KGFMs can predict links using observed half-links, with performance varying across four scenarios of half-link visibility in inference graphs.
Title resolution pending
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
Autonomous FAIR Digital Objects augment FDOs with Semantic Web-based policy, announcement, and reputation-weighted agreement layers, resolving 56.3% of ClinVar conflicts in evaluation while tolerating bounded attacks.
Action Units are introduced as typed, composable components in knowledge graphs that encode epistemic, transformational, and intervention operations with explicit applicability conditions, enabling post-FAIR infrastructures via the TripleA principle.
Graph-PRefLexOR fine-tunes graph-native models with GRPO to organize reasoning into phases, yielding 40-65% gains in traceable hypothesis generation and 2-3x semantic diversity on 100 materials science questions.
Graph2Idea builds dynamic knowledge graphs from retrieved literature to supply compact, relational contexts that guide LLMs in generating novel, feasible, and high-quality scientific ideas, outperforming flat-text baselines on automatic metrics.
The authors introduce a three-part ontology-based verification system for AI agents that generates regulatory and adversarial test scenarios and issues machine-verifiable trust certificates, with pilot results indicating improved coverage over baselines in four industries.
A per-item Q-learning policy that explicitly decides which observed knowledge-graph facts to keep or drop outperforms fixed heuristics and sequence-memory baselines on the RoomKG benchmark at memory capacity 128.
IdeaForge combines multiple innovation methodologies through specialist agents on a persistent knowledge graph, using cross-methodology convergent claim linkages to rank and draft patent claims with higher traceability than single-method baselines.
ARLtR is a framework for jointly constructing knowledge graphs, embeddings, and grounded QA pairs from text, released as a Roman Empire dataset with over 19,000 entities and 8,400 QA pairs.
LLMs produced coherent but incomplete ontologies for the Blue Amazon domain that required human refinement to be fully satisfactory.
A phenotype-driven framework integrates GNNs, causal inference, probabilistic reasoning, and LLMs to expand knowledge graphs via multi-objective optimization that balances novelty, relevance, and evidence validation.
BifrostRAG combines dual knowledge graphs with hybrid retrieval to improve multi-hop question answering on construction safety regulations, reporting 87.3% F1 on a custom dataset.
MetaConfigurator gains an integrated RDF Authoring View that turns JSON/YAML/CSV into editable, queryable, visualizable RDF via AI-assisted RML mappings and SPARQL inside a single browser app.
Didact is a RAG-based prototype with an Evidence Rail for conversational capability discovery from integrated Australian defence documents and research publications.
The thesis proposes specialized algebraic, logical, and geometric methods to enable scalable reasoning over imprecise attributes, probabilistic triples, and incomplete schemas in knowledge graphs.
citing papers explorer
-
Half a Link can Be Enough to Predict a Whole Link: Understanding Generalization in Knowledge Graph Foundation Models
KGFMs can predict links using observed half-links, with performance varying across four scenarios of half-link visibility in inference graphs.
-
Autonomous FAIR Digital Objects: From Passive Assertions to Active Knowledge
Autonomous FAIR Digital Objects augment FDOs with Semantic Web-based policy, announcement, and reputation-weighted agreement layers, resolving 56.3% of ClinVar conflicts in evaluation while tolerating bounded attacks.
-
Actionable Understanding: Action Units for Bridging the Knowledge-Action Gap in Post-FAIR Knowledge Infrastructures
Action Units are introduced as typed, composable components in knowledge graphs that encode epistemic, transformational, and intervention operations with explicit applicability conditions, enabling post-FAIR infrastructures via the TripleA principle.
-
Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination
Graph-PRefLexOR fine-tunes graph-native models with GRPO to organize reasoning into phases, yielding 40-65% gains in traceable hypothesis generation and 2-3x semantic diversity on 100 materials science questions.
-
Graph2Idea:Retrieval-Augmented Scientific Idea Generation with Graph-Structured Contexts
Graph2Idea builds dynamic knowledge graphs from retrieved literature to supply compact, relational contexts that guide LLMs in generating novel, feasible, and high-quality scientific ideas, outperforming flat-text baselines on automatic metrics.
-
Toward Pre-Deployment Assurance for Enterprise AI Agents: Ontology-Grounded Simulation and Trust Certification
The authors introduce a three-part ontology-based verification system for AI agents that generates regulatory and adversarial test scenarios and issues machine-verifiable trust certificates, with pilot results indicating improved coverage over baselines in four industries.
-
Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability
A per-item Q-learning policy that explicitly decides which observed knowledge-graph facts to keep or drop outperforms fixed heuristics and sequence-memory baselines on the RoomKG benchmark at memory capacity 128.
-
IdeaForge: A Knowledge Graph-Grounded Multi-Agent Framework for Cross-Methodology Innovation Analysis and Patent Claim Generation
IdeaForge combines multiple innovation methodologies through specialist agents on a persistent knowledge graph, using cross-methodology convergent claim linkages to rank and draft patent claims with higher traceability than single-method baselines.
-
All Relations Lead to Rome: Automated Knowledge Graph Creation and Question Generation
ARLtR is a framework for jointly constructing knowledge graphs, embeddings, and grounded QA pairs from text, released as a Roman Empire dataset with over 19,000 entities and 8,400 QA pairs.
-
Specific Domain Ontology Construction Using Large Language Models
LLMs produced coherent but incomplete ontologies for the Blue Amazon domain that required human refinement to be fully satisfactory.
-
A phenotype-driven and evidence-governed framework for knowledge graph enrichment and hypotheses discovery in population data
A phenotype-driven framework integrates GNNs, causal inference, probabilistic reasoning, and LLMs to expand knowledge graphs via multi-objective optimization that balances novelty, relevance, and evidence validation.
-
Bridging Dual Knowledge Graphs for Multi-Hop Question Answering in Construction Safety
BifrostRAG combines dual knowledge graphs with hybrid retrieval to improve multi-hop question answering on construction safety regulations, reporting 87.3% F1 on a custom dataset.
-
MetaConfigurator: AI-Assisted RDF Authoring from JSON Data
MetaConfigurator gains an integrated RDF Authoring View that turns JSON/YAML/CSV into editable, queryable, visualizable RDF via AI-assisted RML mappings and SPARQL inside a single browser app.
-
Didact: A Cross-Domain Capability Discovery System for Defence
Didact is a RAG-based prototype with an Evidence Rail for conversational capability discovery from integrated Australian defence documents and research publications.
-
Scalable Uncertainty Reasoning in Knowledge Graphs
The thesis proposes specialized algebraic, logical, and geometric methods to enable scalable reasoning over imprecise attributes, probabilistic triples, and incomplete schemas in knowledge graphs.