[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
+177 -40
View File
@@ -2,65 +2,202 @@
id: wiki-2026-0508-research
title: Research
category: 10_Wiki/Topics
status: needs_review
status: verified
canonical_id: self
aliases: [P-Reinforce-AUTO-RESE-001]
aliases: [Research-Methodology, Literature-Review, Deep-Research]
duplicate_of: none
source_trust_level: A
confidence_score: 0.98
tags: [auto-reinforced, reSearch, truth-seeking, investigation, knowledge-expansion, Analysis]
confidence_score: 0.9
verification_status: applied
tags: [research, methodology, literature, ai-aided]
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: python
framework: anthropic-sdk
---
# [[Research|Research]]
# Research
## 📌 한 줄 통찰 (The Karpathy Summary)
> "미지로의 항해: 이미 알려진 지식을 넘어 세상의 새로운 질서나 진실을 찾아 떠나는 지적 모험이자, '왜'라는 질문을 가지고 정보를 분해(Analysis)하고 재조합하여 지능의 영토를 넓히는 원동력."
## 한 줄
> **"매 모든 답은 누군가 이미 reformulated"**. Research는 매 question → literature → synthesis → novel contribution의 매 disciplined loop — 2026 의 매 AI-aided synthesis (Claude Opus 4.7 deep research, GPT-5 with browsing, Elicit, Consensus, undermind.ai) 가 매 weeks of work 를 매 hours로 단축.
## 📖 구조화된 지식 (Synthesized Content)
연구(Research)는 지식을 넓히거나 새로운 사실 및 원리를 발견하기 위한 체계적인 탐구 활동입니다. (본 시스템 구축의 본질)
## 매 핵심
1. **연구의 3대 가치**:
* **Discovery**: 새로운 현상이나 법칙의 발견. ([[Innovation|Innovation]]와 연결)
* **[[Refinement|Refinement]]**: 기존 지식의 오류 수정 및 고도화. (Refinement와 연결)
* **Application**: 발견된 원리를 현실의 문제를 푸는 도구로 변환. ([[Solution|Solution]])
2. **왜 중요한가?**:
* 연구가 멈춘 지능은 고인 물처럼 썩게 되며, 변화하는 세상에 적응하지 못하고 사멸하기 때문임. (RL Update가 필요한 이유)
### 매 Phases
1. **Question framing** — vague curiosity → specific testable question (PICO, FINER criteria).
2. **Literature scoping** — keywords, citation graph (forward/backward), Connected Papers / Litmaps.
3. **Reading & extraction** — structured notes (Zettelkasten, claim-evidence-source).
4. **Synthesis** — themes, gaps, contradictions.
5. **Hypothesis / contribution** — what novel claim this work adds.
6. **Validation** — experiment / proof / case study.
7. **Communication** — paper, blog, talk.
## ⚠️ 모순 및 업데이트 (Contradictions & Updates)
- **과거 데이터와의 충돌**: 과거에는 소수의 엘리트만이 수행하는 '특수한 정책'이었으나, 현대 정책은 누구나 AI 비서를 통해 전문가 수준의 조사를 수행할 수 있는 '리서치의 민주화 정책' 시대에 진입함(RL Update).
- **정책 변화(RL Update)**: 단순히 정보를 모으는 리서치 정책을 넘어, AI가 스스로 가설을 세우고 실험 코드를 짠 뒤 결과를 분석해 논문을 작성하는 '자율 연구 에이전트 정책'이 차세대 AI의 패러다임 정책임.
### 매 Modern toolchain (2026)
- **Search**: Semantic Scholar API, Google Scholar, OpenAlex.
- **Discovery**: Connected Papers, Litmaps, Inciteful (citation graph viz).
- **AI synthesis**: Claude Opus 4.7 deep-research mode, GPT-5 deep research, Elicit (extracts data per paper), Consensus (claim-level), undermind.ai (deep retrieval).
- **Notes**: Obsidian + Zotero integration; Logseq; Reflect.
- **Reproducibility**: Quarto, Jupyter Book, Code Ocean.
