{
  "artifact": "s46c_apc_fixed_bridge_n8",
  "config_path": "configs/s46c_apc_fixed_bridge_n8.yaml",
  "sealed_utc": "2026-09-02T22:51:51.369388+00:00",
  "threshold": {
    "ratio_orientation": "apc_off/apc_on",
    "primary": "paired median knee ratio apc_off/apc_on < 1.0, significant at alpha=0.05, n=8 (MDE at s_y 0.047 is 5.58%: results/s47_aa_null_real_trace.json, bench/stats.mde)",
    "paired_ratio_must_be_significant_at_05": true,
    "paired_cv_pct_max": 8.72,
    "engine_hit_rate_apc_on_must_be_at_most": 0.169,
    "engine_hit_rate_apc_off_must_be": 0.0,
    "quote_only_if_harness_bound_arm_knees": 0,
    "companion_aa": "results/s47b_aa_fixed_bridge_n8.json must be within [0.90, 1.10] and not significant, else nothing here is quoted"
  },
  "threshold_sha256": "5c81877d25c93bbed9c6cef13c2329e12ac58fda702c8736779fa81e54fc2b49",
  "config_sha256": "ece2c2b4f5e59cdadff081c33298eae95eff88958c28ac2761fce993d5f73fdb",
  "config": {
    "artifact": "s46c_apc_fixed_bridge_n8",
    "sprint": "46b",
    "claim": "Whether vLLM's prefix caching still raises the sustainable-QPS knee on the real Mooncake slice once the trace bridge no longer collapses distinct blocks into identical text -- and what hit rate the engine reports on the real stream.",
    "model": "Qwen/Qwen2.5-1.5B-Instruct",
    "provider": "modal",
    "reps": 8,
    "seed": 20260906,
    "cost_cap_usd": 20.0,
    "telemetry_hz": 10,
    "warmup": 8,
    "request_timeout_s": 300,
    "drain_timeout_s": 45,
    "client_shards": 8,
    "server_args": {
      "max_model_len": 16384,
      "max_num_seqs": 256,
      "gpu_memory_utilization": 0.85,
      "num_gpu_blocks_override": 4096
    },
    "arms": [
      {
        "name": "apc_off",
        "server_args": {
          "enable_prefix_caching": false
        }
      },
      {
        "name": "apc_on",
        "server_args": {
          "enable_prefix_caching": true
        }
      }
    ],
    "slo": {
      "name": "nominal",
      "ttft_p95_ms": 2000.0,
      "tpot_p95_ms": 50.0,
      "ttft_p99_ms": 4000.0,
      "min_completion_rate": 0.99
    },
    "trace": {
      "source": "mooncake_timed_600",
      "max_requests": 600,
      "block_tokens": 64,
      "max_output_tokens": 256,
      "duration_s": 60.0,
      "calibrate_tokens": true
    },
    "gpu": "L40S",
    "sweep": {
      "lo_qps": 6.0,
      "hi_qps": 14.0,
      "coarse_points": 5,
      "refinements": 3,
      "reference_offered_qps": 100.0
    },
    "preregistered_threshold": {
      "ratio_orientation": "apc_off/apc_on",
      "primary": "paired median knee ratio apc_off/apc_on < 1.0, significant at alpha=0.05, n=8 (MDE at s_y 0.047 is 5.58%: results/s47_aa_null_real_trace.json, bench/stats.mde)",
      "paired_ratio_must_be_significant_at_05": true,
      "paired_cv_pct_max": 8.72,
      "engine_hit_rate_apc_on_must_be_at_most": 0.169,
      "engine_hit_rate_apc_off_must_be": 0.0,
      "quote_only_if_harness_bound_arm_knees": 0,
      "companion_aa": "results/s47b_aa_fixed_bridge_n8.json must be within [0.90, 1.10] and not significant, else nothing here is quoted"
    }
  },
  "git_rev": "7f7b8c0",
  "seal_convention": "verifycore.canonical_seal_bytes (frozen)",
  "rule": "The experiment runner verifies this hash before spending anything. A changed threshold aborts the run rather than quietly redefining success."
}