SciBERT-Based Interpretable Framework for Citation Influence Classification Using Sparse Rationale Extraction

Assessing the influence of scientific citations is critical to understanding the impact of scholarly research beyond the raw citation counts. Recent neural models achieve strong performance in citation classification but typically function as black boxes, limiting their suitability for transparent b...

Descrición completa

Detalles Bibliográficos

Principais autores:	Arshad Iqbal, Muhammad Inam Ul Haq, Abdul Wahid, Shad Muhammad, Muhammad Yahya, Abdul Shahid
Formato:	Artigo
Idioma:	Inglês
Publicado:	IEEE 2026-01-01
Series:	IEEE Access
Assuntos:	Citation importance explainable AI SciBERT sparse rationale extraction HardKuma interpretability
Acceso en liña:	https://ieeexplore.ieee.org/document/11499403/
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!