codedebugger / outputs /baselines_20260425_100854.json
psdhanushkumar's picture
Upload folder using huggingface_hub
f361447 verified
Raw
History Blame Contribute Delete
22.5 kB
{
"timestamp": "2026-04-25T10:07:45.034726",
"baselines": {
"no_change": {
"baseline": "no_change",
"total_problems": 30,
"solved": 1,
"solve_rate": 0.0333,
"avg_reward": 0.5503,
"avg_steps": 1.0,
"avg_pass_rate": 0.3056,
"results": [
{
"problem_id": "bug_001",
"title": "Off-by-one in range",
"steps_taken": 1,
"best_pass_rate": 0.0,
"cumulative_reward": 0.45,
"solved": false
},
{
"problem_id": "bug_002",
"title": "Wrong default mutable argument",
"steps_taken": 1,
"best_pass_rate": 0.6666666666666666,
"cumulative_reward": 0.6833,
"solved": false
},
{
"problem_id": "bug_003",
"title": "Integer division instead of float",
"steps_taken": 1,
"best_pass_rate": 0.6666666666666666,
"cumulative_reward": 0.6833,
"solved": false
},
{
"problem_id": "bug_004",
"title": "Missing return statement",
"steps_taken": 1,
"best_pass_rate": 0.0,
"cumulative_reward": 0.45,
"solved": false
},
{
"problem_id": "bug_005",
"title": "String concatenation type error",
"steps_taken": 1,
"best_pass_rate": 0.0,
"cumulative_reward": 0.45,
"solved": false
},
{
"problem_id": "bug_006",
"title": "Wrong comparison operator",
"steps_taken": 1,
"best_pass_rate": 0.0,
"cumulative_reward": 0.2,
"solved": false
},
{
"problem_id": "bug_007",
"title": "Index out of range in list access",
"steps_taken": 1,
"best_pass_rate": 0.0,
"cumulative_reward": 0.45,
"solved": false
},
{
"problem_id": "bug_008",
"title": "Infinite recursion \u2014 missing base case",
"steps_taken": 1,
"best_pass_rate": 0.0,
"cumulative_reward": 0.45,
"solved": false
},
{
"problem_id": "bug_009",
"title": "Wrong variable in return",
"steps_taken": 1,
"best_pass_rate": 0.0,
"cumulative_reward": 0.45,
"solved": false
},
{
"problem_id": "bug_010",
"title": "Dictionary KeyError",
"steps_taken": 1,
"best_pass_rate": 0.3333333333333333,
"cumulative_reward": 0.5667,
"solved": false
},
{
"problem_id": "bug_011",
"title": "Reversed sort order",
"steps_taken": 1,
"best_pass_rate": 0.6666666666666666,
"cumulative_reward": 0.6833,
"solved": false
},
{
"problem_id": "bug_012",
"title": "Mutating input list unintentionally",
"steps_taken": 1,
"best_pass_rate": 0.6666666666666666,
"cumulative_reward": 0.6833,
"solved": false
},
{
"problem_id": "bug_013",
"title": "Forgotten self in method",
"steps_taken": 1,
"best_pass_rate": 0.3333333333333333,
"cumulative_reward": 0.5667,
"solved": false
},
{
"problem_id": "bug_014",
"title": "Wrong boolean logic",
"steps_taken": 1,
"best_pass_rate": 0.3333333333333333,
"cumulative_reward": 0.5667,
"solved": false
},
{
"problem_id": "bug_015",
"title": "Scope issue with global variable",
"steps_taken": 1,
"best_pass_rate": 0.0,
"cumulative_reward": 0.45,
"solved": false
},
{
"problem_id": "bug_016",
"title": "Shallow copy issue",
"steps_taken": 1,
"best_pass_rate": 0.5,
"cumulative_reward": 0.625,
"solved": false
},
{
"problem_id": "bug_017",
"title": "Wrong string method",
"steps_taken": 1,
"best_pass_rate": 0.6666666666666666,
"cumulative_reward": 0.6833,
"solved": false
},
{
"problem_id": "bug_018",
"title": "Wrong exception handling",
"steps_taken": 1,
"best_pass_rate": 0.6666666666666666,
"cumulative_reward": 0.6833,
"solved": false
},
{
"problem_id": "bug_019",
"title": "Fibonacci off-by-one",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 1.0,
"solved": true
},
{
"problem_id": "bug_020",
"title": "List comprehension filter wrong",
"steps_taken": 1,
"best_pass_rate": 0.0,
"cumulative_reward": 0.45,
"solved": false
},
{
"problem_id": "bug_021",
"title": "Binary search wrong midpoint update",
"steps_taken": 1,
"best_pass_rate": 0.0,
"cumulative_reward": 0.3,
"solved": false
},
{
"problem_id": "bug_022",
"title": "Reversed dictionary comprehension",
"steps_taken": 1,
"best_pass_rate": 0.3333333333333333,
"cumulative_reward": 0.5667,
"solved": false
},
{
"problem_id": "bug_023",
"title": "String reverse off by one",
"steps_taken": 1,
"best_pass_rate": 0.3333333333333333,
"cumulative_reward": 0.5667,
"solved": false
},
{
"problem_id": "bug_024",
"title": "Wrong accumulator init for max",
"steps_taken": 1,
"best_pass_rate": 0.6666666666666666,
"cumulative_reward": 0.6833,
"solved": false
},
{
"problem_id": "bug_025",
"title": "Nested loop wrong variable",
"steps_taken": 1,
"best_pass_rate": 0.0,
"cumulative_reward": 0.45,
"solved": false
},
{
"problem_id": "bug_026",
"title": "Palindrome check wrong slice",
"steps_taken": 1,
"best_pass_rate": 0.0,
"cumulative_reward": 0.45,
"solved": false
},
{
"problem_id": "bug_027",
"title": "Power function wrong operator",
"steps_taken": 1,
"best_pass_rate": 0.0,
"cumulative_reward": 0.45,
