OntoKG-EQ: A provenance-grounded, competency-question-governed knowledge graph for auditable analyst querying
AuthorsFurqan Nasir, Muhammad Atif Saeed, Muhammad Ehsan, Sher Jeel Ahmad, Abdul Moiz Altaf
Resources
OntoKG-EQ turns emerging-market financial analysis into reproducible, provenance-linked answers that can be checked from the final claim back to the original evidence.
Key results
Ontology, SHACL shapes, queries, rules, and code logic are reused after data alignment.
The 64-stock scaled run materialized this many RDF triples.
The eight-model transcription study reached a lower-bound provenance coverage of 0.00, with results ranging to 1.00.
Evidence bundles increased perceived trust by 2.87 points on a 7-point scale in the 17-participant study.
What the paper found
OntoKG-EQ is a provenance-grounded knowledge-graph system for auditable equity analysis in Pakistan, Malaysia, and Indonesia. Instead of forecasting prices, it governs the graph with five frozen competency questions covering fundamentals versus market response, currency associations, relative outperformance, announcement reactions, and explanations. The pipeline materializes sourced observations as RDF, computes nine derived metrics, validates structure with SHACL, answers parameterized SPARQL queries, materializes typed findings through deterministic rules, and generates evidence bundles linking each result to observations, official sources, and provenance. Across the three markets, 100% of the ontology, shapes, queries, rules, and code logic are reused after manual data alignment; a scaled Indonesia graph contains 37046 triples and covers 64 stocks. Unlike GraphRAG, OntoKG-EQ does not generate factual content, so deterministic rendering is faithful by construction. As a reference for language-model transcription, eight open models—including Qwen2.5, Mistral-7B, and Phi-3.5-mini—showed provenance coverage from 0.00 to 1.00, demonstrating that model size alone does not ensure traceability. A 17-participant study found that attaching evidence increased perceived trust by 2.87 points on a 7-point scale. The paper also discloses using Anthropic Claude for prose and script assistance, while emphasizing that experiments and results were independently verified. Its central contribution is governance and inspectability, not better analytics: SQL produced identical analytical results, while OntoKG-EQ supplied standardized validation, provenance, and self-explaining output.
Original abstract
Analysts in emerging equity markets keep answering the same questions. Did fundamentals match the market's response? How does the local currency co-move with returns? Which firms outperform sector and benchmark, and which disclosures coincide with abnormal trading? These answers come from ad-hoc spreadsheets that are hard to reproduce, audit, or trust. We present OntoKG-EQ, a knowledge-based system that makes such queries reproducible, evidence-linked, temporally explicit, valid, and inspectable. It couples a bounded, competency-question-governed core ontology with a provenance-aware knowledge graph in which every class, property, shape, and metric is justified by one of five frozen questions. The system materialises market data into the graph, computes the metrics, validates its structure against declarative shape constraints, answers each competency question with a graph query, derives typed findings, and generates an explanation tracing each result to its observations, evidence, sources, and provenance. We evaluate on curated datasets from three emerging markets (Pakistan, Malaysia, Indonesia). Once each market's data is mapped into the common schema, the ontology, shapes, queries, and rules are reused unchanged. A relational-database baseline shows the graph changes no analytics. Its value is governance, provenance, and self-explaining structure. Because answers are rendered deterministically from the validated graph, their consistency with it is guaranteed by construction. Used as a reference, the system measures how consistently eight open language models transcribe the same evidence (provenance coverage 0.00 to 1.00). A study with a 17-participant convenience panel finds the evidence bundle significantly increased perceived trust and completeness. Code and data are openly released.
Read the original paperMore in Graph Learning
Browse all 32 papers →CodeGraph: Open-Taxonomy Knowledge Graph for Source Code with Wikidata Grounding
Federico Pennino, Andrea Gurioli, Stefano Zacchiroli, Maurizio Gabbrielli, Paolo Ferragina
CodeGraph turns 167 million source files into a Wikidata-grounded knowledge graph of algorithms, paradigms, patterns, and software domains.
GraphWrit3R: End-to-End 3D Scene Graph Writing
Luka Milivojevic, Nikola Popovic, Sayan Deb Sarkar, Sebastian Koch, Iro Armeni, Luc Van Gool, Danda Pani Paudel
GraphWrit3R turns 3D spatial data into open-vocabulary scene graphs using multimodal encoders and an LLM, without requiring ground-truth object annotations at inference.
Statistical Inference for Causal Discovery under Selection and Latent Variables via Single-Target Interventions
Xiaotian Hou, Kwangmoon Park, Hongzhe Li
This work shows how a small, carefully designed set of single-variable interventions can recover causal structure even when hidden confounders and selection bias complicate the data.