Empirical study across 12 corpora shows tail slope of global-KL predictive contribution spectrum correlates with scaling exponents and effective truncation rank K(N) scales linearly with log N (R² 0.96 raw), supporting spectrum coverage as the driver of excess loss reduction.
The smallest automaton recognizing the subwords of a text.Theoretical Computer Science, 40:31–55
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Data Scaling as Progressive Coverage of a Predictive Contribution Spectrum
Empirical study across 12 corpora shows tail slope of global-KL predictive contribution spectrum correlates with scaling exponents and effective truncation rank K(N) scales linearly with log N (R² 0.96 raw), supporting spectrum coverage as the driver of excess loss reduction.