{"total":6,"items":[{"citing_arxiv_id":"2606.03365","ref_index":18,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Link Prediction or Perdition: the Seeds of Instability in Knowledge Graph Embeddings","primary_cat":"cs.LG","submitted_at":"2026-06-02T09:13:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"KGEMs for link prediction exhibit high instability in predictions and embeddings from initialization, negative sampling, and other factors, with better MRR not ensuring higher stability.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17669","ref_index":29,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Multimodal Cultural Heritage Knowledge Graph Extension with Language and Vision Models","primary_cat":"cs.AI","submitted_at":"2026-05-17T22:02:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Authors release the multimodal WJoconde knowledge graph for French cultural heritage and a LLM-VLM pipeline that extracts and validates new triples from unstructured text and images to extend the graph.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.13910","ref_index":41,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"PARK: Personalized academic retrieval with knowledge-graphs","primary_cat":"cs.IR","submitted_at":"2025-07-18T13:41:01+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PARK personalizes academic search by embedding a citation-derived knowledge graph into the same vector space as a neural retrieval model, beating baselines in three of four domains.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2506.23141","ref_index":10,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Context-Driven Knowledge Graph Completion with Semantic-Aware Relational Message Passing","primary_cat":"cs.AI","submitted_at":"2025-06-29T08:37:48+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":5.0,"formal_verification":"none","one_line_summary":"SARMP improves knowledge graph link prediction by selecting the Top-K semantically relevant edges per node and aggregating them with multi-head attention, beating some baselines on FB15k-237 and Kinship but not all benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2506.19661","ref_index":126,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Higher-Order Graph Databases","primary_cat":"cs.DB","submitted_at":"2025-06-24T14:24:20+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Encoding higher-order structures as heterogeneous property graphs lets standard graph databases support hyperedges, node-tuples, and subgraphs; a Neo4j-based prototype, ACID discussion, complexity analysis, and a GNN accuracy demonstration are presented.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2506.03576","ref_index":18,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"KG-BiLM: Knowledge Graph Embedding via Bidirectional Language Models","primary_cat":"cs.CL","submitted_at":"2025-06-04T04:47:24+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A bidirectional decoder with a graph-aware attention mask, knowledge-masked prediction, and contrastive sub-graph alignment achieves reported state-of-the-art link prediction on Wikidata5M and competitive results on WN18RR.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}