Climate-science knowledge graph: 134k nodes, 755k relations, every triple carries evidence
JeremyCMorgan · x · 2026-11-05
An arXiv paper (2610.32725) introduces an agentic, ontology-guided knowledge graph construction framework with released data and pipeline. Specialized agents handle document understanding, extraction, ontology conformance, and entity linking; every extracted triple must carry supporting text evidence, then passes multistage verification. In an agreement study over 1,000 triples, Gemini-2.5-flash scored Cohen's κ of 0.640–0.700 against three human annotators, matching the human–human range of 0.616–0.689. Applied to 2,000 climate-science publications, it produced a KG with 133,990 nodes and 755,308 relations, with 98.96% of 23,327 validated triples judged correct. The most reusable idea: every AI-extracted relationship must carry supporting text evidence.
More from Research
- Dejan's LLM brand study probes 193k brand mentions for just $391.71 using Gemini — dejanseo · 2026-11-13
- Galaxea Co-founder Hang Zhao's CoRL Keynote: Split Robot Intelligence into System 2/1/0 by Timescale — YuXiang_IRVL · 2026-11-13
- A Summary of the Macy Conferences: The Birthplace of Cybernetics and Early AI Thought — ArtificialOther · 2026-11-13
- vismatch: unified API wrapping 50+ image matching models, 943 stars on GitHub — gabriberton · 2026-11-13
- Stanford's Speculative Self-Distillation cuts training tokens 38-69% with less forgetting — khademinori · 2026-11-13
- EEPO: Adaptive Sample-Then-Forget Rollouts Break Diversity Collapse in RLVR Training — burkov · 2026-11-13