herb-viewer / computation_comparison_report.json
timchen0618's picture
Use type-aware HERB scores for every run
9548217 verified
Raw
History Blame Contribute Delete
4.06 kB
{
"scope": 815,
"brackets": {
"computation_comparison": {
"scope": 130,
"percent": 15.95
},
"other": {
"scope": 685,
"percent": 84.05
}
},
"runs": [
{
"slot": "c1",
"label": "c1 Closed-book",
"score_mode": "mean_judge_score",
"brackets": {
"computation_comparison": {
"scope": 130,
"answered": 130,
"correct": 0,
"score_pct": 0.0,
"perfect_pct": 0.0,
"coverage_pct": 100.0
},
"other": {
"scope": 685,
"answered": 685,
"correct": 0,
"score_pct": 5.05,
"perfect_pct": 0.0,
"coverage_pct": 100.0
}
}
},
{
"slot": "c2",
"label": "c2 With-docs",
"score_mode": "mean_judge_score",
"brackets": {
"computation_comparison": {
"scope": 130,
"answered": 130,
"correct": 61,
"score_pct": 50.1,
"perfect_pct": 46.92,
"coverage_pct": 100.0
},
"other": {
"scope": 685,
"answered": 685,
"correct": 324,
"score_pct": 71.35,
"perfect_pct": 47.3,
"coverage_pct": 100.0
}
}
},
{
"slot": "c6",
"label": "c6 Agentic-DCI",
"score_mode": "mean_judge_score",
"brackets": {
"computation_comparison": {
"scope": 130,
"answered": 126,
"correct": 90,
"score_pct": 79.5,
"perfect_pct": 69.23,
"coverage_pct": 96.92
},
"other": {
"scope": 685,
"answered": 666,
"correct": 296,
"score_pct": 74.91,
"perfect_pct": 43.21,
"coverage_pct": 97.23
}
}
},
{
"slot": "naive",
"label": "Naive-search",
"score_mode": "mean_judge_score",
"brackets": {
"computation_comparison": {
"scope": 130,
"answered": 26,
"correct": 21,
"score_pct": 18.21,
"perfect_pct": 16.15,
"coverage_pct": 20.0
},
"other": {
"scope": 685,
"answered": 521,
"correct": 157,
"score_pct": 51.22,
"perfect_pct": 22.92,
"coverage_pct": 76.06
}
}
},
{
"slot": "e2e_raw",
"label": "E2E raw",
"score_mode": "mean_judge_score",
"brackets": {
"computation_comparison": {
"scope": 130,
"answered": 125,
"correct": 75,
"score_pct": 71.64,
"perfect_pct": 57.69,
"coverage_pct": 96.15
},
"other": {
"scope": 685,
"answered": 673,
"correct": 209,
"score_pct": 67.16,
"perfect_pct": 30.51,
"coverage_pct": 98.25
}
}
},
{
"slot": "e2e_combined",
"label": "E2E combined",
"score_mode": "mean_judge_score",
"brackets": {
"computation_comparison": {
"scope": 130,
"answered": 130,
"correct": 80,
"score_pct": 72.83,
"perfect_pct": 61.54,
"coverage_pct": 100.0
},
"other": {
"scope": 685,
"answered": 683,
"correct": 256,
"score_pct": 74.12,
"perfect_pct": 37.37,
"coverage_pct": 99.71
}
}
},
{
"slot": "e2e_rawtext",
"label": "E2E v3 + rawtext",
"score_mode": "mean_judge_score",
"brackets": {
"computation_comparison": {
"scope": 130,
"answered": 129,
"correct": 88,
"score_pct": 78.05,
"perfect_pct": 67.69,
"coverage_pct": 99.23
},
"other": {
"scope": 685,
"answered": 683,
"correct": 290,
"score_pct": 77.55,
"perfect_pct": 42.34,
"coverage_pct": 99.71
}
}
}
]
}