trace_synthesis/tasks/173.json
yuyr a84d51a101 1. 增加r1生成综合策略代码和输出;
2. 增加tasks;
3. 增加analysis部分,对策略进行归纳分类,然后进行评测。
2025-04-17 17:40:15 +08:00

33 lines
921 B
JSON

{
"sites": [
"gitlab"
],
"task_id": 173,
"require_login": true,
"storage_state": "./.auth/gitlab_state.json",
"start_url": "http://localhost:28084",
"geolocation": null,
"intent_template": "Open my latest updated issue that has keyword \"{{keyword}}\" in its title to check if it is closed",
"instantiation_dict": {
"keyword": "better"
},
"intent": "Open my latest updated issue that has keyword \"better\" in its title to check if it is closed",
"require_reset": false,
"eval": {
"eval_types": [
"string_match",
"url_match"
],
"reference_answers": {
"fuzzy_match": [
"No, it is open"
]
},
"reference_url": "http://localhost:28084/byteblaze/empathy-prompts/-/issues/8",
"program_html": [],
"reference_answer_raw_annotation": "Not closed",
"string_note": "",
"url_note": "GOLD in PRED"
},
"intent_template_id": 310
}