fix(learning-harness): a slice is part of what identifies a baseline

Keyed by model alone, the memory-safety run over the vfc slice silently
replaced the run over the web families, and the published table would have
shown one of them as if it were everything. The artifact key and the
comparison label now carry the slice selection when it is not the default.

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

src/openultrasast/cli.py

@@ -1343,7 +1343,7 @@ def _learning_run(args: argparse.Namespace, cases: Sequence[PairCase], taxonomy:
         model=model,
         journal=journal,
         archive=Archive(out / "archive.jsonl"),
-        floors=load_noise_floors(out, model),
+        floors=load_noise_floors(out, model, (args.slice,) if args.slice != "all" else DEFAULT_SLICES),
         out_dir=out,
         cost_cap_usd=args.cost_cap_usd or config.learning.round_cost_cap_usd,
         minibatch=config.learning.minibatch,

src/openultrasast/learning/rounds.py

@@ -196,7 +196,10 @@ def compare_baselines(out_dir: Path) -> dict[str, dict[str, dict[str, object]]]:
         if not report.is_file():
             continue
         payload = json.loads(report.read_text(encoding="utf-8"))
-        table[str(payload.get("model", directory.name))] = {family: dict(block) for family, block in (payload.get("metrics") or {}).items()}
+        model = str(payload.get("model", directory.name))
+        slices = tuple(str(item) for item in (payload.get("slices") or ()))
+        label = model if not slices or slices == DEFAULT_SLICES else f"{model} ({', '.join(slices)})"
+        table[label] = {family: dict(block) for family, block in (payload.get("metrics") or {}).items()}
     return table
 
 
@@ -224,8 +227,18 @@ def _family_of(case: PairCase, taxonomy: FamilyTaxonomy) -> str:
     return answer.families[0] if answer.families else "unknown"
 
 
+def _artifact_key(model: str, slices: Sequence[str]) -> str:
+    """What identifies a baseline run: the detector model, and the slice selection when it is not the default.
+
+    Keyed by model alone, a run over the memory-safety slice silently replaces the run over the web families and
+    the published table shows one of them as if it were everything (Req 8.4)."""
+    if tuple(slices) == DEFAULT_SLICES:
+        return _slug(model)
+    return f"{_slug(model)}-{_slug('-'.join(sorted(slices)))}"
+
+
 def _write(out_dir: Path, report: BaselineReport) -> None:
-    directory = out_dir / "baseline" / _slug(report.model)
+    directory = out_dir / "baseline" / _artifact_key(report.model, report.slices)
     directory.mkdir(parents=True, exist_ok=True)
     payload = report.to_dict()
     (directory / "noise-floors.json").write_text(
@@ -239,9 +252,9 @@ def _slug(model: str) -> str:
     return re.sub(r"[^A-Za-z0-9._-]+", "-", model).strip("-") or "unnamed"
 
 
-def load_noise_floors(out_dir: Path, model: str) -> dict[str, NoiseFloor]:
+def load_noise_floors(out_dir: Path, model: str, slices: Sequence[str] = ()) -> dict[str, NoiseFloor]:
     """The budgets a later round must stay inside, as round zero measured them for this model."""
-    path = out_dir / "baseline" / _slug(model) / "noise-floors.json"
+    path = out_dir / "baseline" / _artifact_key(model, slices or DEFAULT_SLICES) / "noise-floors.json"
     if not path.is_file():
         return {}
     payload = json.loads(path.read_text(encoding="utf-8"))