Question Answering on Task 1 pooled across three runs 1.0 (test)
24Ours Win CountTyped claim network
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| Typed claim networkDimension=Overall (weighted)2026.05 | 24 | — | 7 | 63.2 | 60 | 0.143 | — | |
| Typed claim networkDimension=Multi-source Integration2026.05 | 13 | — | 20 | 52 | 40 | 1 | 1 | |
| Typed claim networkDimension=Relevance2026.05 | 12 | — | 23 | 54.5 | 33.3 | 0.832 | 1 | |
| Typed claim networkDimension=Factual Correctness2026.05 | 10 | — | 30 | 66.7 | 55.61 | 0.302 | 1 | |
| Typed claim networkDimension=Conciseness2026.05 | 10 | — | 20 | 40 | 14.3 | 0.424 | 1 | |
| Standard RAGDimension=Relevance2026.05 | — | 10 | — | — | — | — | — | |
| Standard RAGDimension=Factual Correctness2026.05 | — | 5 | — | — | — | — | — | |
| Standard RAGDimension=Multi-source Integration2026.05 | — | 12 | — | — | — | — | — | |
| Standard RAGDimension=Conciseness2026.05 | — | 15 | — | — | — | — | — | |
| Standard RAGDimension=Overall (weighted)2026.05 | — | 14 | — | — | — | — | — |