摘要：我们提出了一种基于离散 EventGraph、连续 EventField 以及人类可读的 EventGlyph 视图构建的结构化时序视频推理管线。在包含 10 个视频和 50 个时序推理问题的校准 EPIC-KITCHENS 子集上，EventField+Glyph 取得了 0.98 的总体准确率，在此子集上相比字幕基线（caption baseline）高出 +0.40（配对 p = 1.1 \times 10^{-5}），相比直接仅使用 VLM 的问答（direct VLM-only QA）高出 +0.20（p = 0.0063）。我们进一步评估了包括人工标注、启发式规则以及启发式+Gemini 管线在内的标注来源变体，发现最佳结构化方法在所有设置下均优于字幕基线。我们还提供了跨视频对的基准测试，并在附录图库中展示了所有研究视频的字形（glyph）输出。总体而言，实验结果表明结构化时序表征能够通过保留符号结构、捕捉时序连续性，并为视频推理提供人类可读的诊断信息，从而同时支持高性能与可检查性。

Abstract:We present a structured temporal video reasoning pipeline built around a discrete EventGraph, a continuous EventField, and a human-readable EventGlyph view. On a calibrated EPIC-KITCHENS subset of 10 videos and 50 temporal reasoning questions, EventField+Glyph achieves 0.98 overall accuracy, which is higher than the caption baseline by +0.40 (paired p = 1.1 \times 10^{-5}) and direct VLM-only QA by +0.20 (p = 0.0063) on this subset. We further evaluate annotation-source variations, including manual, heuristic, and heuristic+Gemini pipelines, and find that the best structured method stays above the caption baseline across settings. We also include cross-video pair benchmarking and an appendix gallery of glyph outputs for all studied videos. Overall, the results indicate that structured temporal representations can support both performance and inspectability by preserving symbolic structure, capturing temporal continuity, and providing human-readable diagnostics for video reasoning.