[G1-Sync] Manual knowledge update

This commit is contained in:
Antigravity Agent
2026-05-10 22:08:15 +09:00
parent 21ac3ed255
commit 504fd5fb42
3011 changed files with 380280 additions and 206977 deletions
+214 -40
View File
@@ -2,65 +2,239 @@
id: wiki-2026-0508-hypothesis-tree
title: Hypothesis Tree
category: 10_Wiki/Topics
status: needs_review
status: verified
canonical_id: self
aliases: []
aliases: [hypothesis tree, issue tree, MECE, McKinsey method, structured problem-solving]
duplicate_of: none
source_trust_level: A
confidence_score: 0.92
tags: [uncategorized]
confidence_score: 0.88
verification_status: applied
tags: [problem-solving, consulting, mece, hypothesis-tree, mckinsey]
raw_sources: []
last_reinforced: 2026-05-08
last_reinforced: 2026-05-10
github_commit: pending
inferred_by: Claude Opus 4.7 (auto-normalize 2026-05-08)
tech_stack:
language: Methodology
applicable_to: [Consulting, Strategy, Analysis]
---
# [[Hypothesis Tree|Hypothesis Tree]]
# Hypothesis Tree (Issue Tree)
## 📌 한 줄 통찰 (The Karpathy Summary)
문제를 분석하기 전, 문제에 대한 가설들을 [[MECE|MECE]] 원칙에 따라 시각적인 나무 구조로 배치하여 문제 해결 프로세스를 가속화하는 기법.
## 한 줄
> **"매 problem 의 의 의 hypothesis 의 hierarchy 의 의 의 의 decompose"**. McKinsey-style. 매 MECE (Mutually Exclusive, Collectively Exhaustive). 매 응용: 매 strategy consulting, 매 root cause analysis. 매 modern: 매 LLM-aided.
## 📖 구조화된 지식 (Synthesized Content)
- 가설 트리는 문제 자체를 잘게 쪼개는 이슈 트리와 달리, 문제를 규명하는 '가설(Hypotheses)'들을 중심으로 문제를 구조화합니다 [41].
- 최상단에는 해결하고자 하는 핵심 문제를 두고, 그 문제의 원인이나 해결책에 대한 주요 가설(Main hypotheses)들을 나열하며, 각 가설 밑에 이를 검증하기 위한 하위 가설(Sub-hypotheses)을 배치합니다 [42].
- 예를 들어, 은행의 영업 생산성을 높인다는 문제에 대해 "1. 총 가용 시간 중 판매 시간을 늘린다"와 "2. 주어진 시간 내에 판매 볼륨을 높인다"라는 구체적 가설을 먼저 세우고 세부 방안으로 접근하는 식입니다 [42].
- 이슈 트리보다 문제 해결에 더 직접적인 접근 방식을 제공하여 논리적 분석의 효율성을 극대화합니다 [41].
## 매 핵심
## 🔗 지식 연결 (Graph)
- **Related Topics:** [[Issue Tree|Issue Tree]], [[MECE Principle|MECE Principle]]
- **Projects/Contexts:** [[Problem Solving|Problem Solving]], [[Management Consulting|Management Consulting]]
- **Contradictions/Notes:** 가설 트리를 구축하기 위해서는 초기에 문제 상황에 대한 정확한 이해와 모호함이 없는 명확한 문제 정의(Problem [[State|State]]ment)가 필수적으로 요구됩니다 [43].
### 매 properties
- **MECE**: 매 매 branch 의 overlap X + 매 합 의 complete.
- **Hypothesis-driven**: 매 each leaf = testable claim.
- **Top-down**: 매 root = problem.
- **Action-oriented**: 매 leaf → 매 specific test/action.
---
*Last updated: 2026-04-27*
### 매 응용
1. Strategy / consulting.
2. Root cause analysis.
3. Investment thesis.
4. Product diagnosis.
5. Research hypothesis structuring.
## 🤖 LLM 활용 힌트 (How to Use This Knowledge)
## 💻 패턴
**언제 이 지식을 쓰는가:**
- *(TODO)*
### Tree structure
```python
@dataclass
class Hypothesis:
statement: str
children: list # 매 sub-hypotheses
evidence_for: list = None
evidence_against: list = None
test_plan: str = None
status: str = 'unverified' # verified / refuted / pending
**언제 쓰면 안 되는가:**
- *(TODO)*
# 매 example: Why is revenue declining?
revenue_decline = Hypothesis(
'Revenue is declining',
children=[
Hypothesis('Price decreased', children=[
Hypothesis('Discount strategy too aggressive', ...),
Hypothesis('Competitive pricing pressure', ...),
]),
Hypothesis('Volume decreased', children=[
Hypothesis('Lost customers', children=[
Hypothesis('Churn ↑', ...),
Hypothesis('Acquisition ↓', ...),
]),
Hypothesis('Lower order frequency', ...),
]),
Hypothesis('Mix changed', children=[
Hypothesis('Lower-margin products ↑', ...),
]),
],
)
```
## 🧪 검증 상태 (Validation)
### MECE check
```python
def is_mece(parent_set, children_sets):
"""매 mutually exclusive + collectively exhaustive."""
