Synthesis paper. Agent model, working memory, orthographic embedding (bijection via LPP counts), 100-word experimental results, two-level trace (word events + spelling residual), MDL lexicon criterion, factor tower. Experimental plan with predictions for full-lexicon implementation.
The Lexicon Embedding: From Bytes to Words in the Universal Model
Complete picture: agent model, orthographic bijection, two-level trace (word events + spelling residual), MDL lexicon, factor tower, quotient ring algebra, P-programming, formal tokenization contrast. 100-word results (−0.552 bpc). Experimental plan for full lexicon. 14pp.