AI Desk · Model Identity · Evidence object
Tokenizer signature tk_b6cc7610
An exact tokenizer signature: every model listed below returned the same marginal prompt-token count on all 50 test strings. Sharing a signature is strong evidence of a shared vocabulary. This signature sits in the IBM group.
- Members
- 1
- First observed
- 3 September 2026
- Last observed
- 3 September 2026
- Group
- IBM
Models with this signature
The measured vector
Marginal prompt-token cost per string, as measured on IBM: Granite 4.2 8BAll 50 rows
English and whitespace
en-prose14
en-long16
spaces-203
spaces-603
tabs-204
newlines-205
mixed-ws5
Digits
digits-93
digits-125
digits-3015
digits-sep7
float-long10
CJK
zh-common18
zh-long25
zh-rare23
ja-kana14
ja-kanji17
ko19
Other scripts
ru16
ar25
he24
hi35
th26
el29
Emoji
emoji-basic10
emoji-skin30
emoji-zwj-family18
emoji-zwj-x354
emoji-flags24
emoji-prof29
Rare Unicode
math32
boxdraw28
combining14
cjk-ext-b13
surrogates39
zalgo36
rtl-mix11
Code
py-code28
py-indent18
json23
html17
regex47
camel5
snake11
Repetition and encodings
rare-word-x531
repeat-tok22
base6435
hex11
url21
uuid27
Method: tokenizer fingerprinting, v1-50.