| # Baseline Results (dlb-results-summary-v1) | |
| - complete: `false` | |
| - expected supported tasks: `137` | |
| - valid result rows: `130` | |
| - failures: `7` | |
| - unsupported cells: `1` | |
| A strict result set requires every supported task to have 1,024 samples, three quality metrics, one independent timing artifact, and matching provenance. | |