feat(learning-harness): fix dates and the post-cutoff slice

The catalog generator fills `fix_date` from the recipe at the precision the
recipe has -- a full ISO day when one was recorded, otherwise the year.
Every harvested recipe carries a year and almost none carries a day, and
writing `-01-01` would turn a year into a claim about a month. A row counts
as post-cutoff only when its earliest possible date is after the cutoff, so
a coarse date can under-claim the clean slice but never over-claim it.

Each family now reports the same numbers over the rows fixed after the
cutoff, beside the whole number and never instead of it, with the undated
count on its own line. Without a configured cutoff every scoreboard says so
rather than inventing one: guessing a model's training cutoff and then
publishing a contamination number from the guess would be worse than
reporting none.

Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01T7XD7x5KonMdmGRkp63EQG

src/openultrasast/learning/rounds.py

@@ -99,6 +99,7 @@ def run_baseline(
     k_runs: int = DEFAULT_K_RUNS,
     prompt: str | None = None,
     spent_usd: Callable[[], float] | None = None,
+    cutoff: str = "",
 ) -> BaselineReport:
     """Clone one detector into every family, measure each family **with its own configuration**, write the artifacts.
 
@@ -123,7 +124,7 @@ def run_baseline(
         if config is None:
             continue  # a family with no configuration is not measured rather than measured with someone else's
         scores.append(score_case(case, scan_factory(config), taxonomy=taxonomy, runs=k_runs, family=name))
-    metrics = aggregate(scores, taxonomy=taxonomy)
+    metrics = aggregate(scores, taxonomy=taxonomy, cutoff=cutoff)
     floors = {name: _floor(name, block, [item for item in scores if item.family == name], k_runs) for name, block in metrics.items()}
     report = BaselineReport(
         model=model,
@@ -132,7 +133,7 @@ def run_baseline(
         slices=tuple(slices),
         floors=floors,
         metrics={name: block.to_dict() for name, block in metrics.items()},
-        per_slice={name: block.to_dict() for name, block in aggregate(scores, taxonomy=taxonomy, per_slice=True).items()},
+        per_slice={name: block.to_dict() for name, block in aggregate(scores, taxonomy=taxonomy, per_slice=True, cutoff=cutoff).items()},
         scores=tuple(scores),
         cost_usd=spent_usd() if spent_usd is not None else 0.0,
     )
@@ -156,6 +157,7 @@ def score_case(case: PairCase, scan: Scan, *, taxonomy: FamilyTaxonomy, runs: in
             runs=(),
             outcome="unscorable",
             slice=case.slice,
+            fix_date=case.fix_date,
             unscorable_reason=case.unscorable,
         )
     with tempfile.TemporaryDirectory(prefix="ousast-round-") as scratch: