Step F first pass: 81/92 accepted; budget floor 60 calls; rejected slots moved for regeneration
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014aUaQeLnwbb1zTpN7kHeat
This commit is contained in:
72
tasks_gen/eval/G0126/mutation.json
Normal file
72
tasks_gen/eval/G0126/mutation.json
Normal file
@@ -0,0 +1,72 @@
|
||||
{
|
||||
"task": "G0126",
|
||||
"mutants": [
|
||||
{
|
||||
"object": "{{P}}BAG_DROP",
|
||||
"mutant": "line 77: + -> - (arith)",
|
||||
"status": "killed",
|
||||
"hidden": "10/11",
|
||||
"failed_tests": [
|
||||
"REJECTS_OVERSIZE"
|
||||
]
|
||||
},
|
||||
{
|
||||
"object": "{{P}}BAG_DROP",
|
||||
"mutant": "line 77: + -> - (arith)",
|
||||
"status": "killed",
|
||||
"hidden": "10/11",
|
||||
"failed_tests": [
|
||||
"REJECTS_OVERSIZE"
|
||||
]
|
||||
},
|
||||
{
|
||||
"object": "{{P}}BAG_DROP",
|
||||
"mutant": "line 77: > -> <= (rel)",
|
||||
"status": "killed",
|
||||
"hidden": "3/11",
|
||||
"failed_tests": [
|
||||
"ACCEPTS_40_MINUTES",
|
||||
"ACCEPTS_MAX_SIZE",
|
||||
"ACCEPTS_MAX_WEIGHT",
|
||||
"ACCEPTS_ONE_BAG",
|
||||
"ACCEPTS_VALID_BAG",
|
||||
"REJECTS_39_MINUTES",
|
||||
"REJECTS_OVERSIZE",
|
||||
"REJECTS_THIRD_BAG"
|
||||
]
|
||||
},
|
||||
{
|
||||
"object": "{{P}}BAG_DROP",
|
||||
"mutant": "line 83: >= -> < (rel)",
|
||||
"status": "killed",
|
||||
"hidden": "4/11",
|
||||
"failed_tests": [
|
||||
"ACCEPTS_40_MINUTES",
|
||||
"ACCEPTS_MAX_SIZE",
|
||||
"ACCEPTS_MAX_WEIGHT",
|
||||
"ACCEPTS_ONE_BAG",
|
||||
"ACCEPTS_VALID_BAG",
|
||||
"REJECTS_39_MINUTES",
|
||||
"REJECTS_THIRD_BAG"
|
||||
]
|
||||
},
|
||||
{
|
||||
"object": "{{P}}BAG_DROP",
|
||||
"mutant": "line 89: < -> >= (rel)",
|
||||
"status": "killed",
|
||||
"hidden": "5/11",
|
||||
"failed_tests": [
|
||||
"ACCEPTS_40_MINUTES",
|
||||
"ACCEPTS_MAX_SIZE",
|
||||
"ACCEPTS_MAX_WEIGHT",
|
||||
"ACCEPTS_ONE_BAG",
|
||||
"ACCEPTS_VALID_BAG",
|
||||
"REJECTS_39_MINUTES"
|
||||
]
|
||||
}
|
||||
],
|
||||
"valid": 5,
|
||||
"killed": 5,
|
||||
"kill_rate": 1.0,
|
||||
"ok": true
|
||||
}
|
||||
Reference in New Issue
Block a user