- docs/eval-inceleme.md checklist; harness/review.py - 19 accept, 1 fix pending (G0019), 4 flagged (I/E tasks solvable without legacy code) - generator: categories I and E fix/refactor the seed object in place Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014aUaQeLnwbb1zTpN7kHeat
55 lines
1.0 KiB
JSON
55 lines
1.0 KiB
JSON
{
|
|
"id": "G0022",
|
|
"pool": "eval",
|
|
"object_type": "CLAS",
|
|
"category": "D",
|
|
"attempts": [
|
|
{
|
|
"stage": "validate",
|
|
"oracle": 0,
|
|
"null": 0
|
|
},
|
|
{
|
|
"stage": "validate",
|
|
"oracle": 0,
|
|
"null": 0
|
|
},
|
|
{
|
|
"stage": "validate",
|
|
"oracle": 0,
|
|
"null": 0
|
|
},
|
|
{
|
|
"stage": "validate",
|
|
"oracle": 0,
|
|
"null": 0
|
|
},
|
|
{
|
|
"stage": "revalidate",
|
|
"by": "harness fix 2026-10-03",
|
|
"change": "G6 ignores unknown standard superclass (abaplint); reference in dependency order. Bundle not changed.",
|
|
"oracle": 95.0,
|
|
"null": 0
|
|
},
|
|
{
|
|
"stage": "revalidate",
|
|
"by": "harness fix 2026-10-03",
|
|
"change": "budget floor: max_activations 12 -> 14 (reference alone needs 13).",
|
|
"oracle": 100.0,
|
|
"null": 0
|
|
},
|
|
{
|
|
"stage": "manual_fix",
|
|
"by": "Claude review 2026-10-03",
|
|
"change": "Review: added hidden test other_currencies_pass (USD, GBP, CHF).",
|
|
"oracle": 100.0,
|
|
"null": 0,
|
|
"mutation": {
|
|
"valid": 5,
|
|
"killed": 5,
|
|
"ok": true
|
|
}
|
|
}
|
|
],
|
|
"accepted": true
|
|
} |