Publishing FAIR and Machine-actionable Reviews in Materials Science: The Case for Symbolic Knowledge in Neuro-symbolic Artificial Intelligence

TL;DR

This paper advocates for publishing scientific reviews in materials science as FAIR, machine-actionable data within the Open Research Knowledge Graph, emphasizing the importance of symbolic knowledge for reliable neurosymbolic AI, complemented by large language models.

Contribution

It introduces a method to publish review data as structured, queryable knowledge in ORKG and argues for the primacy of symbolic knowledge over LLMs in materials science AI applications.

Findings

FAIR, machine-actionable review tables enable better knowledge reuse.

Symbolic querying outperforms LLM-based querying in reliability.

A curated symbolic layer enhances neurosymbolic AI robustness.

Abstract

Scientific reviews are central to knowledge integration in materials science, yet their key insights remain locked in narrative text and static PDF tables, limiting reuse by humans and machines alike. This article presents a case study in atomic layer deposition and etching (ALD/E) where we publish review tables as FAIR, machine-actionable comparisons in the Open Research Knowledge Graph (ORKG), turning them into structured, queryable knowledge. Building on this, we contrast symbolic querying over ORKG with large language model-based querying, and argue that a curated symbolic layer should remain the backbone of reliable neurosymbolic AI in materials science, with LLMs serving as complementary, symbolically grounded interfaces rather than standalone sources of truth.