$Φ$asmaNet：用约73万参数的神经网络快速预测引力波信噪比
$Φ$asmaNet: A Staged Spectral Token-Refinement Architecture for Fast Gravitational-Wave Signal-to-Noise Ratio Prediction
天体物理里的引力波信噪比计算向来很费算力，这篇用一个小模型把百万次评估压缩到几秒，做引力波种群研究的人可以直接拿来用。
$Φ$asmaNet 是一个针对表格回归的分阶段谱注意力架构，用于预测旋进高阶模双黑洞信号（IMRPhenomXPHM）的相位平均最优信噪比。模型仅约 732k 参数，在 10^6 样本训练后，held-out 测试集上 100-MAPE 达 98.73%，经 PCHIP 单调校准后为 99.29%，在 ρ>8 的探测相关区间达到 99.39%（R²=0.9998），优于 MLP、1D-ResNet 和 Transformer-encoder 基线。单张 GPU 上每秒可完成约 1.2×10^5 次 SNR 评估，处理 10^6 注入目录约 8.3 秒，比 16 核 CPU 上的传统波形内积计算快约两个数量级。
$Φ$asmaNet: A Staged Spectral Token-Refinement Architecture for Fast Gravitational-Wave Signal-to-Noise Ratio Prediction
Quantifying selection effects in gravitational-wave population studies requires millions of costly signal-to-noise ratio (SNR) calculations. We present $Φ$asmaNet, a compact neural architecture for structured tabular regression, with staged spectral refinement as an explicit architectural prior. Learned input tokens are refined through ordered attention-based $Φ$-Stages, each augmented by a $Φ$-Refractor subspace-mixing module, then revisited through gated top-down $Φ$-Feedback. Applied to the 11-dimensional parameters of precessing, higher-mode binary black hole signals (IMRPhenomXPHM), it predicts phase-averaged optimal SNR for a single detector at fixed Advanced LIGO design sensitivity. With approximately 732k parameters, it outperforms MLP, 1D-ResNet and Transformer-encoder baselines under matched training across $10^5$--$10^6$ samples. At $10^6$ samples, it achieves $100-\mathrm{MAPE}=98.73\%$ on the held-out test set, $99.29\%$ after rank-preserving monotonic (PCHIP) calibration, and $99.39\%$ ($R^2=0.9998$) in the detection-relevant regime $ρ>8$, with stable accuracy across independent dataset realizations. On a single GPU, it sustains approximately $1.2\times10^5$ SNR evaluations per second and processes a $10^6$-injection catalogue end-to-end in approximately 8.3 s, about two orders of magnitude faster than conventional waveform-and-inner-product calculations on a 16-core CPU. Exact distance rescaling through $ρ\propto1/d_L$ supports repeated catalogue-wide detectability evaluations. The fully documented pipeline is intended as a reproducible benchmark, while results on public tabular datasets indicate competitiveness beyond gravitational-wave applications. Although demonstrated for a fixed single-detector configuration, the construction supports extensions to detector networks and epoch-specific sensitivities. (Abridged)