stefanocarrera/autophagycode_D_he_train-mercury_Qwen3-8B_strategy_trust_t0.75_g9_run0_metrics
收藏资源简介:
该数据集包含代码片段的执行结果和静态分析指标,包括任务ID、入口点、是否可执行、是否正确、测试通过数、测试失败数、错误类型、Halstead复杂度指标(词汇量、长度、体积、难度、努力、时间)、循环复杂度、可维护性指数、代码行数、源代码行数、注释百分比、TTR(类型-令牌比)、令牌字典、香农熵、预测熵、定义的函数数量以及入口点是否重复等。数据仅包含训练集,共164个样本。
This dataset contains execution results and static analysis metrics for code snippets, including task ID, entry point, executable flag, correctness flag, number of tests passed/failed, error type, Halstead complexity metrics (vocabulary, length, volume, difficulty, effort, time), cyclomatic complexity, maintainability index, lines of code, source lines of code, comment percentage, TTR (type-token ratio), token dictionary, Shannon entropy, predictive entropy, number of defined functions, and whether the entry point is repeated. The dataset only includes a training split with 164 samples.




