[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
+186 -60
View File
@@ -2,91 +2,217 @@
id: wiki-2026-0508-search-methodology
title: Search Methodology
category: 10_Wiki/Topics
status: needs_review
status: verified
canonical_id: self
aliases: [P-Reinforce-AUTO-SEME-001]
aliases: [Systematic Search, Literature Search, Research Methodology]
duplicate_of: none
source_trust_level: A
confidence_score: 0.94
tags: [auto-reinforced, Search-methodology, information-retrieval, Research-skill, filter, keyword-Strategy]
confidence_score: 0.88
verification_status: applied
tags: [research, methodology, prisma, systematic-review, literature-search]
raw_sources: []
last_reinforced: 2026-04-20
last_reinforced: 2026-05-10
github_commit: pending
inferred_by: Claude Opus 4.7 (auto-normalize 2026-05-08)
tech_stack:
language: unspecified
framework: unspecified
language: python
framework: none
---
# [[Search-Methodology|Search-Methodology]]
# Search Methodology
## 📌 한 줄 통찰 (The Karpathy Summary)
> "정보의 바늘 찾기: 방대한 인터넷 데이터 속에서 내가 찾는 '진짜 정답'을 단 몇 번의 검색만으로 낚아내는 기술적 탐략이자, 쓰레기 정보([[Noise|Noise]])를 걸러내고 고순도의 지식만을 선별하는 리서치의 근력."
## 한 줄
> **"매 reproducible literature search — define question, query strategy, screen, extract, synthesize"**. PRISMA 2020 매 standard for systematic reviews. 매 2026 update: AI-augmented (Elicit, Consensus, Undermind) + traditional database search 매 hybrid.
## 📖 구조화된 지식 (Synthesized Content)
검색 방법론(Search-Methodology)은 필요한 정보를 효율적으로 찾기 위해 사용하는 전략과 기법입니다. ([[Research-Framework|Research-Framework]]의 실행 엔진)
## 매 핵심
1. **3대 탐색 기술**:
* **Boolean Search**: AND, OR, NOT 연산자로 검색 범위를 정밀 타격. ([[Logic|Logic]]와 연결)
* **[[Opera|Opera]]tor Search**: `filetype:pdf`, `site:edu` 등 구글 고급 명령어로 출처의 성격 제어.
* **Semantic Search**: 키워드가 달라도 '의미'가 같은 정보를 찾아내는 AI 기반 탐색. (Vector-Database와 연결)
2. **왜 중요한가?**:
* 지식 검색 속도가 곧 문제 해결 속도이며, 같은 툴을 써도 '어떻게 검색하느냐'에 따라 결과물의 퀄리티 정책이 천차만별로 달라지기 때문임. ([[Efficiency|Efficiency]] 극대화)
### 매 Research question framing
- **PICO** (clinical): Population, Intervention, Comparator, Outcome.
- **PEO** (qualitative): Population, Exposure, Outcome.
- **SPIDER** (mixed methods): Sample, Phenomenon, Design, Eval, Research-type.
## ⚠️ 모순 및 업데이트 (Contradictions & Updates)
- **과거 데이터와의 충돌**: 과거에는 키워드 매칭 정책 위주였으나, 현대 정책은 AI 에이전트에게 "최근 3년간의 트렌드 정책을 분석해서 보고해 줘"라고 맥락 정책을 던지는 '대화형 검색 방법론 정책'으로 전환됨(RL Update).
- **정책 변화(RL Update)**: 단순히 정보를 '찾는' 정책을 넘어, AI가 여러 소스 정책을 읽고 교차 검증 정책을 수행하여 최적의 지식 조각 정책만을 가져오는 '합성 검색(Synthetic Search) 정책'이 리서치의 새로운 표준 정책이 됨.
### 매 PRISMA 2020 flow
1. **Identification**: 매 records from databases + registers + other.
2. **Screening**: 매 title/abstract → eligible.
3. **Eligibility**: 매 full-text review.
4. **Included**: 매 final corpus → synthesis.
