Derive a unique per-job seed for minicalosim shard generation

Concurrent job launches in create_root_files.py can start within the
same wall-clock second, and minicalosim's default seed falls back to
time(NULL) in that case — so two "independent" shards could silently
get identical RNG state and produce byte-identical physics. Requires
the companion MINICALOSIM_SEED env-var support in the minicalosim repo.

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

scripts/create_root_files.py

@@ -25,6 +25,7 @@ import shutil
 import subprocess
 import sys
 import uuid
+import zlib
 from dataclasses import dataclass
 from concurrent.futures import ThreadPoolExecutor, as_completed
 from pathlib import Path
@@ -104,6 +105,20 @@ def plan_jobs(
     return jobs
 
 
+def job_seed(kind: str, gen: str, job: SimJob) -> int:
+    """Deterministic RNG seed for one sim job, unique per (kind, gen, detector, config, shard).
+
+    Jobs run concurrently (ThreadPoolExecutor below) and can start within the
+    same wall-clock second; minicalosim's default seed falls back to
+    time(NULL) in that case, so two concurrently-launched jobs can silently
+    get identical RNG state and produce byte-identical physics despite
+    landing in separate shard files. Deriving the seed from the full job
+    identity instead keeps it both unique and reproducible.
+    """
+    key = f"{kind}|{gen}|{job.detector}|{job.config or ''}|{job.shard_index}"
+    return zlib.crc32(key.encode()) & 0x7FFFFFFF
+
+
 def run_job(
     job: SimJob,
     executable: Path,
@@ -124,7 +139,8 @@ def run_job(
         cmd.append(job.config)
     cmd.append(str(events_per_file))
 
-    result = subprocess.run(cmd, cwd=workdir, capture_output=True, text=True)
+    env = dict(os.environ, MINICALOSIM_SEED=str(job_seed(kind, gen, job)))
+    result = subprocess.run(cmd, cwd=workdir, capture_output=True, text=True, env=env)
 
     if result.returncode != 0:
         return JobResult(
@@ -254,7 +270,8 @@ def run_make_root(
             / job.detector
             / f"shard-{job.shard_index:03d}.root"
         )
-        print(f"  {' '.join(cmd)}  ->  {dest}")
+        seed = job_seed(kind, gen, job)
+        print(f"  MINICALOSIM_SEED={seed} {' '.join(cmd)}  ->  {dest}")
 
     if not execute:
         print("\nDry run only — pass --execute to apply.")

tests/test_create_root_files.py

@@ -9,6 +9,7 @@ from scripts import create_root_files
 parse_detector_spec = create_root_files.parse_detector_spec
 next_shard_index = create_root_files.next_shard_index
 plan_jobs = create_root_files.plan_jobs
+job_seed = create_root_files.job_seed
 run_job = create_root_files.run_job
 run_all = create_root_files.run_all
 SimJob = create_root_files.SimJob
@@ -35,7 +36,13 @@ start = time.time()
 time.sleep({sleep})
 end = time.time()
 payload = json.dumps(
-    {{"argv": sys.argv[1:], "cwd": os.getcwd(), "start": start, "end": end}}
+    {{
+        "argv": sys.argv[1:],
+        "cwd": os.getcwd(),
+        "start": start,
+        "end": end,
+        "seed": os.environ.get("MINICALOSIM_SEED"),
+    }}
 )
 for i in range({output_count}):
     with open(f"out_{{i}}.root", "w") as f:
@@ -130,6 +137,42 @@ def test_plan_jobs_multiple_detectors_each_start_independently(tmp_path):
     assert by_detector["sampling_fe_scint"] == [0, 1]
 
 
+def test_job_seed_deterministic():
+    job = SimJob(detector="pbwo4", config=None, shard_index=3)
+    assert job_seed("steps", "gen1", job) == job_seed("steps", "gen1", job)
+
+
+def test_job_seed_varies_by_shard_index():
+    a = SimJob(detector="pbwo4", config=None, shard_index=0)
+    b = SimJob(detector="pbwo4", config=None, shard_index=1)
+    assert job_seed("steps", "gen1", a) != job_seed("steps", "gen1", b)
+
+
+def test_job_seed_varies_by_detector():
+    a = SimJob(detector="pbwo4", config=None, shard_index=0)
+    b = SimJob(detector="sampling_pb_scint", config="pb_scint", shard_index=0)
+    assert job_seed("steps", "gen1", a) != job_seed("steps", "gen1", b)
+
+
+def test_job_seed_varies_by_gen():
+    job = SimJob(detector="pbwo4", config=None, shard_index=0)
+    assert job_seed("steps", "gen1", job) != job_seed("steps", "gen2", job)
+
+
+def test_run_job_passes_deterministic_seed_env_var(tmp_path):
+    fake = _write_fake_executable(tmp_path / "fake_exe.py")
+    (tmp_path / "raw" / "steps" / "gen1").mkdir(parents=True)
+    tmp_root = tmp_path / ".sim-tmp"
+    tmp_root.mkdir()
+
+    job = SimJob(detector="pbwo4", config=None, shard_index=5)
+    result = run_job(job, fake, 10000, tmp_path, "steps", "gen1", tmp_root)
+
+    assert result.dest is not None
+    payload = json.loads(result.dest.read_text())
+    assert payload["seed"] == str(job_seed("steps", "gen1", job))
+
+
 def test_run_job_moves_output_to_correct_shard_path(tmp_path):
     fake = _write_fake_executable(tmp_path / "fake_exe.py")
     gen_dir = tmp_path / "raw" / "steps" / "gen1"