{
  "run_id": "TayHCode--sysone-cpu-claude-haiku-5-5-1792644887338465139",
  "checker": {
    "claims": [
      {
        "claim": "The README quickstart benchmark command runs PyTorch FP32 inference on CPU and writes its results file",
        "command": "<guest-path> run --no-project --python .venv python benchmarks/bench_laya_cpu.py --model .cache/model/typed-decisions --threads 4 --warmup 1 --repeats 1 --counts 1,3 --output .cache/claim-bench.json",
        "evidence": "wrote .cache/claim-bench.json\n",
        "expected": "stdout reports the file was written",
        "input": "same command with --output .cache/claim-bench.json",
        "kind": "claim",
        "outcome": "Real input produced the expected result: wrote .cache/claim-bench.json",
        "returncode": 0,
        "source": "uv run --no-project --python .venv python benchmarks/bench_laya_cpu.py --model .cache/model/typed-decisions --threads 4 --warmup 1 --repeats 1 --counts 1,3 --output .cache/first-run.json",
        "source_checked": true,
        "source_file": "README.md",
        "verdict": "yes"
      },
      {
        "claim": "The checkpoint downloader verifies the pinned typed-decisions checkpoint",
        "command": "<guest-path> run --no-project --python .venv python scripts/download_model.py",
        "evidence": "Pinned typed-decisions checkpoint verified.\n\rFetching 5 files:   0%|          | 0/5 [00:00<?, ?it/s]\rFetching 5 files:  40%|\u2588\u2588\u2588\u2588      | 2/5 [00:00<00:00, 19.03it/s]\rFetching 5 files: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 5/5 [00:00<00:00, 42.13it/s]\n",
        "expected": "prints that the pinned checkpoint is verified",
        "input": "download and verify the pinned checkpoint",
        "kind": "claim",
        "outcome": "Real input produced the expected result: Pinned typed-decisions checkpoint verified.",
        "returncode": 0,
        "source": "uv run --no-project --python .venv python scripts/download_model.py",
        "source_checked": true,
        "source_file": "README.md",
        "verdict": "yes"
      }
    ],
    "cycle_checks": [
      {
        "claim": "Scheduled or looping main behavior",
        "command": "",
        "evidence": "Entry points inspected: README.md, scripts/ (download_model.py, download_onnx.py, parity.py, check_syntax.py, onnx_runtime.py), benchmarks/ (bench_laya_cpu.py, bench_laya_ort.py). Searched for cron, schedule, loop, --once, --now, webhook and daemon; no product scheduler or recurring cycle exists. The product is a one-shot CLI run per command, and README states no server, background service or model weights ship here.",
        "expected": "identify the product trigger",
        "input": "source inspection",
        "kind": "cycle",
        "outcome": "Entry points inspected: README.md, scripts/ (download_model.py, download_onnx.py, parity.py, check_syntax.py, onnx_runtime.py), benchmarks/ (bench_laya_cpu.py, bench_laya_ort.py). Searched for cron, schedule, loop, --once, --now, webhook and daemon; no product scheduler or recurring cycle exists. The product is a one-shot CLI run per command, and README states no server, background service or model weights ship here.",
        "source": "repository entry points",
        "verdict": "yes"
      }
    ],
    "details": {
      "argv": [
        "<guest-path>",
        "run",
        "--no-project",
        "--python",
        ".venv",
        "python",
        "benchmarks/bench_laya_cpu.py",
        "--model",
        ".cache/model/typed-decisions",
        "--threads",
        "4",
        "--warmup",
        "1",
        "--repeats",
        "1",
        "--counts",
        "1,3",
        "--output",
        ".cache/probe-run.json"
      ],
      "kind": "cli",
      "needs_browser": false,
      "needs_credentials": false,
      "returncode": 0,
      "scope": "product operation",
      "stderr": "",
      "stdout": "timing 1 questions ...\n  p50=965.1 ms p95=965.1 ms 1.04 q/s RSS=2056.2 MiB CPU=106.3%\ntiming 3 questions ...\n  p50=2298.6 ms p95=2298.6 ms 1.30 q/s RSS=2060.1 MiB CPU=123.9%\nwrote .cache/probe-run.json",
      "working": true
    },
    "evidence_strength": "readme_checked",
    "example_checks": [
      {
        "claim": "Local checks need only Python's standard library and run the offline unit tests",
        "command": "python3 -m unittest discover -s tests -q",
        "deferred": false,
        "evidence": "----------------------------------------------------------------------\nRan 19 tests in 0.101s\n\nOK",
        "expected": "all offline tests pass with exit 0",
        "input": "unittest discovery over tests/",
        "kind": "example",
        "outcome": "command completed successfully",
        "returncode": 0,
        "source": "README.md Local checks",
        "verdict": "yes"
      },
      {
        "claim": "Local syntax check of the repository Python files",
        "command": "python3 scripts/check_syntax.py",
        "deferred": false,
        "evidence": "Python syntax checked.",
        "expected": "prints Python syntax checked.",
        "input": "scripts, benchmarks and tests directories",
        "kind": "example",
        "outcome": "command completed successfully",
        "returncode": 0,
        "source": "README.md Local checks",
        "verdict": "yes"
      },
      {
        "claim": "Optional ONNX Runtime FP32 route and parity check against the PyTorch reference",
        "command": "",
        "deferred": true,
        "evidence": "Deferred: needs a second Python environment with onnxruntime and about 1.69 GB of additional ONNX weights, while this VM has 3 GB RAM total (README asks for 8 GB available for setup). Not run.",
        "expected": "documented command completes successfully",
        "input": "",
        "kind": "example",
        "outcome": "Deferred: needs a second Python environment with onnxruntime and about 1.69 GB of additional ONNX weights, while this VM has 3 GB RAM total (README asks for 8 GB available for setup). Not run.",
        "source": "README.md Optional: ONNX Runtime FP32",
        "verdict": "deferred"
      }
    ],
    "status": "PASS"
  },
  "diagnosis": null
}