"solved": false
},
{
"problem_id": "bug_028",
"title": "GCD wrong recursion",
"steps_taken": 1,
"best_pass_rate": 0.0,
"cumulative_reward": 0.45,
"solved": false
},
{
"problem_id": "bug_029",
"title": "Zip truncation issue",
"steps_taken": 1,
"best_pass_rate": 0.6666666666666666,
"cumulative_reward": 0.6833,
"solved": false
},
{
"problem_id": "bug_030",
"title": "Matrix transpose wrong indices",
"steps_taken": 1,
"best_pass_rate": 0.6666666666666666,
"cumulative_reward": 0.6833,
"solved": false
}
]
},
"oracle": {
"baseline": "oracle",
"total_problems": 30,
"solved": 30,
"solve_rate": 1.0,
"avg_reward": 0.9904,
"avg_steps": 1.0,
"avg_pass_rate": 1.0,
"results": [
{
"problem_id": "bug_001",
"title": "Off-by-one in range",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9978,
"solved": true
},
{
"problem_id": "bug_002",
"title": "Wrong default mutable argument",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9751,
"solved": true
},
{
"problem_id": "bug_003",
"title": "Integer division instead of float",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.999,
"solved": true
},
{
"problem_id": "bug_004",
"title": "Missing return statement",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9786,
"solved": true
},
{
"problem_id": "bug_005",
"title": "String concatenation type error",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9971,
"solved": true
},
{
"problem_id": "bug_006",
"title": "Wrong comparison operator",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9986,
"solved": true
},
{
"problem_id": "bug_007",
"title": "Index out of range in list access",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9959,
"solved": true
},
{
"problem_id": "bug_008",
"title": "Infinite recursion \u2014 missing base case",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9754,
"solved": true
},
{
"problem_id": "bug_009",
"title": "Wrong variable in return",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9985,
"solved": true
},
{
"problem_id": "bug_010",
"title": "Dictionary KeyError",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9877,
"solved": true
},
{
"problem_id": "bug_011",
"title": "Reversed sort order",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9873,
"solved": true
},
{
"problem_id": "bug_012",
"title": "Mutating input list unintentionally",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9611,
"solved": true
},
{
"problem_id": "bug_013",
"title": "Forgotten self in method",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9984,
"solved": true
},
{
"problem_id": "bug_014",
"title": "Wrong boolean logic",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9954,
"solved": true
},
{
"problem_id": "bug_015",
"title": "Scope issue with global variable",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9831,
"solved": true
},
{
"problem_id": "bug_016",
"title": "Shallow copy issue",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9977,
"solved": true
},
{
"problem_id": "bug_017",
"title": "Wrong string method",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9966,
"solved": true
},
{
"problem_id": "bug_018",
"title": "Wrong exception handling",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9926,
"solved": true
},
{
"problem_id": "bug_019",
"title": "Fibonacci off-by-one",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9981,
"solved": true
},
{
"problem_id": "bug_020",
"title": "List comprehension filter wrong",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9984,
"solved": true
},
{
"problem_id": "bug_021",
"title": "Binary search wrong midpoint update",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9985,
"solved": true
},
{
"problem_id": "bug_022",
"title": "Reversed dictionary comprehension",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9966,
"solved": true
},
{
"problem_id": "bug_023",
"title": "String reverse off by one",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9921,
"solved": true
},
{
"problem_id": "bug_024",
"title": "Wrong accumulator init for max",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9964,
"solved": true
},
{
"problem_id": "bug_025",
"title": "Nested loop wrong variable",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9974,
"solved": true
},
{
"problem_id": "bug_026",
"title": "Palindrome check wrong slice",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.983,
"solved": true
},
{
"problem_id": "bug_027",
"title": "Power function wrong operator",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9966,
"solved": true
},
{
"problem_id": "bug_028",
"title": "GCD wrong recursion",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9986,
"solved": true
},
{
"problem_id": "bug_029",