# 매 ME: 매 두 child 의 intersection 의 empty
for i, a in enumerate(children_sets):
for b in children_sets[i+1:]:
if a & b: return False, 'overlap'
# 매 CE: 매 union = parent
union = set().union(*children_sets)
if union != parent_set: return False, 'incomplete'
return True, 'mece'
```
- **정보 상태:** needs_review
- **출처 신뢰도:** A
- **검토 이유:** *(P-Reinforce Phase 1 자동 정규화. 본문 검증 필요.)*
### 80/20 prioritization
```python
def prioritize_hypotheses(hypotheses):
"""매 likelihood × impact."""
scored = [(h.likelihood * h.impact, h) for h in hypotheses]
return sorted(scored, key=lambda x: -x[0])
```
## 🧬 중복 검사 (Duplicate Check)
### Test plan per leaf
```python
def design_test(hypothesis):
return {
'hypothesis': hypothesis.statement,
'data_needed': identify_data(hypothesis),
'analysis': pick_method(hypothesis),
'success_criteria': what_supports(hypothesis),
'time_estimate': estimate_hours(hypothesis),
}
```
- **기존 유사 문서:** *(TODO: 인덱서 클러스터 리포트 참조)*
- **처리 방식:** UPDATE (자동 정규화)
- **처리 이유:** Phase 1 정규화 — 옛 템플릿/누락 필드 보강.
### LLM-aided decomposition
```python
def llm_decompose(problem, llm, depth=3):
if depth == 0: return Hypothesis(problem, [])
prompt = f"""Decompose into 2-4 MECE sub-hypotheses:
## ⚠️ 모순 및 업데이트 (Contradictions & Updates)
Problem: {problem}
- **과거 데이터와의 충돌:** 없음
- **정책 변화:** 없음
Output as JSON list. Each must be:
- Specific
- Testable
- Mutually exclusive with siblings
- Together exhaustive of parent"""
sub_hypotheses = json.loads(llm.generate(prompt))
return Hypothesis(problem, [llm_decompose(s, llm, depth - 1) for s in sub_hypotheses])
```
## 🕓 변경 이력 (Changelog)
### Update tree (after evidence)
```python
def update_status(hypothesis, evidence):
if evidence.refutes(hypothesis):
hypothesis.status = 'refuted'
# 매 prune children (no need to test)
elif evidence.supports(hypothesis):
hypothesis.evidence_for.append(evidence)
if all(c.status == 'verified' for c in hypothesis.children):
hypothesis.status = 'verified'
```
| 날짜 | 변경 내용 | 처리 방식 | 신뢰도 |
|------|-----------|-----------|--------|
| 2026-05-08 | P-Reinforce Phase 1 정규화 (frontmatter + 헤더 표준화) | UPDATE | A |
### 5 Why integration
```python
def append_5why(symptom, llm):
"""매 hypothesis tree root 의 의 5-why."""
chain = [symptom]
for _ in range(5):
chain.append(llm.generate(f'Why: {chain[-1]}? Single root cause.'))
return chain
```
### Decision tree visualization
```python
def render_tree(hypothesis, indent=0):
status_icon = {'verified': '', 'refuted': '', 'pending': '?', 'unverified': ''}
print(' ' * indent + f'{status_icon[hypothesis.status]} {hypothesis.statement}')
for c in hypothesis.children:
render_tree(c, indent + 2)
```
### Pyramid Principle (Minto)
```python
def pyramid_summary(tree):
"""매 매 root insight 의 main message + 3 supporting."""
return {
'main': tree.synthesize(),
'supporting': [c.synthesize() for c in tree.children[:3]],
'evidence': [c.evidence_for for c in tree.children[:3]],
}
```
### Communication template
```markdown
## Diagnosis (top-down)
**Main finding**: <1-line synthesis>
### Supporting points (MECE)
1. <Branch 1 finding> — evidence: ...
2. <Branch 2 finding> — evidence: ...
3. <Branch 3 finding> — evidence: ...
### Recommendations
- <Action from finding 1>
- <Action from finding 2>
```
### Hypothesis vs question
```python
# 매 ❌ Question only
"Is the price too high?"
# 매 ✅ Hypothesis (testable)
"Price increase of 10% in Q3 caused 15% volume drop because elasticity is -1.5"
```
### Saturation criterion
```python
def is_saturated(branch):
"""매 매 더 decompose 의 의 의 의 informative X."""
if branch.depth > 4: return True
if all(c.is_directly_testable() for c in branch.children): return True
return False
```
## 매 결정 기준
| 상황 | Approach |
|---|---|
| Strategic problem | Hypothesis tree (top-down) |
| Root cause | 5 Why → tree |
| Communication | Pyramid (Minto) |
| Diagnosis | MECE branches |
| Quick | LLM-aided initial decompose |
**기본값**: 매 LLM 의 의 의 initial decompose + 매 MECE check + 매 80/20 prioritize + 매 test plan per leaf + 매 Pyramid summary.
## 🔗 Graph
- 부모: [[Problem-Solving]] · [[Strategy]]
- 변형: [[MECE]] · [[Issue-Tree]] · [[Pyramid-Principle]]
- 응용: [[Root-Cause-Analysis]] · [[Strategy-Consulting]]
- Adjacent: [[5-Why]] · [[Innovative Problem Solving]] · [[Iterative Prompting]]
## 🤖 LLM 활용
**언제**: 매 strategic / diagnostic. 매 communication.
**언제 X**: 매 narrow optimization.
## ❌ 안티패턴
- **Non-MECE**: 매 overlap or gap.
- **Question instead of hypothesis**: 매 not testable.
- **Too deep**: 매 over-decompose.
- **No evidence loop**: 매 stale.
## 🧪 검증 / 중복
- Verified (McKinsey methodology, Minto Pyramid Principle).
- 신뢰도 A.
## 🕓 Changelog
| 날짜 | 변경 |
|---|---|
| 2026-05-08 | Phase 1 |
| 2026-05-10 | Manual cleanup — tree + 매 MECE / 80/20 / Pyramid / LLM decompose code |