AI Desk · Model Identity · Evidence object

Tokenizer signature tk_f04fd33e

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 Nova · group B group.

Members
1
First observed
21 August 2026
Last observed
21 August 2026
Group
Nova · group B

Models with this signature

The measured vector

Marginal prompt-token cost per string, as measured on Amazon: Nova 2 Lite
All 50 rows

English and whitespace

en-prose14
en-long15
spaces-203
spaces-603
tabs-203
newlines-204
mixed-ws6

Digits

digits-93
digits-124
digits-3010
digits-sep7
float-long9

CJK

zh-common12
zh-long16
zh-rare18
ja-kana8
ja-kanji10
ko12

Other scripts

ru11
ar10
he10
hi11
th9
el14

Emoji

emoji-basic10
emoji-skin11
emoji-zwj-family11
emoji-zwj-x333
emoji-flags14
emoji-prof18

Rare Unicode

math25
boxdraw24
combining10
cjk-ext-b16
surrogates32
zalgo34
rtl-mix6

Code

py-code25
py-indent15
json20
html16
regex42
camel6
snake6

Repetition and encodings

rare-word-x530
repeat-tok21
base6431
hex10
url17
uuid27

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