Measure the counterpart honestly: warm models, vectorised search, scope split

Three defects made the external baseline numbers and labels wrong.

- bench/systems.py: _sentence_model rebuilt the model on every query, so dense arm
  latency was mostly model loading and the latency-vs-size curve was flat because a
  constant dominated it. Models are now cached per process.
- bench/counterpart.py: visible() and search() walked 404k Python objects per query.
  Per-item holder/source/time columns are built once and the query path is numpy;
  12.5 queries/s instead of 0.7.
- bench/metrics.py: the aggregate key was named wrong_holder_confidence_unanswerable
  while it counts top hits that ARE from the asking holder. BASELINE.md read that
  backwards. Renamed to top_hit_from_holder_unanswerable and the sentence rewritten.
- bench/run_external.py: the by-modality table read row['answerable'] but aggregate
  emits n_answerable, so the writer died after scoring finished. Each store is now
  scored twice, [holder scope] and [whole corpus], so the gain from the holder
  boundary is separable from the gain from ranking; progress lines every 500 queries.

Verification: pytest bench/tests -q -> 61 passed; ruff check bench/ -> all checks
passed; mypy (fresh cache) -> no issues in 25 source files.

bench/run.py

@@ -292,7 +292,8 @@ def write_markdown(report: dict[str, Any], path: Path) -> None:
         overall = arm["overall"]
         lines.append(
             f"- {arm['arm']}: abstains on {overall['abstention_rate_unanswerable']:.0%} of unanswerable queries, "
-            f"and puts a wrong-holder source on top for {overall['wrong_holder_confidence_unanswerable']:.0%} of them"
+            f"and its top hit comes from the query's own holder for {overall['top_hit_from_holder_unanswerable']:.0%} of them; "
+            "the rest are confident answers pulled out of somebody else's memory"
         )
     if "live_product" in report:
         live = report["live_product"]