casper

Traditional matched filtering has been the standard for Gravitational waves (GW) detection ever since LIGO was established,even though it requires pre-computed waveform templates and provides no accounts of information about which signal drove thedecision of classification. Deep-learning alternatives showed competitive sensitivity, but system biasesincluding class overlap,imbalanced class weighting, limited sample variation, and traintest mismatchcontinue to cause problems with generalisation inreal detector noise. We introduce CASPER-Classification with Attribution via ShaPlEy in Residual neural networks, an end-to-endpipeline combining residual convolutional neural network (CNN) classifier with a FastSHAP explainer. 260 distinct events from theGravitational Wave open Science Centre were fetched across SNR range of 7-42 from both H1 and L1 detectors with no syntheticaugmentation. The classifier achieves AUC (Area Under Curve) of 91% across the model with a low false alarm rate. Focal Lossand Platt Calibration were used to improve decision boundary and generalisation. FastSHAP attribution maps recover the completechirp morphology and provides detailed maps for a visual interpretation of the decision. The complete pipeline contains fewerparameters than standard deep learning models and requires no hardware except a standard CPU making our model an effectivelightweight pipeline for Gravitational Wave Detection under real life conditions.