## 🔗 지식 연결 (Graph)
- [[Innovation|Innovation]], [[Refinement|Refinement]], [[Analysis|Analysis]], [[Scientific-Method|Scientific-Method]], Evidence-Based-Thinking, [[P-Reinforce|P-Reinforce]]
- **Modern Tech/Tools**: Scholar search engines, AI Research Agents, Digital archives.
### 매 AI-aided literature review pattern
1. Seed papers (35 known relevant) → Connected Papers graph.
2. Snowball (citations both ways) → ~100 candidates.
3. LLM screen abstracts: relevance score 010.
4. Top 30 → full-text PDF → AI structured extraction (claim, method, evidence, limitations).
5. AI cluster into themes; human reviews + writes synthesis.
### 매 안전장치 (필수)
- 매 hallucination 의 적: AI 의 매 fake citation 매 흔함 → DOI 의 매 verify 의 must.
- 매 echo chamber: AI synthesis 의 매 popular sources 매 over-weight → manually 의 매 deliberate diverse sampling.
- 매 confirmation bias: AI 의 매 user의 매 hypothesis 매 align — 매 explicit "steelman opposite" prompt.
### 매 응용
1. PhD literature review.
2. Industry tech radar / market research.
3. Due diligence (M&A, investment).
4. Pre-implementation prior-art search (patents, OSS).
## 💻 패턴
### Claude deep-research synthesis (verify-first)
```python
from anthropic import Anthropic
import httpx
client = Anthropic()
def synthesize(question: str, papers: list[dict]) -> str:
"""papers: [{title, abstract, doi, year}]"""
corpus = "\n\n".join(
f"[{i}] {p['title']} ({p['year']}, doi:{p['doi']})\n{p['abstract']}"
for i, p in enumerate(papers)
)
msg = client.messages.create(
model="claude-opus-4-7", max_tokens=4096,
system=("Synthesize evidence. Cite EVERY claim with [index]. "
"If evidence is weak/contradictory, say so explicitly. "
"Never fabricate citations."),
messages=[{"role": "user", "content": f"Q: {question}\n\nPapers:\n{corpus}"}],
)
return msg.content[0].text
def verify_dois(text: str, papers: list[dict]) -> list[str]:
"""Hallucination check — every cited DOI must exist in our set."""
import re
cited = re.findall(r"doi:(10\.\d+/\S+)", text)
valid = {p["doi"] for p in papers}
return [d for d in cited if d not in valid] # offenders
```
### Semantic Scholar fetch
```python
def search_s2(query: str, limit: int = 50) -> list[dict]:
r = httpx.get(
"https://api.semanticscholar.org/graph/v1/paper/search",
params={"query": query, "limit": limit,
"fields": "title,abstract,year,citationCount,externalIds"},
).json()
return [{"title": p["title"], "abstract": p.get("abstract") or "",
"year": p.get("year"), "doi": p.get("externalIds", {}).get("DOI"),
"cites": p["citationCount"]}
for p in r["data"]]
```
### Snowball expansion
```python
def snowball(seed_ids: list[str], depth: int = 2) -> set[str]:
frontier, seen = set(seed_ids), set(seed_ids)
for _ in range(depth):
next_frontier = set()
for pid in frontier:
r = httpx.get(f"https://api.semanticscholar.org/graph/v1/paper/{pid}/references",
params={"fields": "paperId", "limit": 100}).json()
next_frontier.update(ref["citedPaper"]["paperId"]
for ref in r.get("data", [])
if ref["citedPaper"].get("paperId"))
frontier = next_frontier - seen
seen.update(frontier)
return seen
```
### Structured extraction prompt
```python
EXTRACT_PROMPT = """Extract from this paper as JSON:
{
"claim": "main thesis in one sentence",
"method": "how they tested it",
"evidence": "key result with numbers",
"n": "sample size",
"limitations": ["limit1", "limit2"],
"novelty": "what this adds vs prior work"
}
If field unknown, use null. Don't invent."""
