Timely disclosure of insider transactions is a cornerstone of market transparency, yet delays in filing remain widespread and challenging to monitor at scale. This study introduces a comprehensive insider filing delay dataset spanning more than four million Form 4 transactions from 2002 to 2025, enriched with annotations on insider roles, governance attributes, and firm-level indicators. Building on these data, we present a hybrid framework that integrates a state-space encoder with an XGBoost classifier to capture temporal trading patterns while retaining interpretability essential for regulatory auditing. The framework consistently outperforms statistical models, deep sequence learners, and large language model baselines, achieving balanced gains in precision, recall, and F1-score. Feature ablation analyses highlight the predictive importance of insider history, spatiotemporal factors, and governance signals, shedding light on the behavioral drivers of both minor oversights and systematic violations. Beyond accuracy, the dataset and framework establish a reproducible benchmark for studying disclosure compliance, offering regulators and researchers transparent tools to strengthen market integrity.

翻译：内幕交易的及时披露是市场透明度的基石，然而申报延迟现象仍普遍存在且难以大规模监控。本研究构建了一个涵盖2002年至2025年逾400万份Form 4交易记录的综合性内幕申报延迟数据集，并标注了内幕人员角色、治理属性及公司层面指标。基于此数据，我们提出一种融合状态空间编码器与XGBoost分类器的混合框架，既能捕捉时序交易模式，又保持了监管审计所必需的可解释性。该框架在精确率、召回率与F1分数上均取得均衡提升，持续优于统计模型、深度序列学习器及大语言模型基线。特征消融分析揭示了内幕交易历史、时空因素与治理信号的关键预测作用，为理解轻微疏忽与系统性违规的行为动因提供了新视角。除预测性能外，本数据集与框架为披露合规研究建立了可复现的基准，为监管机构与研究者提供了增强市场完整性的透明化工具。