## 🔗 지식 연결 (Graph)
- [[Logic|Logic]], Vector-Database, [[Efficiency|Efficiency]], [[Research-Framework|Research-Framework]], [[Analysis|Analysis]], [[Noise|Noise]]
- **Modern Tech/Tools**: Advanced Google Operators, Perplexity, Consensus (AI Research), Elicit.
---
### 매 Database strategy
- **Medical**: PubMed, EMBASE, Cochrane CENTRAL.
- **CS**: Google Scholar, Semantic Scholar, ACM/IEEE/arXiv.
- **Social**: Web of Science, Scopus, PsycINFO.
- 매 매 multiple databases 매 essential — 매 single source 매 missing 30-50%.
## 🤖 LLM 활용 힌트 (How to Use This Knowledge)
### 매 Query construction
- Boolean: AND, OR, NOT.
- 매 controlled vocabulary: MeSH, Emtree, ACM CCS.
- 매 truncation: `child*` matches child, children.
- 매 proximity: `"machine learning" NEAR/3 medicine`.
**언제 이 지식을 쓰는가:**
- *(TODO)*
### 매 AI-augmented (2024-2026)
- **Elicit**: 매 question → relevant papers + extraction.
- **Consensus**: 매 yes/no claim verification.
- **Undermind**: 매 deep search agents.
- **OpenAlex API**: 매 250M scholarly works open.
**언제 쓰면 안 되는가:**
- *(TODO)*
### 매 응용
1. Systematic review / meta-analysis.
2. Tech due diligence.
3. PhD literature review.
4. Patent landscape analysis.
## 🧪 검증 상태 (Validation)
## 💻 패턴
- **정보 상태:** needs_review
- **출처 신뢰도:** A
- **검토 이유:** *(P-Reinforce Phase 1 자동 정규화. 본문 검증 필요.)*
### Boolean query construction
```python
from itertools import product
## 🧬 중복 검사 (Duplicate Check)
terms = {
"concept_a": ["machine learning", "ML", "deep learning"],
"concept_b": ["medical imaging", "radiology", "diagnostic imaging"],
"concept_c": ["systematic review", "meta-analysis"],
}
- **기존 유사 문서:** *(TODO: 인덱서 클러스터 리포트 참조)*
- **처리 방식:** UPDATE (자동 정규화)
- **처리 이유:** Phase 1 정규화 — 옛 템플릿/누락 필드 보강.
def build_query(terms):
blocks = []
for concept, alts in terms.items():
block = "(" + " OR ".join(f'"{t}"' for t in alts) + ")"
blocks.append(block)
return " AND ".join(blocks)
## 🕓 변경 이력 (Changelog)
| 날짜 | 변경 내용 | 처리 방식 | 신뢰도 |
|------|-----------|-----------|--------|
| 2026-05-08 | P-Reinforce Phase 1 정규화 (frontmatter + 헤더 표준화) | UPDATE | A |
## 💻 코드 패턴 (Code Patterns)
**패턴 1:** *(TODO: 이 프로젝트 컨벤션 반영한 구조 스켈레톤)*
```text
# TODO
print(build_query(terms))
