A Random Matrix Theory method identifies growing Correlation Traps in neural network weight spectra during an 'anti-grokking' overfitting phase, and applies the same diagnostic to some foundation LLMs.
Plancks Gesetz und Lichtquantenhypothese.Zeitschrift für Physik, 26(1): 178–181
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
The phase-number commutation for macroscopic order parameters emerges from second quantization in the thermodynamic limit, unifying BEC, BCS superconductivity, and their crossover as coherent-state dynamics.
citing papers explorer
-
Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory
A Random Matrix Theory method identifies growing Correlation Traps in neural network weight spectra during an 'anti-grokking' overfitting phase, and applies the same diagnostic to some foundation LLMs.
-
Third Quantization for Order Parameter (I): BCS-BEC crossover with macroscopically coherent state
The phase-number commutation for macroscopic order parameters emerges from second quantization in the thermodynamic limit, unifying BEC, BCS superconductivity, and their crossover as coherent-state dynamics.