Include preflight in benchmark reproducibility

This commit is contained in:
yaojingang
2026-06-16 01:49:51 +08:00
parent dd33d55b62
commit d3fb78f4fe
17 changed files with 112 additions and 79 deletions
@@ -41,6 +41,7 @@ REQUIRED_ARTIFACTS = [
("world_class_evidence_plan", "reports/world_class_evidence_plan.json"),
("world_class_evidence_ledger", "reports/world_class_evidence_ledger.json"),
("world_class_evidence_intake", "reports/world_class_evidence_intake.json"),
("world_class_evidence_preflight", "reports/world_class_evidence_preflight.json"),
("world_class_submission_review", "reports/world_class_submission_review.json"),
("world_class_operator_runbook", "reports/world_class_operator_runbook.json"),
("world_class_operator_runbook_markdown", "reports/world_class_operator_runbook.md"),
@@ -134,6 +135,11 @@ REPRODUCTION_COMMANDS = [
"command": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
"evidence": "reports/world_class_evidence_intake.json",
},
{
"label": "world-class evidence preflight",
"command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"evidence": "reports/world_class_evidence_preflight.json",
},
{
"label": "world-class submission review",
"command": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions",