diff --git a/giant/analysis/condor.py b/giant/analysis/condor.py
index 914c8ab..13c5183 100644
--- a/giant/analysis/condor.py
+++ b/giant/analysis/condor.py
@@ -130,7 +130,9 @@ class RunMeta:
         return cls(**json.loads(Path(path).read_text()))
 
 
-def _rows_per_chunk(rollout: str | Path, reference: str | Path, n_chunks: int) -> list[int]:
+def _rows_per_chunk(
+    rollout: str | Path, reference: str | Path, n_chunks: int
+) -> list[int]:
     """Rollout+reference row count of each ``event_id % n_chunks`` chunk.
 
     One cheap streaming ``group_by`` per side (just the ``event_id`` column) —
@@ -345,7 +347,9 @@ def _submit_description(cfg: SubmitConfig, wrapper: Path, jobs_file: Path) -> st
     )
 
 
-def _job_walltimes(run_dir: Path, ids: list[str], n_chunks: int) -> list[tuple[str, int, int]]:
+def _job_walltimes(
+    run_dir: Path, ids: list[str], n_chunks: int
+) -> list[tuple[str, int, int]]:
     """``(spec_id, chunk, walltime_s)`` for every job, sized from ``run_meta.json``.
 
     Row counts come from ``prep``'s ``RunMeta.rows_per_chunk``/``total_rows``;
diff --git a/giant/analysis/runtime_estimate.py b/giant/analysis/runtime_estimate.py
index 7f6cc37..f5279f7 100644
--- a/giant/analysis/runtime_estimate.py
+++ b/giant/analysis/runtime_estimate.py
@@ -54,7 +54,9 @@ _FIXED_OVERHEAD_S = 60.0
 # scan. Calibrated from the 3 real router jobs' observed wall times (119, 66,
 # 124s) — max minus _FIXED_OVERHEAD_S, on top of it.
 _ROUTER_FIXED_S = 64.0
-_ROUTER_IDS = frozenset({"router_gating", "router_share_by_pdg", "router_share_by_process"})
+_ROUTER_IDS = frozenset(
+    {"router_gating", "router_share_by_pdg", "router_share_by_process"}
+)
 
 # Conservative fallback for any catalog id not in _COST_MODEL (e.g. a plot
 # added after the last calibration run) — the most expensive fitted per-row
diff --git a/scripts/profile_analysis_costs.py b/scripts/profile_analysis_costs.py
index bbb0a98..de97a2b 100644
--- a/scripts/profile_analysis_costs.py
+++ b/scripts/profile_analysis_costs.py
@@ -68,9 +68,7 @@ def _make_rollout(n: int, n_events: int, seed: int) -> pl.DataFrame:
 
     reasons = np.where(
         is_synthetic,
-        rng.choice(
-            ["escaped", "energy_cutoff", "max_steps", "unknown_pdg"], size=n
-        ),
+        rng.choice(["escaped", "energy_cutoff", "max_steps", "unknown_pdg"], size=n),
         "natural_end",
     )
 
@@ -96,7 +94,9 @@ def _make_rollout(n: int, n_events: int, seed: int) -> pl.DataFrame:
             "post_dx": post_dir[:, 0],
             "post_dy": post_dir[:, 1],
             "post_dz": post_dir[:, 2],
-            "edep": np.where(is_synthetic, np.where(reasons == "escaped", 0.0, pre_E), edep),
+            "edep": np.where(
+                is_synthetic, np.where(reasons == "escaped", 0.0, pre_E), edep
+            ),
             "step_length": np.where(is_synthetic, 0.0, step_length),
             "material": rng.choice(_MATERIALS, size=n),
             "layer_id": rng.integers(0, 30, size=n),
@@ -163,11 +163,19 @@ def _make_reference(n: int, n_events: int, seed: int) -> pl.DataFrame:
     )
 
 
-def _time(spec_id: str, rollout: Path, reference: Path, shared: Path, out: Path) -> float:
+def _time(
+    spec_id: str, rollout: Path, reference: Path, shared: Path, out: Path
+) -> float:
     t0 = time.perf_counter()
     compute_reduced(
-        spec_id, rollout, reference, shared, out, checkpoint=None,
-        chunk_index=0, n_chunks=1,
+        spec_id,
+        rollout,
+        reference,
+        shared,
+        out,
+        checkpoint=None,
+        chunk_index=0,
+        n_chunks=1,
     )
     return time.perf_counter() - t0
 
@@ -187,8 +195,11 @@ def main() -> None:
 
             shared = tmp_path / f"shared_{n_side}.json"
             ctx = build_context(
-                rollout, reference,
-                n_energy_bins=4, n_marginal_bins=50, top_k_pdg=6,
+                rollout,
+                reference,
+                n_energy_bins=4,
+                n_marginal_bins=50,
+                top_k_pdg=6,
                 sample_rows=min(n_side, 200_000),
             )
             ctx.save(shared)