Confidence Calibration for Evidence-Graded Knowledge Graph Edges: Methods, Metrics, and Cold-Start Protocols
Abstract
Paper 3 in the Prioris research series. Analyzes Platt scaling, isotonic regression, and temperature scaling for knowledge graph edge calibration. Proposes level-specific quality metrics and a cold-start calibration protocol. Shows ECE < 0.05 is achievable for inference-level edges with n >= 500 samples. Part of the research programme (Paper 0: 10.5281/zenodo.19024611).
Fields of Study & Subjects
Advanced Graph Neural Networks
Graph Theory and Algorithms
Data Quality and Management
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 14 March 2026
- Language
- EN
- Document type
- Preprint