GRAPHRAG_EVAL_2026-08-10.json

{
  "gold_set": "gold_v1.jsonl",
  "backend": "endpoint",
  "live_artifact": true,
  "summary": {
    "n_questions": 9,
    "n_scored": 7,
    "n_negative": 2,
    "precision@5": 0.0,
    "recall@5": 0.2857,
    "precision@10": 0.0143,
    "recall@10": 0.4286,
    "mrr": 0.0238,
    "graph_coverage": 0.7143,
    "facet_recall": 0.2143,
    "negative_pass_rate": 1.0,
    "latency_p50_ms": 4525.41,
    "latency_p95_ms": 4672.03,
    "faithfulness": 0.249,
    "faithfulness_scored": 7,
    "faithfulness_failed": 0
  },
  "per_question": [
    {
      "id": "gq-001",
      "archetype": "journey_traversal",
      "latency_ms": 4525.41,
      "n_retrieved": 10,
      "precision@5": 0.0,
      "recall@5": 0.0,
      "precision@10": 0.1,
      "recall@10": 1.0,
      "mrr": 0.1667,
      "graph_coverage": 0.0,
      "facet_recall": 1.0,
      "faithfulness": 0.4
    },
    {
      "id": "gq-002",
      "archetype": "journey_traversal",
      "latency_ms": 4408.54,
      "n_retrieved": 6,
      "precision@5": 0.0,
      "recall@5": 0.0,
      "precision@10": 0.0,
      "recall@10": 0.0,
      "mrr": 0.0,
      "graph_coverage": 0.0,
      "facet_recall": 0.5,
      "faithfulness": 0.35294117647058826
    },
    {
      "id": "gq-101",
      "archetype": "causal_path",
      "latency_ms": 4410.35,
      "n_retrieved": 5,
      "precision@5": 0.0,
      "recall@5": 0.0,
      "precision@10": 0.0,
      "recall@10": 0.0,
      "mrr": 0.0,
      "graph_coverage": 1.0,
      "facet_recall": 0.0,
      "faithfulness": 0.18181818181818182
    },
    {
      "id": "gq-102",
      "archetype": "causal_path",
      "latency_ms": 4538.12,
      "n_retrieved": 5,
      "precision@5": 0.0,
      "recall@5": 0.0,
      "precision@10": 0.0,
      "recall@10": 0.0,
      "mrr": 0.0,
      "graph_coverage": 1.0,
      "facet_recall": 0.0,
      "faithfulness": 0.0
    },
    {
      "id": "gq-201",
      "archetype": "intent_explanation",
      "latency_ms": 4572.03,
      "n_retrieved": 5,
      "precision@5": 0.0,
      "recall@5": 0.0,
      "precision@10": 0.0,
      "recall@10": 0.0,
      "mrr": 0.0,
      "graph_coverage": 1.0,
      "facet_recall": 0.0,
      "faithfulness": 0.0
    },
    {
      "id": "gq-301",
      "archetype": "aggregation",
      "latency_ms": 4424.13,
      "n_retrieved": 5,
      "precision@5": 0.0,
      "recall@5": 1.0,
      "precision@10": 0.0,
      "recall@10": 1.0,
      "mrr": 0.0,
      "graph_coverage": 1.0,
      "facet_recall": 0.0,
      "faithfulness": 0.4444444444444444
    },
    {
      "id": "gq-302",
      "archetype": "aggregation",
      "latency_ms": 4550.67,
      "n_retrieved": 5,
      "precision@5": 0.0,
      "recall@5": 1.0,
      "precision@10": 0.0,
      "recall@10": 1.0,
      "mrr": 0.0,
      "graph_coverage": 1.0,
      "facet_recall": 0.0,
      "faithfulness": 0.36363636363636365
    },
    {
      "id": "gq-901",
      "archetype": "negative",
      "latency_ms": 4397.71,
      "n_retrieved": 5,
      "negative_pass": true
    },
    {
      "id": "gq-902",
      "archetype": "negative",
      "latency_ms": 4672.03,
      "n_retrieved": 5,
      "negative_pass": true
    }
  ],
  "generated_at": "2026-08-10T12:37:47.235985+00:00"
}
← All docsView source on GitHub →