Files
CGA-bench/analysis/paper_runs/paper_fsm/run_level.csv

6 lines
1.9 KiB
CSV
Raw Normal View History

2026-05-22 10:02:42 +08:00
experiment_name,model,condition,repeat,run_dir,task_id,coverage,semantic_coverage,eval1_pass,eval2_pass,eval2_ratio,eval2_ratio_float,eval2_failed_mutants,full_pass,time_sec,token_cost,first_improvement_iter,op_record,task_log
paper_fsm,qwen-max,baseline,1,/home/zhang/CorrectBench/saves/0406~0412/Paper_Experiments/paper_fsm/qwen-max/baseline/paper_fsm_qwen-max_baseline_r01_20260410_184106,2013_q2afsm,92.3076923076923,73.51,False,,,,,False,519.09,0.7850400000000001,,"gen,syncheck,funccheck,coverage_eval,eval",/home/zhang/CorrectBench/saves/0406~0412/Paper_Experiments/paper_fsm/qwen-max/baseline/paper_fsm_qwen-max_baseline_r01_20260410_184106/2013_q2afsm/task_log.log
paper_fsm,qwen-max,baseline,1,/home/zhang/CorrectBench/saves/0406~0412/Paper_Experiments/paper_fsm/qwen-max/baseline/paper_fsm_qwen-max_baseline_r01_20260410_184106,2012_q2fsm,91.66666666666666,61.17,True,False,7/10,0.7,"6,7,8",False,348.97,0.62682,,"gen,syncheck,funccheck,coverage_eval,eval",/home/zhang/CorrectBench/saves/0406~0412/Paper_Experiments/paper_fsm/qwen-max/baseline/paper_fsm_qwen-max_baseline_r01_20260410_184106/2012_q2fsm/task_log.log
paper_fsm,qwen-max,cga,1,/home/zhang/CorrectBench/saves/0406~0412/Paper_Experiments/paper_fsm/qwen-max/cga/paper_fsm_qwen-max_cga_r01_20260410_185537,2013_q2afsm,92.3076923076923,73.51,False,,,,,False,1803.02,2.66142,,"gen,syncheck,funccheck,gen,syncheck,funccheck,cga,eval",/home/zhang/CorrectBench/saves/0406~0412/Paper_Experiments/paper_fsm/qwen-max/cga/paper_fsm_qwen-max_cga_r01_20260410_185537/2013_q2afsm/task_log.log
paper_fsm,qwen-max,cga,1,/home/zhang/CorrectBench/saves/0406~0412/Paper_Experiments/paper_fsm/qwen-max/cga/paper_fsm_qwen-max_cga_r01_20260410_185537,2012_q2fsm,91.66666666666666,61.17,True,False,3/10,0.3,"2,4,6,7,8,9,10",False,489.72,0.7213599999999999,,"gen,syncheck,funccheck,cga,eval",/home/zhang/CorrectBench/saves/0406~0412/Paper_Experiments/paper_fsm/qwen-max/cga/paper_fsm_qwen-max_cga_r01_20260410_185537/2012_q2fsm/task_log.log