AI 中文总结
本研究以S-PLUS DR6类星体为对象，对比表格基础模型与8种基线模型，发现TabPFN 2.5在概率测光红移估计中表现最优，尤其适用于小训练集或协变量偏移场景。
AI 中文摘要
我们评估表格基础模型是否可作为S-PLUS DR6巡天中类星体的现成概率测光红移估计器，该巡天中色-红移简并会产生多模态后验分布，且光谱训练集相对于测光样本存在偏移。我们将TabPFN 2.5、RealTabPFN 2.5和TabICL与8种特定任务基线模型进行基准测试，包括线性条件高斯模型、FlexZBoost、混合密度网络、归一化流、随机森林和梯度提升树，训练集包含500至121626个类星体，使用密度和点预测指标，以及近似测光目标样本部署的重要性加权分数。TabPFN 2.5在除未加权CDE损失外的所有指标上表现最佳或统计上并列最佳，归一化流在该指标上统计并列且均值最低；其最大优势出现在训练集较小和困难场景（极亮与极暗源、高红移）中，同时在协变量偏移下保持接近标称的校准效果。其主要实际成本在于推理：在权重冻结时，大型支持集和目标目录需要大量GPU/加速器内存，全目录部署可能需要支持集子采样或蒸馏。SHAP归因分析表明WISE W1/W2是最强的单一预测因子，紫外和光学波段提供不可忽略的改进。我们得出结论，TabPFN 2.5是概率类星体测光红移估计的强默认选择，尤其在训练数据有限或协变量偏移下的校准至关重要时。
英文摘要
We assess whether tabular foundation models can be used as off-the-shelf probabilistic photometric-redshift estimators for quasars in the 12-band S-PLUS DR6 survey, where colour-redshift degeneracies produce multi-modal posteriors and spectroscopic training sets are shifted relative to the photometric population. TabPFN 2.5, RealTabPFN 2.5, and TabICL are benchmarked against eight task-specific baselines, including linear conditional Gaussians, FlexZBoost, mixture-density networks, normalising flows, random forests, and gradient-boosted trees, with training sets from 500 to 121,626 quasars, using both density and point-prediction metrics, together with importance-weighted scores that approximate deployment on the photometric target sample. TabPFN 2.5 is best or statistically tied for best on all metrics except the unweighted CDE loss, on which the normalising flow is statistically tied and attains the lowest mean value; its largest gains occur for small training sets and in difficult regimes (very bright and faint sources, high redshift), while retaining near-nominal calibration under covariate shift. Its main practical cost is inference: with frozen weights, large support and target catalogues require substantial GPU/accelerator memory, and full-catalogue deployment may need support-set subsampling or distillation. SHAP attributions identify WISE W1/W2 as the strongest individual predictors, with UV and optical bands offering non-negligible refinements. We conclude that TabPFN 2.5 is a strong default for probabilistic quasar photo-z estimation, particularly when training data are limited or when calibration under covariate shift is critical.
Comments28 pages, 10 figures, 6 tables. Submitted to the AAS Journals
