fig-20260131-07: SN Layered Graph

Sparse Network with Named Event Spaces and Pattern Flow

Layered Event Space Structure

INPUT HIDDEN OUTPUT Digits Punctuation Vowels Whitespace XML chars Other (219) Persistent neurons h[34] h[48] h[62] h[71] h[113] Digit-correlated (10) Punct-correlated (6) Vowel-correlated (5) Undifferentiated (107 neurons) Digits Punctuation Vowels Whitespace XML chars Other (219) 255 Confirmed ES Investigating Numbered (not yet named)

Information Accounting (Compression Framing)

Framing: We describe compression in bits, then renormalize to remaining bits. No percentages - each step describes a compression from X bpc to Y bpc.
Random baseline:
8.00 bpc
RNN model:
5.69 bpc
Bits captured by RNN:
2.31 bits
ES-based model:
6.63 bpc
Bits captured by ESs:
1.37 bits
Result: 5 ESs (Digits, Punct, Vowels, Whitespace, Other) explain 59.3% of RNN's compression (1.37 of 2.31 bits/char).

Remaining: 0.94 bits/char unexplained by ES-level predictions. This is what byte-specific patterns add beyond character class membership.

Named Events (E → N mapping)

Input Layer - Confirmed ESs

Digits (10) Punctuation (6) Vowels (5) Whitespace (3) XML <>/= (4) Consonants (21) Other (207)

Hidden Layer - Discovered

Persistent (5) Digit-corr (10) Punct-corr (6) Vowel-corr (5) Unassigned (102)

Output Layer - Predicted

Digits (10) Punctuation (6) Vowels (5) Other (235)

Strongest Named Patterns

Whitespace
Punctuation
255
"SPACE" → "-", "=", "#", "(", "{" (Wikipedia formatting)
Digits
Digits
~200
Multi-digit numbers: "1" → "9", "0" → "0", etc.
Vowels
Consonants
~150
Vowel-consonant alternation in English words

Extraction Status

Completed: Next (for tick-tock cycle):
  1. Feed ES membership as additional input features
  2. Train next round on augmented input
  3. Measure improvement in bpc
  4. Extract higher-level ESs from new hidden layer

Reproducibility

Figure: fig-20260131-07

Model: model.bin (Elman RNN, 256→128→256, 6.02 bpc)

ES confirmation: hypothesis-results.html (fig-20260131-04)

Data: enwik9

./hutter stats model.bin
./hutter probe enwik9 model.bin "prev=0" 5  # digit context