AI Desk · Model Identity · Evidence object
Tokenizer signature tk_41571a13
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 Baidu group.
- Members
- 1
- First observed
- 22 August 2026
- Last observed
- 22 August 2026
- Group
- Baidu
Models with this signature
The measured vector
Marginal prompt-token cost per string, as measured on Baidu: ERNIE 4.5 VL 424B A47BAll 50 rows
English and whitespace
en-prose14
en-long15
spaces-204
spaces-606
tabs-2022
newlines-2022
mixed-ws9
Digits
digits-99
digits-1212
digits-3030
digits-sep12
float-long22
CJK
zh-common8
zh-long10
zh-rare27
ja-kana10
ja-kanji13
ko12
Other scripts
ru13
ar12
he12
hi14
th14
el13
Emoji
emoji-basic20
emoji-skin22
emoji-zwj-family19
emoji-zwj-x357
emoji-flags8
emoji-prof35
Rare Unicode
math44
boxdraw41
combining10
cjk-ext-b16
surrogates54
zalgo36
rtl-mix6
Code
py-code28
py-indent19
json28
html17
regex44
camel6
snake11
Repetition and encodings
rare-word-x526
repeat-tok21
base6431
hex15
url23
uuid36
Method: tokenizer fingerprinting, v1-50.