Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

TOPIC · ENTITY #6714

knowledge graph

Related event timeline, sources and context from the news index.

EVENT TIMELINE

3

RESEARCH · 1 SOURCE · arXiv cs.AI

Study: graph serialization choice substantially affects LLM structural reasoning

The paper (arXiv:2610.22734v1) evaluates 15 graph serialization formats across nine frontier LLM configurations on ontology-based knowledge extraction and structural graph reasoning tasks. It finds knowledge extraction is relatively insensitive to format, but structural reasoning accuracy depends strongly on the serialization, with the best format varying by model, query, and task; the authors propose treating serialization as a dynamic orchestration decision.

7.0

COMPANIES · 1 SOURCE · InfoQ AI, ML & Data Engineering

Netflix presents ontology‑driven E2E knowledge graph for observability

Netflix engineers Prasanna Vijayanathan and Renzo Sanchez‑Silva presented at QCon London an approach to observability that unifies MELT telemetry into a queryable end‑to‑end knowledge graph. They described replacing reactive monitoring with an AI‑driven operational ontology and agentic workflows (using Claude and graph databases) to enable automated triage, root‑cause analysis and self‑healing at Netflix scale (reported ~38M events/sec, 65M concurrent streams peak).

6.0

RESEARCH · 1 SOURCE · arXiv cs.AI

Graph-guided evidence navigation improves a local 9B model's reasoning on novels (exploratory arXiv result)

The arXiv preprint (arXiv:2609.22939v1) tests whether a frozen knowledge graph can help a local 9B model (qwen3.5:9b) answer questions about long novels. Across 30 detective novels and 234 multiple-choice questions, the best graph-based retrieval route reached 53.85% accuracy versus 46.15% for a recent-window baseline and ~51% for whole-book compression and vector retrieval; however, none of the fifteen graph vs baseline contrasts survive Holm correction, so the authors present these results as exploratory. Two more robust findings are that annotated evidence is enriched in the graphs' topological core (2.35× pooled) and that two graph-construction pipelines differ greatly in paragraph coverage (16% vs 73%), indicating pipeline bottlenecks that affect performance reporting.

5.0