AI Desk · AI Fingerprinting · Evidence object
Tokenizer signature tk_7d8ce940
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 Unbiased group.
- Members
- 1
- First observed
- 5 October 2026
- Last observed
- 5 October 2026
- Group
- Unbiased
Models with this signature
The measured vector
Marginal prompt-token cost per string, as measured on ParetoAll 50 rows
English and whitespace
en-prose6
en-long8
spaces-201
spaces-601
tabs-201
newlines-201
mixed-ws1
Digits
digits-91
digits-121
digits-302
digits-sep1
float-long1
CJK
zh-common1
zh-long2
zh-rare10
ja-kana1
ja-kanji3
ko5
Other scripts
ru5
ar2
he6
hi10
th3
el8
Emoji
emoji-basic2
emoji-skin6
emoji-zwj-family3
emoji-zwj-x325
emoji-flags8
emoji-prof11
Rare Unicode
math14
boxdraw19
combining2
cjk-ext-b8
surrogates25
zalgo25
rtl-mix1
Code
py-code17
py-indent7
json12
html8
regex39
camel8
snake9
Repetition and encodings
rare-word-x518
repeat-tok33
base6426
hex4
url9
uuid19
Method: tokenizer fingerprinting, v1-50.