stefanocarrera/autophagycode_D_he_train-mercury_Qwen3-8B_strategy_trust_t0.75_g6_run0_metrics

该数据集包含164个样本，每个样本记录了一个代码函数（可能是Python）的多项指标，包括任务ID、入口点、可执行性、正确性、测试通过/失败数量、运行时间、错误类型，以及一系列代码复杂度度量（如Halstead词汇量、长度、难度、工作量、时间、圈复杂度、可维护性指数、代码行数、有效代码行数、注释百分比、TTR、令牌字典、香农熵、预测熵等）。主要用于代码度量分析、质量评估或机器学习研究。This dataset contains 164 samples, each recording multiple metrics for a code function (likely Python), including task ID, entry point, executability, correctness, tests passed/failed, runtime, error type, and various code complexity measures (Halstead vocabulary, length, difficulty, effort, time, cyclomatic complexity, maintainability index, lines of code, source lines of code, comment percentage, TTR, token dictionary, Shannon entropy, predictive entropy, etc.). It is intended for code metrics analysis, quality assessment, or machine learning research.