PREPRINT V3.0 DOI: 10.5281/zenodo.22179715 OPEN ACCESS (CC-BY-4.0)

CorpusLD: A Dual-Layer Semantic Extraction Framework and Deep Knowledge Graph Architecture for Scientific Literature with Deterministic Unit Ontology and Dynamic Authority Disambiguation

Sharrif Faqih Fajarudin
Department of Electrical Engineering, Universitas Tanjungpura (UNTAN)

Abstract

Scientific and technical documents published in Portable Document Format (PDF) frequently function as unstructured "data graveyards," creating severe semantic isolation. Conventional Retrieval-Augmented Generation (RAG) and large language model (LLM) chunking pipelines suffer from three fundamental failure modes: top-K context truncation loss, multi-page tabular fragmentation, and numeric collisions caused by superscript citation markers polluting quantitative parameters (e.g., misinterpreting reference indices as numerical quantities).

To resolve these challenges, we introduce CorpusLD (Corpus + Linked Data), a production-grade, dual-layer semantic extraction engine and deep knowledge graph architecture. CorpusLD combines a macro-level W3C Schema.org ScholarlyArticle JSON-LD serialization with a micro-level Deep Knowledge Graph ($\mathcal{G} = (\mathcal{V}, \mathcal{E})$) spanning 10 formal semantic predicates. The system incorporates a 4-tier layout-aware parser, a section-wise map-reduce orchestrator, and a deterministic scientific unit ontology supporting Base SI, clinical, energy, and compound units. Furthermore, CorpusLD integrates a dynamic REST authority linker communicating with the Research Organization Registry (ROR v2) and Wikidata/MeSH registries.

Evaluated across an 8-document multi-disciplinary benchmark corpus (arXiv, IEEE, SINTA, and Springer), CorpusLD achieves 100% structural compliance on the Google Rich Results Test, extracts 100% of complex multi-page tables without boundary corruption, and eliminates superscript citation pollution deterministically. CorpusLD is released as an open-source framework and Python package.

Knowledge Graphs Linked Data Schema.org Semantic Web Information Extraction Retrieval-Augmented Generation (RAG) Scholarly Metadata Ontology Engineering Document Layout Analysis

Technical Architecture & Validation

CorpusLD processes unstructured multi-disciplinary PDFs through a deterministic 5-stage pipeline:

Stage 1
PDF Ingestion
Raw multi-page PDF decomposition into textual blocks, tables, and mathematical formulas.
Stage 2
4-Tier Hybrid Parser
LlamaParse, Unstructured.io, and Local PyPDF with 75% cloud cost reduction router.
Stage 3
5-Agent Map-Reduce
Deterministic section-wise extraction without Top-K context truncation.
Stage 4
Unit Ontology & ROR
De-aliases superscript citations and resolves institutional URIs via ROR v2 & Wikidata.
Stage 5
Dual-Layer Output
Simultaneous export to W3C Schema.org JSON-LD, RDF Turtle, and Neo4j Cypher.

Sample Cypher query executed on CorpusLD property graph to uncover conflicting methodologies and calibrated metrics across literature without vector re-ranking:

Cypher Property Graph Query
MATCH (p1:Paper)-[:USES_METHOD]->(m1:Method)
MATCH (p2:Paper)-[:USES_METHOD]->(m2:Method)
MATCH (m1)-[r:CONTRADICTS]->(m2)
MATCH (p1)-[:EVALUATES]->(k:Metric)
WHERE k.unit = 'ms' AND k.value < 50.0
RETURN p1.title AS PaperA, m1.name AS MethodA, 
       r.reason AS ConflictBasis, m2.name AS MethodB, 
       k.name AS MetricName, k.value AS LatencyVal;

Empirical comparative performance across 8 multi-disciplinary ground-truth benchmark documents:

Evaluation Metric Naive Vector RAG Baseline CorpusLD (Proposed)
Section Extraction Recall 54.2% 100.0%
Table Structure Preservation 37.6% 100.0%
Quantitative Metric Recall 51.3% 98.5%
Superscript Citation Error Rate 43.1% 0.0% (Zero Collision)
Context Truncation Loss Rate 48.7% 0.0% (Zero Loss)
Google Rich Results Structural Pass 0.0% 100.0%

Beyond static document ingestion, CorpusLD establishes the architectural foundation for Living Knowledge Graphs. By decoupling document visualization from binary document storage, CorpusLD federates with open scholarly registries (OpenAlex Works API, Crossref REST API, and Semantic Scholar) via persistent Digital Object Identifiers (DOIs).

By performing community detection (Louvain modularity) and structural hole analysis across multidisciplinary clusters (e.g., Edge TinyML, clinical Linked Data, and semantic RAG), the system algorithmically identifies topological voids—unexplored conceptual intersections with zero co-occurrence citations—actively directing researchers toward high-impact, unfilled research gaps.

🕸️ Launch Interactive Living Graph & Lineage Explorer

Cite This Work

Select your preferred citation format to copy directly into your bibliography or manuscript:

IEEE Standard Citation
S. F. Fajarudin, "CorpusLD: A Dual-Layer Semantic Extraction Framework and Deep Knowledge Graph Architecture for Scientific Literature with Deterministic Unit Ontology and Dynamic Authority Disambiguation," Zenodo, Aug. 2026. doi: 10.5281/zenodo.22179715.
Citation copied to clipboard!