Hard batch G0022-G0026: 5/5 accepted; budget floor, CDS checks, mutation check

- generator: budget floor (2x oracle activations, 3x calls), static checks for CDS
  $parameters and UNION annotation
- harness/mutation.py: deterministic mutants of the reference; hidden tests must fail
- G0022 revalidated with harness fixes: oracle 100, null 0
- results in docs/faz1-tasarim.md 11f

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Kral
2026-10-03 05:16:30 +02:00
parent 3570d7ef9b
commit 32f03fcad4
53 changed files with 2931 additions and 14 deletions

View File

@@ -0,0 +1,43 @@
{
"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
}
],
"accepted": true
}