dela
e6918ffa35
Attach the stepwise derivation toolkit as a submodule and default SUPERPAPER_PHASE to 2 so rewrite-figure can use superderive. Notes still keep align for short expansions without cancel or subst.
47 lines
1.1 KiB
YAML
47 lines
1.1 KiB
YAML
schema: superpaper.ledger/v1
|
|
retired_ids: []
|
|
paper:
|
|
id: derive-delegate
|
|
title: Scaled attention
|
|
authors: ["Fixture"]
|
|
notes_language: zh
|
|
source: {kind: excerpt}
|
|
coverage:
|
|
mode: excerpt
|
|
questions:
|
|
- {id: Q1, text: "缩放从哪来？", source: "excerpt"}
|
|
claims:
|
|
- id: C1
|
|
text: "1/√d_k 是改写，不是新算子"
|
|
kind: theoretical
|
|
status: core
|
|
supports: [Q1]
|
|
definitions: []
|
|
assumptions: []
|
|
lemmas: []
|
|
symbols:
|
|
- {name: Q, latex: "Q", meaning: "query", kind: value}
|
|
- {name: K, latex: "K", meaning: "key", kind: value}
|
|
- {name: dk, latex: "d_k", meaning: "key 维", kind: "shape parameter"}
|
|
derivations:
|
|
- id: DER1
|
|
claim: C1
|
|
title: "缩放"
|
|
expand: true
|
|
figure: F3
|
|
steps:
|
|
- {id: S1, from: "QK^{\\top}", to: "QK^{\\top}/\\sqrt{d_k}", rule: scale}
|
|
figures:
|
|
- id: F3
|
|
claim: C1
|
|
title: "缩放来自方差"
|
|
grammar: derivation
|
|
toolkit: superderive
|
|
signals: [rewrite-figure]
|
|
request: figures/F3/F3.request.md
|
|
include: figures/F3/build/F3.pdf
|
|
status: included
|
|
evidence: []
|
|
terms: []
|
|
source_assets: []
|