LLM NetOps/AIOps Six-Pillar Evidence Audit Dataset

This dataset accompanies the survey “Large Language Models for Agentic NetOps and AIOps: Architectures, Evaluation, and Safety” (arXiv:2605.12729, https://arxiv.org/abs/2605.12729). It provides the record-level evidence audit used to support the survey’s analysis of LLM-enabled NetOps and AIOps across operational capability and autonomy, architecture and tool grounding, assurance and operational control, evaluation and benchmarking, security and adversarial robustness, and human factors, governance, and standards. The dataset records evidential status, analytical pillar, operational domain, task, autonomy role where applicable, tool surface, evaluation setting, safety controls, inclusion rationale, manuscript location, and permissible claim boundary. Separate files provide the direct LLM-facing subset, operational-system coding, search-update records, coverage-validation records, transparent exclusions, contextual comparison surveys, and PRISMA-style search and corpus accounting. The release includes machine-readable CSV and JSON files, a formatted workbook, a data dictionary, a matching machine-readable bibliography, citation metadata, a CC BY 4.0 licence, and integrity checksums. It contains no source full text, reviewer correspondence, private contact details, or internal compilation material.本数据集配套于综述论文《面向智能体网络运维与智能运维的大语言模型（Large Language Models）：架构、评估与安全》（arXiv:2605.12729，https://arxiv.org/abs/2605.12729）。其提供按记录级整理的证据审核材料，用于支撑该综述针对支持大语言模型的网络运维（NetOps）与智能运维（AIOps）的分析工作，分析维度涵盖运行能力与自主性、架构与工具锚定、保障与运行控制、评估与基准测试、安全与对抗鲁棒性，以及人为因素、治理与标准。 本数据集记录的内容包括证据状态、分析支柱、运行域、任务、适用场景下的自主性角色、工具面、评估设置、安全控制、收录依据、手稿位置以及允许的声明边界。配套独立文件包含面向大语言模型的直接子集、运行系统编码、搜索更新记录、覆盖验证记录、透明排除项、上下文对比综述，以及遵循PRISMA规范的搜索与语料库统计材料。 本次发布包含可机器读取的CSV与JSON文件、格式化工作簿、数据字典、配套可机器读取的参考文献列表、引用元数据、CC BY 4.0许可证，以及完整性校验和。本数据集未包含源全文、审稿人往来通信、私人联系信息，或内部汇编材料。