A pipeline for matching bibliographic references with incomplete metadata: experiments with Crossref and OpenCitations

2025-11-23

AI Summary

Over 698 million references in Crossref lack DOIs, severely impeding the structural construction of citation networks. This paper proposes a systematic approach integrating heuristic rules, metadata matching, and fuzzy text parsing to accurately align unstructured references to target文献 entities in OpenCitations Meta. Methodologically, it combines an interpretable rule engine with semantic matching strategies—specifically designed to enhance linkage accuracy under sparse or inconsistent metadata conditions. Contributions include: (1) a novel hybrid alignment framework balancing precision and robustness; (2) a manually curated gold standard and a validated Crossref subset for rigorous evaluation. Experimental results demonstrate high precision, substantially expanding both the coverage breadth and linkage quality of the open citation network. The method provides a reproducible, scalable technical pathway for large-scale reference DOI enrichment.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Search and Optimization: Metareasoning and Metaheuristics
• Natural Language Processing: Information Extraction

Application Category

• Web Mining and Content Analysis: Bridging structured and unstructured data
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

While Crossref makes available more than 1.8 billion bibliographic references from publications for which it provides a DOI, more than 698 million of these references do not specify a DOI, making the creation of a formal citation link from the citing entity and the cited entity problematic. In this article, we propose an analysis of Crossref bibliographic references to show how we can use the unstructured text defining such references and the available (and partial) metadata specified in them to (a) map them to existing entities included in OpenCitations Meta and, then, (b) to enable the potential inclusion of additional and valid citations link among these entities. We have defined a precise methodology to address the analysis and run it against a manually defined Gold Standard and a subset of Crossref. While the heuristic-based tool developed has demonstrated strong matching precision and effective metadata integration, its recall limitations highlight the necessity of further enhancements to address metadata inconsistencies and leverage additional sources of citation data.

Problem

• Matching bibliographic references with incomplete metadata to existing entities
• Creating formal citation links when references lack specified DOIs
• Addressing metadata inconsistencies in Crossref references using heuristic tools

Innovation

• Pipeline matches references with incomplete metadata
• Heuristic tool integrates metadata for citation links
• Methodology tested against Crossref and OpenCitations datasets