Compare: A Framework for Scientific Comparisons

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Staudinger, Moritz, Kusa, Wojciech, Cancellieri, Matteo, Pride, David, Knoth, Petr, Hanbury, Allan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914027430477824
author Staudinger, Moritz
Kusa, Wojciech
Cancellieri, Matteo
Pride, David
Knoth, Petr
Hanbury, Allan
author_facet Staudinger, Moritz
Kusa, Wojciech
Cancellieri, Matteo
Pride, David
Knoth, Petr
Hanbury, Allan
contents Navigating the vast and rapidly increasing sea of academic publications to identify institutional synergies, benchmark research contributions and pinpoint key research contributions has become an increasingly daunting task, especially with the current exponential increase in new publications. Existing tools provide useful overviews or single-document insights, but none supports structured, qualitative comparisons across institutions or publications. To address this, we demonstrate Compare, a novel framework that tackles this challenge by enabling sophisticated long-context comparisons of scientific contributions. Compare empowers users to explore and analyze research overlaps and differences at both the institutional and publication granularity, all driven by user-defined questions and automatic retrieval over online resources. For this we leverage on Retrieval-Augmented Generation over evolving data sources to foster long context knowledge synthesis. Unlike traditional scientometric tools, Compare goes beyond quantitative indicators by providing qualitative, citation-supported comparisons.
format Preprint
id arxiv_https___arxiv_org_abs_2509_06412
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Compare: A Framework for Scientific Comparisons
Staudinger, Moritz
Kusa, Wojciech
Cancellieri, Matteo
Pride, David
Knoth, Petr
Hanbury, Allan
Digital Libraries
Information Retrieval
Navigating the vast and rapidly increasing sea of academic publications to identify institutional synergies, benchmark research contributions and pinpoint key research contributions has become an increasingly daunting task, especially with the current exponential increase in new publications. Existing tools provide useful overviews or single-document insights, but none supports structured, qualitative comparisons across institutions or publications. To address this, we demonstrate Compare, a novel framework that tackles this challenge by enabling sophisticated long-context comparisons of scientific contributions. Compare empowers users to explore and analyze research overlaps and differences at both the institutional and publication granularity, all driven by user-defined questions and automatic retrieval over online resources. For this we leverage on Retrieval-Augmented Generation over evolving data sources to foster long context knowledge synthesis. Unlike traditional scientometric tools, Compare goes beyond quantitative indicators by providing qualitative, citation-supported comparisons.
title Compare: A Framework for Scientific Comparisons
topic Digital Libraries
Information Retrieval
url https://arxiv.org/abs/2509.06412