2601.13260v1.pdf
Extension
Size
538 KiB
Media Type
application/pdf
SHA-256 is a widely used cryptographic hash function.
This sequence of letters and numbers can be used as a unique identifier for this file
File Hash: SHA-256
dcc17f096f5f5bc6c4da1cda049b28a220c44d6869d96368ea0bd549c6b7fbde
Annotations
Structured records describing the file.
Read moreTitle
Stop Taking Tokenizers for Granted: They Are Core Design Decisions in Large Language Models
Version
1.7
Page Count
23
Producer
pikepdf 8.15.1
{
"file/base": {
"record": {
"extension": ".pdf",
"hash": "dcc17f096f5f5bc6c4da1cda049b28a220c44d6869d96368ea0bd549c6b7fbde",
"media_type": "application/pdf",
"media_type_prefix": "application",
"name": "2601.13260v1.pdf",
"size": 550960
},
"source": {
"execution_id": "a149b5f4-341a-4519-9464-aa38013de59c",
"id": "file/base",
"type": "Model",
"version": "1.0.0"
}
},
"file/pdf": {
"private": false,
"record": {
"keywords": [],
"page_count": 23,
"producer": "pikepdf 8.15.1",
"title": "Stop Taking Tokenizers for Granted: They Are Core Design Decisions in Large Language Models",
"version": "1.7"
},
"source": {
"execution_id": "f39ab7a0-12b7-4a65-9472-bb4b3628362e",
"id": "dorsal/pdf",
"type": "Model",
"version": "1.1.0"
}
}
}
The number of unique users who have indexed this public file record
The date this file's metadata was first publicly indexed by any user.
The most recent date this file's metadata was publicly indexed by any user.
File Statistics
- Views:
- 38
- Indexed by:
- 1 user
- Indexed:
- 2026-02-17