SambaGraph：用于足球战术响应建模的动作-反应时空图
SambaGraph: Action-Reaction Spatio-Temporal Graphs for Soccer Tactical Response Modeling
- Michigan Technological University（密歇根理工大学）
- ESPOL Polytechnic University（ESPOL理工大学）
- University of Granada（格拉纳达大学）
- SambaSports AI
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
SambaGraph构建了足球动作-反应时空图数据集，验证了图编码器在响应分类和防守检索中的有效性，为战术响应建模提供了可复现基准。
AI中文摘要：
足球战术是交互式的：进攻动作改变了对手的防守问题，而观察到的响应取决于多智能体的比赛状态。我们引入了SambaGraph，一个用于足球战术响应建模的动作-反应时空图数据集和基准。从2022年FIFA世界杯全部64场比赛的追踪和事件数据中，我们整理了4,070个以动作为中心的片段，表示为时间对齐的23节点球员-球图序列，包含进攻/防守视图、响应标签和26,270个分割安全的进攻-防守对。我们研究了三个问题：观察到的响应是否能从图片段中分类，是否能针对查询进攻检索到成功的防守，以及图派生的摘要是否支持基于grounded的LLM推理。一个紧凑的签名MLP在响应分类上获得了$0.796\pm0.007$的宏F1分数，而融合的图-签名双编码器在全库防守检索中达到了$0.471\pm0.029$的Hit@5和$0.655\pm0.051$的Hit@10。硬负样本最大化了配对区分度，但并未提高检索质量。局部LLM在直接分类上表现不如监督编码器，并且在八候选重排序中未优于强原始顺序，但它们提供了基于grounded的战术理由。这些结果使SambaGraph成为基于图的足球策略-响应研究的可复现基准。代码和数据集可在以下网址获取：this https URL。
英文摘要：
Soccer tactics are interactive: an attacking action changes the opponent's defensive problem, and the observed response depends on the multi-agent match state. We introduce SambaGraph, an action--reaction spatio-temporal graph dataset and benchmark for soccer tactical response modeling. From tracking and event data for all 64 matches of the 2022 FIFA World Cup, we curate 4,070 action-centered episodes represented as temporally aligned 23-node player--ball graph sequences with attack/defense views, response labels, and 26,270 split-safe attack--defense pairs. We study three questions: whether observed responses can be classified from graph episodes, whether successful defenses can be retrieved for a query attack, and whether graph-derived summaries support grounded LLM reasoning. A compact signature MLP obtains $0.796\pm0.007$ macro-F1 for response classification, while a fused graph--signature dual encoder reaches $0.471\pm0.029$ Hit@5 and $0.655\pm0.051$ Hit@10 for full-bank defensive retrieval. Hard negatives maximize pair discrimination but not retrieval quality. Local LLMs underperform supervised encoders for direct classification and do not improve over a strong original order in eight-candidate reranking, but they provide grounded tactical rationales. These results position SambaGraph as a reproducible benchmark for graph-based soccer strategy-response research. Code and dataset are available at: https://github.com/areyesan/SambaGraph.