"title": "Zip truncation issue",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9551,
"solved": true
},
{
"problem_id": "bug_030",
"title": "Matrix transpose wrong indices",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9858,
"solved": true
}
]
},
"llm": {
"baseline": "llm_llama-3.3-70b-versatile",
"total_problems": 30,
"solved": 29,
"solve_rate": 0.9667,
"avg_reward": 1.0346,
"avg_steps": 1.17,
"avg_pass_rate": 0.9833,
"results": [
{
"problem_id": "bug_001",
"title": "Off-by-one in range",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9963,
"solved": true
},
{
"problem_id": "bug_002",
"title": "Wrong default mutable argument",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9751,
"solved": true
},
{
"problem_id": "bug_003",
"title": "Integer division instead of float",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9548,
"solved": true
},
{
"problem_id": "bug_004",
"title": "Missing return statement",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9786,
"solved": true
},
{
"problem_id": "bug_005",
"title": "String concatenation type error",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9971,
"solved": true
},
{
"problem_id": "bug_006",
"title": "Wrong comparison operator",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9986,
"solved": true
},
{
"problem_id": "bug_007",
"title": "Index out of range in list access",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9448,
"solved": true
},
{
"problem_id": "bug_008",
"title": "Infinite recursion \u2014 missing base case",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9473,
"solved": true
},
{
"problem_id": "bug_009",
"title": "Wrong variable in return",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9985,
"solved": true
},
{
"problem_id": "bug_010",
"title": "Dictionary KeyError",
"steps_taken": 2,
"best_pass_rate": 1.0,
"cumulative_reward": 1.4187,
"solved": true
},
{
"problem_id": "bug_011",
"title": "Reversed sort order",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9568,
"solved": true
},
{
"problem_id": "bug_012",
"title": "Mutating input list unintentionally",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.968,
"solved": true
},
{
"problem_id": "bug_013",
"title": "Forgotten self in method",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9886,
"solved": true
},
{
"problem_id": "bug_014",
"title": "Wrong boolean logic",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9954,
"solved": true
},
{
"problem_id": "bug_015",
"title": "Scope issue with global variable",
"steps_taken": 3,
"best_pass_rate": 0.5,
"cumulative_reward": 1.1811,
"solved": false
},
{
"problem_id": "bug_016",
"title": "Shallow copy issue",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9656,
"solved": true
},
{
"problem_id": "bug_017",
"title": "Wrong string method",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9966,
"solved": true
},
{
"problem_id": "bug_018",
"title": "Wrong exception handling",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9897,
"solved": true
},
{
"problem_id": "bug_019",
"title": "Fibonacci off-by-one",
"steps_taken": 3,
"best_pass_rate": 1.0,
"cumulative_reward": 2.0001,
"solved": true
},
{
"problem_id": "bug_020",
"title": "List comprehension filter wrong",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9984,
"solved": true
},
{
"problem_id": "bug_021",
"title": "Binary search wrong midpoint update",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9901,
"solved": true
},
{
"problem_id": "bug_022",
"title": "Reversed dictionary comprehension",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9651,
"solved": true
},
{
"problem_id": "bug_023",
"title": "String reverse off by one",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9921,
"solved": true
},
{
"problem_id": "bug_024",
"title": "Wrong accumulator init for max",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9719,
"solved": true
},
{
"problem_id": "bug_025",
"title": "Nested loop wrong variable",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9883,
"solved": true
},
{
"problem_id": "bug_026",
"title": "Palindrome check wrong slice",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.983,
"solved": true
},
{
"problem_id": "bug_027",
"title": "Power function wrong operator",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9966,
"solved": true
},
{
"problem_id": "bug_028",
"title": "GCD wrong recursion",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9567,
"solved": true
},
{
"problem_id": "bug_029",
"title": "Zip truncation issue",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9768,
"solved": true
},
{
"problem_id": "bug_030",
"title": "Matrix transpose wrong indices",
"steps_taken": 1,
"best_pass_rate": 1.0,
"cumulative_reward": 0.9677,
"solved": true
}
]
}
}
}