---
title: "$Φ$asmaNet: A Staged Spectral Token-Refinement Architecture for Fast Gravitational-Wave Signal-to-Noise Ratio Prediction"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.05309v1"
permalink: "https://feed.astralor.com/items/itm_cdfe17db6165d656001b375a"
published: "2026-11-03T18:19:11.000Z"
score: 62
channel: "tech"
tags: ["推理效率","RAG","Staged Spectral Token-Refinement","Architecture","Fast Gravitational-Wave Signal-to-Noise","Ratio Prediction Quantifying","SNR","Quantifying"]
---

# $Φ$asmaNet: A Staged Spectral Token-Refinement Architecture for Fast Gravitational-Wave Signal-to-Noise Ratio Prediction

## At a glance

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 re…

## Key points

- 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.

## Full text

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)

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_cdfe17db6165d656001b375a