model,task_id,paired_n,coverage_delta_mean,coverage_delta_ci_low,coverage_delta_ci_high,coverage_delta_best,coverage_delta_worst,semantic_coverage_delta_mean,semantic_coverage_delta_ci_low,semantic_coverage_delta_ci_high qwen-max,2012_q2fsm,1,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0 qwen-max,2013_q2afsm,1,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0