AI Desk · Model Identity · Evidence object

Tokenizer signature tk_25bf52d0

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 ByteDance Seed group.

Members
4
First observed
21 August 2026
Last observed
21 August 2026
Group
ByteDance Seed

Models with this signature

The measured vector

Marginal prompt-token cost per string, as measured on ByteDance Seed: Seed 1.6
All 50 rows

English and whitespace

en-prose14
en-long16
spaces-203
spaces-603
tabs-204
newlines-204
mixed-ws7

Digits

digits-99
digits-1212
digits-3030
digits-sep12
float-long22

CJK

zh-common11
zh-long13
zh-rare18
ja-kana18
ja-kanji13
ko13

Other scripts

ru13
ar12
he13
hi17
th16
el14

Emoji

emoji-basic9
emoji-skin14
emoji-zwj-family11
emoji-zwj-x333
emoji-flags16
emoji-prof19

Rare Unicode

math30
boxdraw29
combining5
cjk-ext-b16
surrogates41
zalgo36
rtl-mix6

Code

py-code26
py-indent18
json25
html16
regex50
camel7
snake8

Repetition and encodings

rare-word-x531
repeat-tok41
base6433
hex19
url20
uuid36

Method: tokenizer fingerprinting, v1-50. Raw data: fingerprints.json · index.json · test-strings.json.