{
  "baseline_run": "demo-baseline",
  "candidate_run": "demo-candidate",
  "comparison": {
    "baseline": 1.0,
    "candidate": 0.88,
    "ci_high": -0.05598784431526255,
    "ci_low": -0.18401215568473744,
    "corrected_alpha": 0.05,
    "delta": -0.12,
    "improvements": [],
    "method": "paired normal approximation",
    "metric": "accuracy",
    "reason": "paired confidence interval excludes the allowed tolerance",
    "regressions": [
      "sample-000",
      "sample-001",
      "sample-002",
      "sample-003",
      "sample-004",
      "sample-005",
      "sample-006",
      "sample-007",
      "sample-008",
      "sample-009",
      "sample-010",
      "sample-011"
    ],
    "verdict": "BLOCKED"
  },
  "dataset_hash": "sha256:70d3abece3399e80f930e2e07c6448f5e7c0d3f40e10ce2126c87fd3092dee7a",
  "samples": [
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 0.0,
      "context": {
        "request": "select tool for case 000"
      },
      "reference": "search",
      "sample_id": "sample-000"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 0.0,
      "context": {
        "request": "select tool for case 001"
      },
      "reference": "lookup",
      "sample_id": "sample-001"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 0.0,
      "context": {
        "request": "select tool for case 002"
      },
      "reference": "search",
      "sample_id": "sample-002"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 0.0,
      "context": {
        "request": "select tool for case 003"
      },
      "reference": "lookup",
      "sample_id": "sample-003"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 0.0,
      "context": {
        "request": "select tool for case 004"
      },
      "reference": "search",
      "sample_id": "sample-004"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 0.0,
      "context": {
        "request": "select tool for case 005"
      },
      "reference": "lookup",
      "sample_id": "sample-005"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 0.0,
      "context": {
        "request": "select tool for case 006"
      },
      "reference": "search",
      "sample_id": "sample-006"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 0.0,
      "context": {
        "request": "select tool for case 007"
      },
      "reference": "lookup",
      "sample_id": "sample-007"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 0.0,
      "context": {
        "request": "select tool for case 008"
      },
      "reference": "search",
      "sample_id": "sample-008"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 0.0,
      "context": {
        "request": "select tool for case 009"
      },
      "reference": "lookup",
      "sample_id": "sample-009"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 0.0,
      "context": {
        "request": "select tool for case 010"
      },
      "reference": "search",
      "sample_id": "sample-010"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 0.0,
      "context": {
        "request": "select tool for case 011"
      },
      "reference": "lookup",
      "sample_id": "sample-011"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 012"
      },
      "reference": "search",
      "sample_id": "sample-012"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 013"
      },
      "reference": "lookup",
      "sample_id": "sample-013"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 014"
      },
      "reference": "search",
      "sample_id": "sample-014"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 015"
      },
      "reference": "lookup",
      "sample_id": "sample-015"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 016"
      },
      "reference": "search",
      "sample_id": "sample-016"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 017"
      },
      "reference": "lookup",
      "sample_id": "sample-017"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 018"
      },
      "reference": "search",
      "sample_id": "sample-018"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 019"
      },
      "reference": "lookup",
      "sample_id": "sample-019"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 020"
      },
      "reference": "search",
      "sample_id": "sample-020"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 021"
      },
      "reference": "lookup",
      "sample_id": "sample-021"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 022"
      },
      "reference": "search",
      "sample_id": "sample-022"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 023"
      },
      "reference": "lookup",
      "sample_id": "sample-023"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 024"
      },
      "reference": "search",
      "sample_id": "sample-024"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 025"
      },
      "reference": "lookup",
      "sample_id": "sample-025"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 026"
      },
      "reference": "search",
      "sample_id": "sample-026"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 027"
      },
      "reference": "lookup",
      "sample_id": "sample-027"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 028"
      },
      "reference": "search",
      "sample_id": "sample-028"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 029"
      },
      "reference": "lookup",
      "sample_id": "sample-029"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 030"
      },
      "reference": "search",
      "sample_id": "sample-030"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 031"
      },
      "reference": "lookup",
      "sample_id": "sample-031"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 032"
      },
      "reference": "search",
      "sample_id": "sample-032"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 033"
      },
      "reference": "lookup",
      "sample_id": "sample-033"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 034"
      },
      "reference": "search",
      "sample_id": "sample-034"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 035"
      },
      "reference": "lookup",
      "sample_id": "sample-035"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 036"
      },
      "reference": "search",
      "sample_id": "sample-036"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 037"
      },
      "reference": "lookup",
      "sample_id": "sample-037"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 038"
      },
      "reference": "search",
      "sample_id": "sample-038"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 039"
      },
      "reference": "lookup",
      "sample_id": "sample-039"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 040"
      },
      "reference": "search",
      "sample_id": "sample-040"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 041"
      },
      "reference": "lookup",
      "sample_id": "sample-041"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 042"
      },
      "reference": "search",
      "sample_id": "sample-042"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 043"
      },
      "reference": "lookup",
      "sample_id": "sample-043"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 044"
      },
      "reference": "search",
      "sample_id": "sample-044"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 045"
      },
      "reference": "lookup",
