| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| 180 prompts Aggregate (held-out) | Story Quality Score72.4 | 15 | 1mo ago | ||
| 180 held-out prompts Far OOD 8–12k | POLARIS | Story Quality Score44.1 | 1 | 1mo ago | |
| 180 prompts Near OOD 4–8k (held-out) | POLARIS | Story Quality Score48.2 | 1 | 1mo ago | |
| 180 held-out prompts (ID 1–4k) | POLARIS | Story Quality Score57.4 | 1 | 1mo ago |