scripts/eval.py

#!/usr/bin/env python3
"""Re-verify the torch surrogate: sha256 the shipped model.safetensors against
TRAINING_RECEIPT.json, then deterministically regenerate the seeded dataset via
scripts/forge.py and compare re-measured fidelity to the receipt (tolerance 0.02).
Run from repo root: python scripts/eval.py"""
import hashlib, json, subprocess, sys, tempfile, os, shutil
root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
receipt = json.load(open(f"{root}/TRAINING_RECEIPT.json"))
got = hashlib.sha256(open(f"{root}/model.safetensors", "rb").read()).hexdigest()
want = receipt["model"]["sha256"]
print(f"model.safetensors sha256 {'MATCHES receipt' if got==want else 'MISMATCH — refuse'}: {got[:16]}…")
if got != want:
    sys.exit(1)
with tempfile.TemporaryDirectory() as td:
    shutil.copy(f"{root}/scripts/forge.py", f"{td}/forge.py")
    out = subprocess.run([sys.executable, f"{td}/forge.py"], capture_output=True, text=True, cwd=td)
    print(out.stdout[-400:] if out.returncode == 0 else out.stderr[-600:])
    if out.returncode:
        sys.exit(1)
    re_receipt = json.load(open(f"{td}/TRAINING_RECEIPT.json"))
    d = abs(re_receipt["metrics_MEASURED"]["fidelity_vs_kernel_heldout"]
            - receipt["metrics_MEASURED"]["fidelity_vs_kernel_heldout"])
    print(f"re-measured fidelity delta vs receipt: {d:.4f} ({'OK ≤0.02' if d<=0.02 else 'FAIL'})")
    sys.exit(0 if d <= 0.02 else 1)