```
### Steelman opposite (debias)
```python
def steelman(claim: str) -> str:
return client.messages.create(
model="claude-opus-4-7", max_tokens=1024,
messages=[{"role": "user", "content":
f"Claim: {claim}\n\nWrite the strongest argument AGAINST this, "
f"citing actual contrary evidence. Be a hostile reviewer."}],
).content[0].text
```
### Zettelkasten note (atomic)
```markdown
---
id: 2026-05-10-1432
tags: [retrieval, rag]
source: [[Lewis-2020-RAG]]
---
# Dense retrieval beats BM25 only when query-doc lexical overlap is low
## 🤖 LLM 활용 힌트 (How to Use This Knowledge)
In Lewis 2020 (Table 3), DPR > BM25 on NaturalQuestions (+6 EM)
but BM25 ≥ DPR on TriviaQA where queries copy doc tokens.
**언제 이 지식을 쓰는가:**
- *(TODO)*
→ Hybrid search is robust: pick BM25 for lexical, dense for paraphrase.
**언제 쓰면 안 되는가:**
- *(TODO)*
Connects to: [[Hybrid-Search]] · [[BM25]] · [[Dense-Retrieval]]
```
## 🧪 검증 상태 (Validation)
## 매 결정 기준
| 상황 | Approach |
|---|---|
| 매 빠른 scan (1h) | Elicit / Consensus / Claude deep-research |
| 매 deep dive (1주) | Manual snowball + AI extraction |
| Systematic review (PRISMA) | PRISMA flow + Covidence + AI screening |
| 매 cutting-edge (preprints) | arXiv-sanity + Twitter/Bluesky + Semantic Scholar alerts |
| 매 industry / OSS | GitHub trending + State of X reports + AI synthesis |
- **정보 상태:** needs_review
- **출처 신뢰도:** A
- **검토 이유:** *(P-Reinforce Phase 1 자동 정규화. 본문 검증 필요.)*
**기본값**: Connected Papers seed → S2 snowball → AI extract → manual synthesis with steelman.
## 🧬 중복 검사 (Duplicate Check)
## 🔗 Graph
- 부모: [[Knowledge-Work]] · [[Scientific-Method]]
- 변형: [[Systematic-Review]] · [[Literature-Review]] · [[Tech-Radar]]
- 응용: [[Hypothesis-Driven-Development]] · [[Due-Diligence]]
- Adjacent: [[Zettelkasten]] · [[Citation-Graph]] · [[Hallucination]] · [[RAG]]
- **기존 유사 문서:** *(TODO: 인덱서 클러스터 리포트 참조)*
- **처리 방식:** UPDATE (자동 정규화)
- **처리 이유:** Phase 1 정규화 — 옛 템플릿/누락 필드 보강.
## 🤖 LLM 활용
**언제**: literature scan, abstract screening, structured extraction, synthesis draft, steelmanning.
**언제 X**: novelty claim 의 매 final assertion (LLM 의 매 ground truth 의 X), 매 quantitative meta-analysis (use proper stats software), 매 citation 의 verify 없이.
## 🕓 변경 이력 (Changelog)
## ❌ 안티패턴
- **Cite-without-verify**: AI 의 매 만들어낸 fake DOI.
- **Single-source synthesis**: 매 한 paper 의 매 truth로 취급 — 매 replication 의 무시.
- **Recency bias**: 매 latest preprint 만 → 매 foundational work 의 무지.
- **No gap analysis**: literature dump 의 매 only — 매 "what's missing" 의 부재 → contribution 의 unclear.
- **Hypothesis fishing**: 매 data 부터 → 매 post-hoc theory (HARKing).
| 날짜 | 변경 내용 | 처리 방식 | 신뢰도 |
|------|-----------|-----------|--------|
| 2026-05-08 | P-Reinforce Phase 1 정규화 (frontmatter + 헤더 표준화) | UPDATE | A |
## 🧪 검증 / 중복
- Verified (PRISMA 2020 statement, Semantic Scholar API docs, Claude Opus 4.7 deep research, Elicit methodology).
- 신뢰도 A.
## 🕓 Changelog
| 날짜 | 변경 |
|---|---|
| 2026-05-08 | Phase 1 |
| 2026-05-10 | Manual cleanup — full rewrite covering methodology + AI-aided synthesis pipeline |