-Based Knowledge Graphs from LLM-Derived Taxonomies

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kim, Seorin, Holst, Vincent, Ginis, Vincent
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908779944083456
author Kim, Seorin
Holst, Vincent
Ginis, Vincent
author_facet Kim, Seorin
Holst, Vincent
Ginis, Vincent
contents Scientific fields are often mapped using citations and metadata, despite knowledge being transmitted primarily through content. We introduce an 'inside-out' approach that reconstructs field structure directly from text by representing each paper as a small set of interpretable knowledge components. Using a large language model to induce domain-specific taxonomies and label papers, each publication is encoded as a triplet of measure, data type, and research-question type. These triplets define a knowledge graph with edges weighted by shared papers. Applied to 617 studies on intergenerational wealth mobility, the graph reveals a stable methodological backbone centered on regression-based mobility measures, alongside substantial temporal variation in component recombination. We further utilize normalized betweenness-to-connectivity ratios to identify components and pairings that act as structural bridges disproportionate to their prevalence. This content-derived, taxonomy-driven mapping complements citation-based approaches by exposing the evolving architecture of methods, data, and questions that define a field.
format Preprint
id arxiv_https___arxiv_org_abs_2601_15062
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Turning Citation Networks Inside Out: Studying Science Using Content-Based Knowledge Graphs from LLM-Derived Taxonomies
Kim, Seorin
Holst, Vincent
Ginis, Vincent
Social and Information Networks
Scientific fields are often mapped using citations and metadata, despite knowledge being transmitted primarily through content. We introduce an 'inside-out' approach that reconstructs field structure directly from text by representing each paper as a small set of interpretable knowledge components. Using a large language model to induce domain-specific taxonomies and label papers, each publication is encoded as a triplet of measure, data type, and research-question type. These triplets define a knowledge graph with edges weighted by shared papers. Applied to 617 studies on intergenerational wealth mobility, the graph reveals a stable methodological backbone centered on regression-based mobility measures, alongside substantial temporal variation in component recombination. We further utilize normalized betweenness-to-connectivity ratios to identify components and pairings that act as structural bridges disproportionate to their prevalence. This content-derived, taxonomy-driven mapping complements citation-based approaches by exposing the evolving architecture of methods, data, and questions that define a field.
title Turning Citation Networks Inside Out: Studying Science Using Content-Based Knowledge Graphs from LLM-Derived Taxonomies
topic Social and Information Networks
url https://arxiv.org/abs/2601.15062