{
  "scope": "handcrafted vectors, scores and qrels; no model training or performance benchmark",
  "candidateDepth": 2,
  "cutoff": 2,
  "evaluatedQueries": 2,
  "excludedNoPositiveQueries": 1,
  "candidateRecall": 0.25,
  "baselineNdcg": 0.289382,
  "challengerNdcg": 0.45866,
  "pairedNdcgDelta": 0.169278,
  "results": [
    {
      "query": "q1-partial-candidate-recall",
      "candidates": [
        "d1",
        "d2"
      ],
      "reranked": [
        "d2",
        "d1"
      ],
      "candidateRecall": 0.5,
      "baseline": {
        "recall": 0.5,
        "ndcg": 0.578764
      },
      "challenger": {
        "recall": 0.5,
        "ndcg": 0.917319
      }
    },
    {
      "query": "q2-missing-gold",
      "candidates": [
        "d3",
        "d2"
      ],
      "reranked": [
        "d3",
        "d2"
      ],
      "candidateRecall": 0,
      "baseline": {
        "recall": 0,
        "ndcg": 0
      },
      "challenger": {
        "recall": 0,
        "ndcg": 0
      }
    },
    {
      "query": "q3-no-positive-qrel",
      "candidates": [
        "d4",
        "d3"
      ],
      "reranked": [
        "d4",
        "d3"
      ],
      "candidateRecall": null,
      "baseline": null,
      "challenger": null
    }
  ]
}