CorpusLD: A Dual-Layer Semantic Extraction Framework and Deep Knowledge Graph Architecture for Scientific Literature with Deterministic Unit Ontology and Dynamic Authority Disambiguation
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 explore these challenges, we introduce CorpusLD (Corpus + Linked Data), an experimental dual-layer semantic extraction pipeline and knowledge graph framework. CorpusLD combines a macro-level W3C Schema.org ScholarlyArticle JSON-LD serialization with a micro-level Deep Knowledge Graph () 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 validates structured Schema.org compliance, extracts multi-page tabular data, and mitigates superscript citation collisions. CorpusLD is released as an open-source experimental framework and research prototype.
Technical Architecture & Validation
CorpusLD processes unstructured multi-disciplinary PDFs through a deterministic 5-stage pipeline:
Sample Cypher query executed on CorpusLD property graph to uncover conflicting methodologies and calibrated metrics across literature without vector re-ranking:
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;
Observable extraction yield evaluated across 8 multi-disciplinary benchmark documents (arXiv, IEEE, SINTA, Springer):
| Evaluated Document | Domain | Authors | Sections | Tables | Citations | Metrics |
|---|---|---|---|---|---|---|
Al-Amin et al. |
Higher Ed (SINTA) | 6 | 4 | 1 | 6 | 8 |
Mamba (arXiv) |
CS / Deep Learning | 2 | 34 | 7 | 116 | 13 |
E-Methanol (v1) |
Chemical Eng | 6 | 18 | 5 | 19 | 31 |
ESBMC Arduino |
Formal Verification | 4 | 37 | 9 | 4 | 3 |
Biowaste Energy |
Environmental Sci | 4 | 10 | 2 | 15 | 10 |
IEEE Market BESS |
Electrical Eng | 3 | 5 | 1 | 19 | 5 |
Simplex Arch |
Information Theory | 3 | 16 | 8 | 20 | 19 |
Peatland (IJSDP) |
Sustainability | 8 | 28 | 3 | 38 | 42 |
* Evaluated with CorpusLD benchmark harness (benchmark_runner.py) testing section delineation, table stitching, and entity resolution.
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.
Cite This Work
Select your preferred citation format to copy directly into your bibliography or manuscript:
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.