yaojingang
111 lines
2.5 KiB
JSON
111 lines
2.5 KiB
JSON
{
|
|
"summary": {
|
|
"target_count": 3,
|
|
"baseline_total_errors": 8,
|
|
"current_total_errors": 5,
|
|
"winner_total_errors": 5,
|
|
"winner_vs_baseline_gain": 3,
|
|
"winner_vs_current_gain": 0
|
|
},
|
|
"comparisons": [
|
|
{
|
|
"label": "root",
|
|
"winner_label": "Current",
|
|
"baseline": {
|
|
"tokens": 8,
|
|
"dev_errors": 1,
|
|
"holdout_errors": 0,
|
|
"blind_errors": 0,
|
|
"judge_blind_errors": 0,
|
|
"adversarial_errors": 0
|
|
},
|
|
"current": {
|
|
"tokens": 65,
|
|
"dev_errors": 0,
|
|
"holdout_errors": 0,
|
|
"blind_errors": 0,
|
|
"judge_blind_errors": 0,
|
|
"adversarial_errors": 0
|
|
},
|
|
"winner": {
|
|
"tokens": 65,
|
|
"dev_errors": 0,
|
|
"holdout_errors": 0,
|
|
"blind_errors": 0,
|
|
"judge_blind_errors": 0,
|
|
"adversarial_errors": 0
|
|
},
|
|
"delta": {
|
|
"current_vs_baseline": 1,
|
|
"winner_vs_baseline": 1,
|
|
"winner_vs_current": 0
|
|
}
|
|
},
|
|
{
|
|
"label": "team-frontend-review",
|
|
"winner_label": "Current",
|
|
"baseline": {
|
|
"tokens": 52,
|
|
"dev_errors": 3,
|
|
"holdout_errors": 0,
|
|
"blind_errors": 0,
|
|
"judge_blind_errors": 0,
|
|
"adversarial_errors": 0
|
|
},
|
|
"current": {
|
|
"tokens": 50,
|
|
"dev_errors": 3,
|
|
"holdout_errors": 0,
|
|
"blind_errors": 0,
|
|
"judge_blind_errors": 0,
|
|
"adversarial_errors": 0
|
|
},
|
|
"winner": {
|
|
"tokens": 50,
|
|
"dev_errors": 3,
|
|
"holdout_errors": 0,
|
|
"blind_errors": 0,
|
|
"judge_blind_errors": 0,
|
|
"adversarial_errors": 0
|
|
},
|
|
"delta": {
|
|
"current_vs_baseline": 0,
|
|
"winner_vs_baseline": 0,
|
|
"winner_vs_current": 0
|
|
}
|
|
},
|
|
{
|
|
"label": "governed-incident-command",
|
|
"winner_label": "Current",
|
|
"baseline": {
|
|
"tokens": 93,
|
|
"dev_errors": 1,
|
|
"holdout_errors": 2,
|
|
"blind_errors": 1,
|
|
"judge_blind_errors": 0,
|
|
"adversarial_errors": 0
|
|
},
|
|
"current": {
|
|
"tokens": 37,
|
|
"dev_errors": 1,
|
|
"holdout_errors": 1,
|
|
"blind_errors": 0,
|
|
"judge_blind_errors": 0,
|
|
"adversarial_errors": 0
|
|
},
|
|
"winner": {
|
|
"tokens": 37,
|
|
"dev_errors": 1,
|
|
"holdout_errors": 1,
|
|
"blind_errors": 0,
|
|
"judge_blind_errors": 0,
|
|
"adversarial_errors": 0
|
|
},
|
|
"delta": {
|
|
"current_vs_baseline": 2,
|
|
"winner_vs_baseline": 2,
|
|
"winner_vs_current": 0
|
|
}
|
|
}
|
|
]
|
|
} |