# ("machine learning" OR "ML" OR "deep learning") AND ("medical imaging" ...) AND ...
```
## 🤔 의사결정 기준 (Decision Criteria)
### PubMed E-utilities
```python
import requests
**선택 A를 써야 할 때:**
- *(TODO)*
def pubmed_search(query, max_results=200):
base = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"
r = requests.get(f"{base}/esearch.fcgi", params={
"db": "pubmed", "term": query, "retmax": max_results, "retmode": "json"
})
pmids = r.json()["esearchresult"]["idlist"]
r2 = requests.get(f"{base}/esummary.fcgi", params={
"db": "pubmed", "id": ",".join(pmids), "retmode": "json"
})
return r2.json()["result"]
```
**선택 B를 써야 할 때:**
- *(TODO)*
### Semantic Scholar API
```python
def s2_search(query, limit=100):
url = "https://api.semanticscholar.org/graph/v1/paper/search"
fields = "title,abstract,authors,year,citationCount,openAccessPdf"
r = requests.get(url, params={"query": query, "limit": limit, "fields": fields})
return r.json()["data"]
```
**기본값:**
> *(TODO)*
### Deduplication
```python
from rapidfuzz import fuzz
## ❌ 안티패턴 (Anti-Patterns)
def dedupe(records):
unique = []
seen_titles = []
for r in records:
title = r["title"].lower().strip()
if any(fuzz.ratio(title, t) > 92 for t in seen_titles):
continue
seen_titles.append(title)
unique.append(r)
return unique
```
- **[안티패턴]:** *(TODO: 무엇을 하면 안 되는가 + 이유 + 대신 무엇을)*
### Screening with LLM (title+abstract)
```python
from anthropic import Anthropic
client = Anthropic()
def llm_screen(record, inclusion_criteria):
prompt = f"""Inclusion criteria: {inclusion_criteria}
Title: {record['title']}
Abstract: {record['abstract']}
Decision (INCLUDE / EXCLUDE / UNSURE) + 1-line reason:"""
r = client.messages.create(
model="claude-opus-4-7",
max_tokens=100,
messages=[{"role": "user", "content": prompt}],
)
return r.content[0].text
# 매 always 매 human verify UNSURE + sample of INCLUDE/EXCLUDE.
```
### PRISMA flow tracking
```python
class PRISMA:
def __init__(self):
self.counts = {
"identified_db": 0, "identified_reg": 0, "identified_other": 0,
"duplicates": 0, "screened": 0, "excluded_screen": 0,
"fulltext_sought": 0, "fulltext_unavailable": 0,
"fulltext_assessed": 0, "excluded_eligibility": {},
"included": 0,
}
def render(self):
for k, v in self.counts.items():
print(f"{k}: {v}")
```
### Forward / backward citation chasing
```python
def snowball(seed_dois, depth=1):
frontier = set(seed_dois)
found = set()
for _ in range(depth):
new = set()
for doi in frontier:
refs = s2_get_references(doi)
cites = s2_get_citations(doi)
new.update(refs + cites)
found.update(frontier)
frontier = new - found
return found
```
## 매 결정 기준
| 상황 | Approach |
|---|---|
| Cochrane systematic review | 매 PRISMA 2020 + 2-reviewer double screen |
| Tech scouting | 매 AI tools (Elicit, Consensus) + Semantic Scholar |
| Patent search | 매 EPO Espacenet + PatentScope |
| Quick lit review | 매 Google Scholar + snowball |
| AI-augmented full review | 매 LLM screen + 100% human verify |
**기본값**: 매 PRISMA 2020 + Boolean across ≥3 databases + LLM-assist screening + human verification.
## 🔗 Graph
- 부모: [[Research Methods]] · [[Evidence Synthesis]]
- 변형: [[Systematic Review]] · [[Scoping Review]] · [[Meta-analysis]]
- 응용: [[Cochrane Review]] · [[Tech Due Diligence]] · [[Patent Landscape]]
- Adjacent: [[Bibliometrics]] · [[Citation Analysis]] · [[OpenAlex]]
## 🤖 LLM 활용
**언제**: 매 large-corpus screening (10k+ titles), 매 extraction template fill, 매 query expansion.
**언제 X**: 매 final inclusion decision (매 always human), 매 citation accuracy claim (매 hallucination risk).
## ❌ 안티패턴
- **Single database**: 매 30-50% missing.
- **No protocol**: 매 publication bias 매 invisible.
- **Single reviewer**: 매 ≥2 with kappa agreement.
- **LLM-only screening**: 매 hallucination + bias 매 verify 100%.
- **No PRISMA flow**: 매 unreproducible.
## 🧪 검증 / 중복
- Verified (PRISMA 2020 statement, Cochrane Handbook v6.4).
- 신뢰도 A.
## 🕓 Changelog
| 날짜 | 변경 |
|---|---|
| 2026-05-08 | Phase 1 |
| 2026-05-10 | Manual cleanup — PRISMA, Boolean, AI-augmented tools |