AI Desk · AI Fingerprinting · Evidence object
Tokenizer signature tk_0ac9122a
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 China Telecom (XingChen) group.
- Members
- 1
- First observed
- 16 October 2026
- Last observed
- 16 October 2026
- Group
- China Telecom (XingChen)
Models with this signature
The measured vector
Marginal prompt-token cost per string, as measured on XingChen: Xing4.0 29B A4B (free)All 50 rows
English and whitespace
en-prose14
en-long17
spaces-203
spaces-603
tabs-2022
newlines-2022
mixed-ws9
Digits
digits-910
digits-1213
digits-3031
digits-sep13
float-long23
CJK
zh-common9
zh-long11
zh-rare28
ja-kana9
ja-kanji14
ko14
Other scripts
ru11
ar13
he15
hi17
th16
el16
Emoji
emoji-basic21
emoji-skin41
emoji-zwj-family20
emoji-zwj-x358
emoji-flags33
emoji-prof36
Rare Unicode
math49
boxdraw40
combining14
cjk-ext-b17
surrogates55
zalgo36
rtl-mix6
Code
py-code28
py-indent18
json28
html17
regex51
camel7
snake11
Repetition and encodings
rare-word-x531
repeat-tok41
base6436
hex19
url23
uuid37
Method: tokenizer fingerprinting, v1-50.