ORCA reports a balanced crisis detection AUC of 0.741 using 206 features from spectral graph analysis of correlation networks, with a backtested dynamic allocation strategy achieving Sharpe 1.13 and -7.5% max drawdown.
Long short-term memory,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Stacked LSTM models are trained to predict the first and second erroneous bits plus a continue-flipping check to improve SCLF decoding performance for polar codes over prior methods.
citing papers explorer
-
ORCA -- Online Regime Correlation Analyzer
ORCA reports a balanced crisis detection AUC of 0.741 using 206 features from spectral graph analysis of correlation networks, with a backtested dynamic allocation strategy achieving Sharpe 1.13 and -7.5% max drawdown.
-
Deep-Learning-Aided Successive Cancellation List Flip Decoding for Polar Codes
Stacked LSTM models are trained to predict the first and second erroneous bits plus a continue-flipping check to improve SCLF decoding performance for polar codes over prior methods.