Condition on material/particle physical properties instead of learned embeddings

Adds model.conditioning = "physical" | "embedding": physical mode routes
particle mass/charge and material Z_eff/A_eff/density/X0/lambda_int through
small MLPs to replace the learned PDG/material embedding tables, so the
surrogate generalizes to PDG codes/materials outside the training vocab
instead of memorizing it. "embedding" stays available as the comparison
baseline (old checkpoints without the key default to it).

Stage 2 now regresses a secondary's mass/charge directly against a fixed
physics-derived target instead of a learned/snapped embedding, and uses no
snapping at inference — the model's raw predicted (mass, charge) is the
secondary's physical identity, including for its own further rollout steps.
A separate reporting-only nearest-known-PDG lookup (never fed back into the
model) populates output pdg columns / the embedding-mode rollout fallback.

giant/materials.py's table is populated with Geant4's own built-in NIST
constants (Z_eff, A_eff, density, X0, lambda_int), extracted directly from
the Geant4 11.4.1 build vendored in minicalosim via G4NistManager rather
than hand-typed literature values. G4_LYSO is left unfilled: confirmed (both
by runtime lookup and by searching minicalosim's history) that it's never
actually a constructed Geant4 material there, only documentation/UI color-map
text.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

tests/test_rollout.py

@@ -20,17 +20,22 @@ PDG_MAP = {22: 0, 11: 1, -11: 2}
 MAT_MAP = {"G4_AIR": 0, "G4_PbWO4": 1}
 
 
-def _models():
-    s1 = DenoisingMLP(pdg_vocab=3, mat_vocab=2, hidden_dim=32, n_blocks=2)
-    s2 = SecondaryDecoder(pdg_vocab=3, mat_vocab=2, hidden_dim=32, n_blocks=2)
+def _models(conditioning="embedding"):
+    s1 = DenoisingMLP(
+        pdg_vocab=3, mat_vocab=2, hidden_dim=32, n_blocks=2, conditioning=conditioning
+    )
+    s2 = SecondaryDecoder(
+        pdg_vocab=3, mat_vocab=2, hidden_dim=32, n_blocks=2, conditioning=conditioning
+    )
     return s1.eval(), s2.eval()
 
 
 def _norms():
     rng = np.random.default_rng(0)
-    cond = Normalizer().fit(rng.standard_normal((1000, 8)).astype(np.float32))
+    cond = Normalizer().fit(rng.standard_normal((1000, 15)).astype(np.float32))
     tgt = Normalizer().fit(rng.standard_normal((1000, 9)).astype(np.float32))
-    return cond, tgt
+    sec_phys = Normalizer().fit(rng.standard_normal((1000, 2)).astype(np.float32))
+    return cond, tgt, sec_phys
 
 
 def _oracle():
@@ -63,11 +68,12 @@ def _run(
     max_steps=30,
     max_tracks_per_event=300,
     seeds=None,
+    conditioning="embedding",
 ):
     torch.manual_seed(0)
     np.random.seed(0)
-    s1, s2 = _models()
-    cond, tgt = _norms()
+    s1, s2 = _models(conditioning)
+    cond, tgt, sec_phys = _norms()
     return rollout(
         s1,
         s2,
@@ -75,6 +81,7 @@ def _run(
         seeds or _seeds(),
         cond,
         tgt,
+        sec_phys,
         PDG_MAP,
         MAT_MAP,
         energy_cutoff=energy_cutoff,
@@ -83,9 +90,35 @@ def _run(
         batch_size=128,
         max_tracks_per_event=max_tracks_per_event,
         escape_threshold=escape_threshold,
+        conditioning=conditioning,
     )
 
 
+@pytest.fixture
+def fake_material_props(monkeypatch):
+    import giant.materials as gm
+
+    fake = {
+        "G4_AIR": gm.MaterialProperties(
+            z_eff=7.3, a_eff=14.4, density=1.2e-3, x0=3.0e4, lambda_int=7.0e5
+        ),
+        "G4_PbWO4": gm.MaterialProperties(
+            z_eff=75.6, a_eff=205.3, density=8.28, x0=0.89, lambda_int=20.7
+        ),
+    }
+    monkeypatch.setattr(gm, "MATERIAL_PROPERTIES", fake)
+    return fake
+
+
+def test_rollout_physical_conditioning_end_to_end(fake_material_props):
+    """Physical-mode rollout runs to completion; spawned secondaries carry
+    mass/charge forward (no snapping) and the output pdg column is populated
+    via the reporting-only nearest-known-PDG label."""
+    rec = _run(conditioning="physical")
+    assert len(rec["event_id"]) > 0
+    assert set(np.unique(rec["pdg"]).tolist()) <= set(PDG_MAP.keys())
+
+
 def test_seed_frontier_track_ids():
     seeds = _seeds(3)
     fr, counts = make_seed_frontier(**seeds)
@@ -171,7 +204,7 @@ def _run_streaming(on_chunk, **kwargs):
     torch.manual_seed(0)
     np.random.seed(0)
     s1, s2 = _models()
-    cond, tgt = _norms()
+    cond, tgt, sec_phys = _norms()
     seeds = kwargs.pop("seeds", None) or _seeds()
     return rollout(
         s1,
@@ -180,6 +213,7 @@ def _run_streaming(on_chunk, **kwargs):
         seeds,
         cond,
         tgt,
+        sec_phys,
         PDG_MAP,
         MAT_MAP,
         energy_cutoff=kwargs.pop("energy_cutoff", 1.0),