{
  "status": "source_pytorch_reference_not_full_onnx_rerun",
  "dataset": "eval/heldout supported phone/address records",
  "records_total": 2000,
  "routing": "learned_router",
  "source_model": "epoch-100 last.pt; heldout was excluded from training and intermediate checkpointing, then used post hoc to compare e79 best.pt with e100 last.pt; e100 last.pt was selected for higher heldout answer exact; the source checkpoint container is not distributed in this package",
  "onnx_fp32_agreement_note": "The source PyTorch reference and the final ONNX FP32 rerun agree exactly on all nine reported accuracy metrics across the overall, address, and phone subsets.",
  "summary": {
    "address": {
      "n": 1032,
      "answer_exact": 0.9496124031007752,
      "recomputed_n": 1032,
      "recomputed_answer_exact": 0.9486434108527132,
      "target_exact": 0.015503875968992248
    },
    "overall": {
      "n": 2000,
      "answer_exact": 0.9705,
      "recomputed_n": 2000,
      "recomputed_answer_exact": 0.97,
      "target_exact": 0.453
    },
    "phone_number": {
      "n": 968,
      "answer_exact": 0.9927685950413223,
      "recomputed_n": 968,
      "recomputed_answer_exact": 0.9927685950413223,
      "target_exact": 0.9194214876033058
    }
  }
}