agent-harness / tasks /validation /summary.json
cuber12's picture
Publish agent harness research code and paper artifacts
d61821a verified
Raw
History Blame Contribute Delete
5.34 kB
{
"go_version": "go version go1.26.5 darwin/arm64",
"schema_version": 1,
"tasks": [
{
"checks": {
"gold_suite_passes": true,
"original_suite_passes": true,
"source_patch_applies": true,
"test_patch_applies": true,
"test_patch_exposes_bug": true
},
"elapsed_seconds": 10.734249542001635,
"task_id": "TASK_CR_001",
"valid_end_to_end": true
},
{
"checks": {
"gold_suite_passes": true,
"original_suite_passes": true,
"source_patch_applies": true,
"test_patch_applies": true,
"test_patch_exposes_bug": true
},
"elapsed_seconds": 2.3070981248747557,
"task_id": "TASK_CR_002",
"valid_end_to_end": true
},
{
"checks": {
"gold_suite_passes": true,
"original_suite_passes": true,
"source_patch_applies": true,
"test_patch_applies": true,
"test_patch_exposes_bug": true
},
"elapsed_seconds": 1.4855274590663612,
"task_id": "TASK_CR_003",
"valid_end_to_end": true
},
{
"checks": {
"gold_suite_passes": true,
"original_suite_passes": true,
"source_patch_applies": true,
"test_patch_applies": true,
"test_patch_exposes_bug": false
},
"elapsed_seconds": 4.444933749968186,
"task_id": "TASK_CR_004",
"valid_end_to_end": false
},
{
"checks": {
"gold_suite_passes": true,
"original_suite_passes": true,
"source_patch_applies": true,
"test_patch_applies": true,
"test_patch_exposes_bug": true
},
"elapsed_seconds": 0.8311544579919428,
"task_id": "TASK_CR_005",
"valid_end_to_end": true
},
{
"checks": {
"gold_suite_passes": true,
"original_suite_passes": true,
"source_patch_applies": true,
"test_patch_applies": true,
"test_patch_exposes_bug": true
},
"elapsed_seconds": 8.65276591712609,
"task_id": "TASK_CR_006",
"valid_end_to_end": true
},
{
"checks": {
"gold_suite_passes": true,
"original_suite_passes": true,
"source_patch_applies": true,
"test_patch_applies": true,
"test_patch_exposes_bug": true
},
"elapsed_seconds": 5.886036082869396,
"task_id": "TASK_CR_007",
"valid_end_to_end": true
},
{
"checks": {
"gold_suite_passes": true,
"original_suite_passes": true,
"source_patch_applies": true,
"test_patch_applies": true,
"test_patch_exposes_bug": true
},
"elapsed_seconds": 8.418221125146374,
"task_id": "TASK_CR_008",
"valid_end_to_end": true
},
{
"checks": {
"gold_suite_passes": true,
"original_suite_passes": true,
"source_patch_applies": true,
"test_patch_applies": true,
"test_patch_exposes_bug": true
},
"elapsed_seconds": 59.26803741697222,
"task_id": "TASK_CR_009",
"valid_end_to_end": true
},
{
"checks": {
"gold_suite_passes": false,
"original_suite_passes": false,
"source_patch_applies": true,
"test_patch_applies": true,
"test_patch_exposes_bug": true
},
"elapsed_seconds": 367.28817354212515,
"task_id": "TASK_CR_010",
"valid_end_to_end": false
},
{
"checks": {
"gold_suite_passes": false,
"original_suite_passes": false,
"source_patch_applies": true,
"test_patch_applies": true,
"test_patch_exposes_bug": true
},
"elapsed_seconds": 123.33281491696835,
"task_id": "TASK_CR_011",
"valid_end_to_end": false
},
{
"checks": {
"gold_suite_passes": true,
"original_suite_passes": true,
"source_patch_applies": true,
"test_patch_applies": true,
"test_patch_exposes_bug": true
},
"elapsed_seconds": 1.5974912918172777,
"task_id": "TASK_CR_012",
"valid_end_to_end": true
},
{
"checks": {
"gold_suite_passes": true,
"original_suite_passes": true,
"source_patch_applies": true,
"test_patch_applies": true,
"test_patch_exposes_bug": true
},
"elapsed_seconds": 7.358322124928236,
"task_id": "TASK_CR_013",
"valid_end_to_end": true
},
{
"checks": {
"gold_suite_passes": false,
"original_suite_passes": false,
"source_patch_applies": true,
"test_patch_applies": true,
"test_patch_exposes_bug": true
},
"elapsed_seconds": 22.20793900010176,
"task_id": "TASK_CR_014",
"valid_end_to_end": false
},
{
"checks": {
"gold_suite_passes": false,
"original_suite_passes": false,
"source_patch_applies": true,
"test_patch_applies": true,
"test_patch_exposes_bug": true
},
"elapsed_seconds": 7.876011084066704,
"task_id": "TASK_CR_015",
"valid_end_to_end": false
}
],
"valid_task_ids": [
"TASK_CR_001",
"TASK_CR_002",
"TASK_CR_003",
"TASK_CR_005",
"TASK_CR_006",
"TASK_CR_007",
"TASK_CR_008",
"TASK_CR_009",
"TASK_CR_012",
"TASK_CR_013"
]
}