ClarusC64/supply-chain-buffer-exhaustion-v0.1

该数据集用于评估模型是否能检测由库存压力和物流延迟引起的供应链不稳定性。每行数据代表一个简化的供应链场景，涵盖三个时间步骤。任务是通过分析库存轨迹、需求轨迹、供应商延迟、运输延迟、仓库利用率和补货响应能力等变量，确定系统是否保持稳定或趋向库存崩溃。预测目标为标签1表示供应链缓冲耗尽风险，标签0表示稳定的库存轨迹。数据集还包括了干扰变量如预测噪声和报告噪声，这些变量单独不影响标签。评估方法包括准确率、精确率、召回率、F1分数、混淆矩阵和数据集完整性诊断。该数据集是Clarus稳定性推理基准的一部分，采用MIT许可证。This dataset evaluates whether models can detect supply chain instability arising from inventory pressure and logistics delay. Each row represents a simplified supply-chain scenario across three time steps. The task is to determine whether the system remains stable or moves toward inventory collapse. The prediction target is label 1 for supply chain buffer exhaustion risk and label 0 for stable inventory trajectory. Each row includes inventory trajectory, demand trajectory, supplier delay, transport delay, warehouse utilization, and restock response capacity, along with decoy variables like forecast_noise and reporting_noise that do not determine the label alone. Evaluation metrics include accuracy, precision, recall, f1, confusion matrix, and dataset integrity diagnostics. This dataset is part of the Clarus Stability Reasoning Benchmark and is licensed under MIT.