{
  "backend": "native Rust + ONNX Runtime CPU, one inference thread",
  "bundle_bytes": 300076892,
  "cold_load_seconds": 0.17001258302479982,
  "cold_load_definition": "process launch through first empty-input response; includes initialization and minimal inference",
  "warm_requests": [
    {
      "id": "train:11173:fe74ed22f6d1401ca2ffd5eff69b393f",
      "bytes": 115,
      "latency_seconds": 0.006004999973811209,
      "findings": 2
    },
    {
      "id": "train:57662:383de2ea1ead4b888647277ce284eda4",
      "bytes": 752,
      "latency_seconds": 0.020578791038133204,
      "findings": 1
    },
    {
      "id": "train:11465:d5a56f0fd54642199415f4f1fb64fcb9",
      "bytes": 2010,
      "latency_seconds": 0.08128199994098395,
      "findings": 2
    },
    {
      "id": "train:83899:780281fffc5548e1a9cc3cb5750ca236",
      "bytes": 4502,
      "latency_seconds": 0.17272016603965312,
      "findings": 11
    }
  ],
  "peak_rss_bytes": 496418816,
  "memory_definition": "maximum RSS sampled after responses, not allocator high-water mark",
  "warm_observed_requests_per_second": 14.255880953107562,
  "sampling": "one request each at observed min/median/p90/max validation byte lengths; descriptive observations, no latency guarantee"
}