      "sample_id": "sample-045"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 046"
      },
      "reference": "search",
      "sample_id": "sample-046"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 047"
      },
      "reference": "lookup",
      "sample_id": "sample-047"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 048"
      },
      "reference": "search",
      "sample_id": "sample-048"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 049"
      },
      "reference": "lookup",
      "sample_id": "sample-049"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 050"
      },
      "reference": "search",
      "sample_id": "sample-050"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 051"
      },
      "reference": "lookup",
      "sample_id": "sample-051"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 052"
      },
      "reference": "search",
      "sample_id": "sample-052"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 053"
      },
      "reference": "lookup",
      "sample_id": "sample-053"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 054"
      },
      "reference": "search",
      "sample_id": "sample-054"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 055"
      },
      "reference": "lookup",
      "sample_id": "sample-055"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 056"
      },
      "reference": "search",
      "sample_id": "sample-056"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 057"
      },
      "reference": "lookup",
      "sample_id": "sample-057"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 058"
      },
      "reference": "search",
      "sample_id": "sample-058"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 059"
      },
      "reference": "lookup",
      "sample_id": "sample-059"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 060"
      },
      "reference": "search",
      "sample_id": "sample-060"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 061"
      },
      "reference": "lookup",
      "sample_id": "sample-061"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 062"
      },
      "reference": "search",
      "sample_id": "sample-062"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 063"
      },
      "reference": "lookup",
      "sample_id": "sample-063"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 064"
      },
      "reference": "search",
      "sample_id": "sample-064"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 065"
      },
      "reference": "lookup",
      "sample_id": "sample-065"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 066"
      },
      "reference": "search",
      "sample_id": "sample-066"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 067"
      },
      "reference": "lookup",
      "sample_id": "sample-067"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 068"
      },
      "reference": "search",
      "sample_id": "sample-068"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 069"
      },
      "reference": "lookup",
      "sample_id": "sample-069"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 070"
      },
      "reference": "search",
      "sample_id": "sample-070"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 071"
      },
      "reference": "lookup",
      "sample_id": "sample-071"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 072"
      },
      "reference": "search",
      "sample_id": "sample-072"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 073"
      },
      "reference": "lookup",
      "sample_id": "sample-073"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 074"
      },
      "reference": "search",
      "sample_id": "sample-074"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 075"
      },
      "reference": "lookup",
      "sample_id": "sample-075"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 076"
      },
      "reference": "search",
      "sample_id": "sample-076"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 077"
      },
      "reference": "lookup",
      "sample_id": "sample-077"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 078"
      },
      "reference": "search",
      "sample_id": "sample-078"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 079"
      },
      "reference": "lookup",
      "sample_id": "sample-079"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 080"
      },
      "reference": "search",
      "sample_id": "sample-080"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 081"
      },
      "reference": "lookup",
      "sample_id": "sample-081"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 082"
      },
      "reference": "search",
      "sample_id": "sample-082"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 083"
      },
      "reference": "lookup",
      "sample_id": "sample-083"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 084"
      },
      "reference": "search",
      "sample_id": "sample-084"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 085"
      },
      "reference": "lookup",
      "sample_id": "sample-085"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 086"
      },
      "reference": "search",
      "sample_id": "sample-086"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 087"
      },
      "reference": "lookup",
      "sample_id": "sample-087"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 088"
      },
      "reference": "search",
      "sample_id": "sample-088"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 089"
      },
      "reference": "lookup",
      "sample_id": "sample-089"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 090"
      },
      "reference": "search",
      "sample_id": "sample-090"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 091"
      },
      "reference": "lookup",
      "sample_id": "sample-091"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 092"
      },
      "reference": "search",
      "sample_id": "sample-092"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 093"
      },
      "reference": "lookup",
      "sample_id": "sample-093"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 094"
      },
      "reference": "search",
      "sample_id": "sample-094"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 095"
      },
      "reference": "lookup",
      "sample_id": "sample-095"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 096"
      },
      "reference": "search",
      "sample_id": "sample-096"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 097"
      },
      "reference": "lookup",
      "sample_id": "sample-097"
    },
    {
      "baseline_prediction": "search",
      "baseline_score": 1.0,
      "candidate_prediction": "search",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 098"
      },
      "reference": "search",
      "sample_id": "sample-098"
    },
    {
      "baseline_prediction": "lookup",
      "baseline_score": 1.0,
      "candidate_prediction": "lookup",
      "candidate_score": 1.0,
      "context": {
        "request": "select tool for case 099"
      },
      "reference": "lookup",
      "sample_id": "sample-099"
    }
  ],
  "scope": "Bundled deterministic fixture. No real-provider, public-checkpoint, latency, cost, or nondeterminism claim.",
  "scorer_hash": "sha256:f11df01ba73ed424fa4f58e3e87a10e54e17945625589870e103599da4e77358"
}
