{
  "bench_version": 1,
  "track": "graph_context_budget",
  "model": "mlp_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.003
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001
        },
        "mean": 0.09124999865889549
      },
      {
        "cfg": {
          "lr": 0.003
        },
        "mean": 0.03874999890103936
      },
      {
        "cfg": {
          "lr": 0.01
        },
        "mean": 0.04374999878928065
      }
    ],
    "full": {
      "mean": 0.0418749984819442,
      "std": 0.006091745648538752,
      "per_seed": [
        0.03500000014901161,
        0.044999998062849045,
        0.044999998062849045,
        0.029999999329447746,
        0.044999998062849045,
        0.03999999910593033,
        0.044999998062849045,
        0.04999999701976776
      ],
      "n": 8
    }
  },
  "idea": {
    "per_seed": [
      0.03500000014901161,
      0.044999998062849045,
      0.044999998062849045,
      0.029999999329447746,
      0.044999998062849045,
      0.03999999910593033,
      0.044999998062849045,
      0.04999999701976776
    ],
    "mean": 0.0418749984819442,
    "lr": 0.003,
    "mode": "anchored",
    "signature_observed_input_abs_mean": 0.7980227172374725,
    "trained_model_accuracy": 0.9581250015180558
  },
  "comparison": {
    "delta_mean": 0.0,
    "idea_wins": 0,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.0,
      0.0,
      0.0,
      0.0,
      0.0,
      0.0,
      0.0,
      0.0
    ],
    "p_value": 1.0,
    "mde": 0.0,
    "mde_rel_pct": 0.0,
    "verdict": "no measurable effect",
    "system_worked": false
  },
  "custom_track": {
    "name": "graph_context_budget",
    "file": "bench_graph_context.py",
    "domain": "retrieval"
  },
  "protocol_notes": "8 paired seeds; baseline and idea share task, MLP, epochs, batch, and lr union; lower err is better.",
  "mechanism_signature": {
    "predicted_D_over_B": 3.0,
    "observed_candidate_units": 24,
    "observed_budget_units": 8,
    "predicted_anchored_gold_recall": 1.0,
    "observed_anchored_gold_recall": 1.0,
    "observed_global_gold_recall": 0.3333333333333333,
    "trained_anchored_accuracy": 0.9581250015180558,
    "trained_baseline_accuracy": 0.0418749984819442,
    "repeated_context_identical": true,
    "confirmed": true
  }
}