Benchmark RadarAI BENCHMARK PROFILE
OpenRTAG
OpenRTAG evaluates text-attributed graph learning under nine degradation scenarios (sparsity, noise, imbalance) across nine TAG datasets and three downstream tasks. It provides a standardized testbed for robustness comparison.
- Released
- 2026-07-21
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
Real-world TAGs suffer from data quality issues, but evidence on robustness is fragmented. OpenRTAG unifies these scenarios, enabling systematic evaluation and comparison of mitigation strategies across model families.
Motivation
Text-attributed graphs (TAGs) are an important graph data form that combine relational structure with rich node text.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.