Interaction valence reveals contrasting social networks in dairy cattle

交互效价揭示奶牛截然不同的社交网络

Abstract: Social relationships shape access to resources, exposure to conflict and group stability, yet automated livestock monitoring typically treats behaviour as isolated events. Here, we present a valence-aware social-network framework that transforms video-derived interactions into herd-level representations of affiliative and agonistic organization. 摘要： 社交关系决定了资源获取、冲突暴露和群体稳定性，然而目前的自动化牲畜监测通常将行为视为孤立的事件。在此，我们提出了一种基于“效价感知”（valence-aware）的社交网络框架，该框架能将视频捕捉到的交互行为转化为牛群层面的亲和与竞争组织结构表征。

A pose-based computer-vision pipeline analysed 7 h 39 min of continuous video from the pre-milking area of one commercial dairy farm. After quality control, 1,183 of 1,414 candidate interactions remained, involving 36 cows and 177 dyads. In a predicted-class-balanced audit of 198 pipeline-detected clips, automated and manual labels agreed in 82.8% of cases, with an unweighted audit-sample macro-F1 of 0.872. These values describe the audited sample rather than prevalence-weighted or end-to-end deployment performance. 一个基于姿态估计的计算机视觉流水线分析了某商业奶牛场挤奶前区域 7 小时 39 分钟的连续视频。经过质量控制，在 1,414 个候选交互中，有 1,183 个被保留，涉及 36 头奶牛和 177 个双牛组合。在对 198 个由流水线检测到的片段进行预测类别平衡审计中，自动标注与人工标注的一致性达到 82.8%，未加权的审计样本宏观 F1 分数为 0.872。这些数值描述的是审计样本的情况，而非加权流行度或端到端部署的性能。

The aggregated network was connected (density = 0.281; transitivity = 0.513; mean path length = 1.88), and predicted affiliative events formed five algorithmic communities (modularity Q = 0.429). Within the observed zone, predicted agonistic interactions comprised 72.4% of retained events and 76.0% of interaction duration. The cow with the most partners did not have the highest betweenness centrality. 聚合后的网络是连通的（密度 = 0.281；传递性 = 0.513；平均路径长度 = 1.88），预测的亲和事件形成了五个算法社区（模块度 Q = 0.429）。在观察区域内，预测的竞争性交互占保留事件的 72.4%，占交互总时长的 76.0%。拥有最多伙伴的奶牛并不具备最高的中介中心性。

Separating events by predicted valence produced descriptively different affiliative and agonistic layers, with contrasting edge sets, community partitions and individual positions. Thus, pooled interaction counts can obscure the behavioural composition of an observed network. Valence-aware analysis provides a framework for testing hypotheses about competition, affiliation and welfare-relevant change, while requiring longitudinal validation before use as a welfare or health indicator. 通过预测效价将事件分离，产生了在描述上截然不同的亲和层和竞争层，它们具有对比鲜明的边集、社区划分和个体位置。因此，汇总的交互计数可能会掩盖观察到的网络的行为构成。这种效价感知分析为检验关于竞争、亲和及福利相关变化的假设提供了一个框架，但在将其用作福利或健康指标之前，仍需进行纵向验证。