Files
yao-meta-skill/reports/baseline-compare.json
T
YAO 31ce04c655 Split meta skill CLI and review gates
Merge the beta-ready Yao Meta Skill architecture, report, evidence gate, and release-boundary updates.\n\nRelease boundary: beta/public testing is allowed; formal world-class, fully reviewed, or superiority claims remain blocked until the pending evidence gates are accepted.
2026-06-17 18:43:02 +08:00

111 lines
2.5 KiB
JSON

{
"summary": {
"target_count": 3,
"baseline_total_errors": 5,
"current_total_errors": 4,
"winner_total_errors": 4,
"winner_vs_baseline_gain": 1,
"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": 53,
"dev_errors": 0,
"holdout_errors": 0,
"blind_errors": 0,
"judge_blind_errors": 0,
"adversarial_errors": 0
},
"winner": {
"tokens": 53,
"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": 0,
"holdout_errors": 1,
"blind_errors": 0,
"judge_blind_errors": 0,
"adversarial_errors": 0
},
"current": {
"tokens": 37,
"dev_errors": 0,
"holdout_errors": 1,
"blind_errors": 0,
"judge_blind_errors": 0,
"adversarial_errors": 0
},
"winner": {
"tokens": 37,
"dev_errors": 0,
"holdout_errors": 1,
"blind_errors": 0,
"judge_blind_errors": 0,
"adversarial_errors": 0
},
"delta": {
"current_vs_baseline": 0,
"winner_vs_baseline": 0,
"winner_vs_current": 0
}
}
]
}