One-shot prediction enables rapid adaptation of pretrained foundation models to new tasks using only one labeled example, but lacks principled uncertainty quantification. While conformal prediction provides finite-sample coverage guarantees, standard split conformal methods are inefficient in the one-shot setting due to data splitting and reliance on a single predictor. We propose Conformal Aggregation of One-Shot Predictors (CAOS), a conformal framework that adaptively aggregates multiple one-shot predictors and uses a leave-one-out calibration scheme to fully exploit scarce labeled data. Despite violating classical exchangeability assumptions, we prove that CAOS achieves valid marginal coverage using a monotonicity-based argument. Experiments on one-shot facial landmarking and RAFT text classification tasks show that CAOS produces substantially smaller prediction sets than split conformal baselines while maintaining reliable coverage.

翻译：一次性预测使得预训练基础模型仅需一个标注样本即可快速适应新任务，但缺乏严格的不确定性量化方法。虽然保形预测能提供有限样本覆盖保证，标准的分割保形方法在一次性场景中因数据分割和依赖单一预测器而效率低下。本文提出一次性预测器的保形聚合（CAOS），该保形框架自适应地聚合多个一次性预测器，并采用留一校准方案以充分利用稀缺标注数据。尽管违背经典可交换性假设，我们通过单调性论证证明了CAOS仍能实现有效的边际覆盖。在一次性人脸关键点检测和RAFT文本分类任务上的实验表明，CAOS在保持可靠覆盖的同时，产生的预测集显著小于分割保形基线方法。