The G1 row compared against a van run whose server had loaded the legacy stock-lopia catalog, so its ids were template-level (sku_005) and every answer scored wrong. Re-run with both servers on stock-lopia-clean, 20 s pan 12: van 17/27 (63%) coverage 53% precision 7 wrong 6 unenrolled accepts local 19-20/27 (70-74%) 77-85% 0 wrong 0 unenrolled accepts G1 asks the new system to be no worse than Van on coverage; it is better on both axes, so G1 now reads as passing on the stream rather than unmeasured. Both recordings are committed under stream-gated/. |
||
|---|---|---|
| .. | ||
| research/2026-09-28-recognition-architecture | ||
| API.md | ||
| DATA.md | ||
| design-price-tags-and-compliance.md | ||
| EXTERNAL-EVAL.md | ||