Semantically-Linked Ontological Knowledge Extraction Graph For Domain-Specific Knowledge Discovery In Scientific Literature
Bibliographic record
Abstract
The rapid growth of scientific papers presents several challenges for researchers, including information overload, data fragmentation, lack of standard terminology, and limited interoperability. These issues make it increasingly difficult to keep up with the literature and extract useful, field-specific information efficiently. To address these challenges, we introduce the semantically-linked ontological knowledge extraction framework, a tool that combines smart linking of concepts, flexible ontology building, and graph-based reasoning to organize and extract knowledge. This semantically-linked ontological knowledge extraction graph (SOKE Graph) leverages large-language models to extract domain-specific concepts from scientific articles, ensuring both semantic accuracy and adaptability to new data. These concepts are organized using an ontology—a structured framework of terms and relationships—that supports systematic data collection by grouping information into clearly defined layers. The resulting knowledge graph enables structured representation of extracted domain-specific information, allowing researchers to explore relationships between concepts and efficiently retrieve relevant data aligned with the objectives of this work. This approach allows SOKE Graph to find the connections between concepts and publications, and retrieve the most relevant studies in response to user questions. Initial evaluations of SOKE Graph show that it helps improve the accuracy of filtering high-relevance papers from large datasets compared to using only large-language models, and generates structured, interpretable outputs that facilitate data-driven insights. Moreover, this framework provides a robust and scalable artificial intelligence-based tool that accelerates literature analysis, guides decision-making, and helps researchers efficiently locate relevant information within complex scientific domains.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.015 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.017 | 0.014 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.003 | 0.005 |
| Open science | 0.001 | 0.004 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".