Open Research Knowledge Graph (ORKG)
The Open Research Knowledge Graph (ORKG) is an open infrastructure for representing research contributions as structured, machine-actionable knowledge. Instead of only storing papers as documents, ORKG models key claims, methods, and results as a knowledge graph so they can be compared across publications.
What it would change
The literature is a set of documents whose relationships exist only in prose. Which studies used the same method, which contradict each other, which relied on a dataset later found to have a calibration problem — all recoverable by reading enough papers, none of it queryable.
ORKG models the claims themselves rather than the documents, so comparisons between studies become structured rather than narrative. A comparison table over a research question, built from represented contributions instead of assembled by hand, is the concrete form of this.
The binding constraint is not the technology. It is that someone has to build the statements. Automatic extraction from text is unreliable for anything requiring judgment, and manual curation does not scale to the literature — which is the difficulty every project of this kind meets, and the reason coverage rather than capability determines whether it is useful.
Connection to FAIR
ORKG supports the goals of FAIR principles by improving findability, interoperability, and reuse of research Metadata and claims.
Related notes
Machine-actionable knowledge for Earth science covers the domain-specific version of the problem, and ORKG reborn the structured publication workflow. Knowledge graphs generally, and the ontology commitment they require, are the wider context — see the open science map.