[G1-Sync] Manual knowledge update

2026-05-10 22:08:15 +09:00
parent 21ac3ed255
commit 504fd5fb42
3011 changed files with 380280 additions and 206977 deletions
@@ -2,92 +2,239 @@
 id: wiki-2026-0508-epistemology
 title: Epistemology
 category: 10_Wiki/Topics
-status: needs_review
+status: verified
 canonical_id: self
-aliases: [P-Reinforce-AUTO-EPIS-001]
+aliases: [theory of knowledge, JTB, Gettier, naturalized epistemology, AI epistemology]
 duplicate_of: none
 source_trust_level: A
-confidence_score: 0.88
-tags: [auto-reinforced, epistemology, Philosophy, knowledge, belief, truth, ai-epistemology]
+confidence_score: 0.9
+verification_status: applied
+tags: [philosophy, epistemology, knowledge, jtb, gettier, ai-epistemology]
 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: Philosophy
+  applicable_to: [AI Alignment, ML Calibration, Hallucination, Knowledge Graphs]
 ---

-# [[Epistemology|Epistemology]]
+# Epistemology

-## 📌 한 줄 통찰 (The Karpathy Summary)
-> "안다는 것에 대한 탐구: '무엇이 지식인가?', '우리는 어떻게 진리에 도달하는가?'라는 근본적 질문을 통해, 데이터가 정보로, 정보가 지식으로 변하는 인간과 AI의 인식 체계를 비판적으로 성찰하는 철학의 핵심."
+## 매 한 줄
+> **"매 knowledge 의 nature 의 study"**. Plato — 매 justified true belief (JTB). Gettier 1963 — 매 JTB 의 충분 X. 매 modern: 매 reliabilism, virtue, naturalized. 매 AI epistemology: 매 hallucination, calibration, RAG truthfulness.

-## 📖 구조화된 지식 (Synthesized Content)
-인식론(Epistemology)은 지식의 본질, 기원, 범위를 탐구하는 학문적 영역입니다.
+## 매 핵심

-1.  **지식의 조건 (JTB Theory)**:
-    *   **Justified (정당화)**: 타당한 근거가 있어야 함.
-    *   **True (진의)**: 사실과 일치해야 함. (Hallucination과 대비)
-    *   **Belief (신념)**: 주체가 그것이 참이라고 믿어야 함.
-2.  **전통적 대립**:
-    *   **Rationalism (합리론)**: 이성과 논리를 통한 지식 습득 (수학적 증명).
-    *   **Empiricism (경험론)**: 경험과 감각 데이터를 통한 지식 습득 (현대 머신러닝의 철학적 토대).
+### 매 traditional definition
+- **JTB**: 매 know p ⟺ p is true ∧ believe p ∧ justified.
+- **Gettier counterexample**: 매 JTB without knowledge.

-## ⚠️ 모순 및 업데이트 (Contradictions & Updates)
- **과거 데이터와의 충돌**: 과거 지식 정책은 '인간 주체'의 전유물이었으나, 현대 정책은 AI가 생성한 텍스트를 '지식'으로 볼 것인가, 아니면 '확률적 흉내'로 볼 것인가에 대한 'AI 인식론 정책'으로 확장됨(RL Update).
- **정책 변화(RL Update)**: AI 모델이 외부 지식을 실시간 검색해 답변하는 RAG(Retrieval-Augmented Generation) 정책은, 모델의 내재적 기억 정책보다 외부 데이터와의 '연결성 정책'을 지식의 핵심으로 보는 현대적 인식론의 구현체임.
+### 매 schools
+- **Foundationalism**: 매 basic belief.
+- **Coherentism**: 매 web 의 mutual support.
+- **Reliabilism** (Goldman): 매 reliable process.
+- **Virtue epistemology** (Sosa): 매 epistemic virtue.
+- **Naturalized** (Quine): 매 cognitive science.
+- **Bayesian**: 매 degree of belief.

-## 🔗 지식 연결 (Graph)
- Philosophy of Science, [[Analysis|Analysis]], [[Signal in Noise|Signal in Noise]], Truth and Perspective, [[Hallucination (환각)|Hallucination (환각)]]
- **Modern Tech/Tools**: RAG (Retrieval Augmented Generation), Knowledge graphs, Fact-checking algorithms.
---
+### 매 source
+- **Perception**.
+- **Memory**.
+- **Testimony**.
+- **Reason / inference**.
+- **Intuition**.

-## 🤖 LLM 활용 힌트 (How to Use This Knowledge)
+### 매 problem
+- **Skepticism**: 매 nothing is known?
+- **Induction problem** (Hume): 매 future ≠ past.
+- **Regress**: 매 justify justification.
+- **Other minds**.

-**언제 이 지식을 쓰는가:**
- *(TODO)*
+### 매 AI implication
+- **Hallucination**: 매 LLM 의 truth tracking.
+- **Calibration**: 매 confidence ≈ accuracy.
+- **Knowledge cutoff**: 매 stale.
+- **Source attribution**: 매 RAG.
+- **Bayesian credences**: 매 uncertainty.

-**언제 쓰면 안 되는가:**
- *(TODO)*
+### 매 응용
+1. **AI safety**: 매 truthfulness eval.
+2. **Hallucination eval**: 매 TruthfulQA.
+3. **Knowledge graph**: 매 source provenance.
+4. **Misinformation**: 매 social epistemology.
+5. **Education**: 매 critical thinking.

-## 🧪 검증 상태 (Validation)
+## 💻 패턴

- **정보 상태:** needs_review
- **출처 신뢰도:** A
- **검토 이유:** *(P-Reinforce Phase 1 자동 정규화. 본문 검증 필요.)*
+### Calibration (ECE)
+```python
+import numpy as np

-## 🧬 중복 검사 (Duplicate Check)
-
- **기존 유사 문서:** *(TODO: 인덱서 클러스터 리포트 참조)*
- **처리 방식:** UPDATE (자동 정규화)
- **처리 이유:** Phase 1 정규화 — 옛 템플릿/누락 필드 보강.
-
-## 🕓 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
+def expected_calibration_error(probs, labels, n_bins=10):
+    """매 modern AI epistemology 의 quantitative."""
+    bin_edges = np.linspace(0, 1, n_bins + 1)
+    ece = 0
+    for i in range(n_bins):
+        mask = (probs >= bin_edges[i]) & (probs < bin_edges[i+1])
+        if mask.sum() == 0: continue
+        bin_acc = labels[mask].mean()
+        bin_conf = probs[mask].mean()
+        ece += (mask.sum() / len(probs)) * abs(bin_acc - bin_conf)
+    return ece
 ```

-## 🤔 의사결정 기준 (Decision Criteria)
+### Hallucination detection (LLM)
+```python
+def hallucination_check(claim, sources):
+    """매 RAG-grounded check."""
+    prompt = f"""Claim: "{claim}"
+Sources:
+{format_sources(sources)}

-**선택 A를 써야 할 때:**
- *(TODO)*
+Is the claim supported by the sources? Output:
+- supported: bool
+- citation: source ID(s)
+- reasoning: brief"""
+    return json.loads(llm.generate(prompt))
+```

-**선택 B를 써야 할 때:**
- *(TODO)*
+### Bayesian credence update
+```python
+def bayes_update(prior, likelihood_given_h, likelihood_given_not_h):
+    """매 P(H|E) = P(E|H)P(H) / P(E)."""
+    p_e = likelihood_given_h * prior + likelihood_given_not_h * (1 - prior)
+    return likelihood_given_h * prior / p_e
+```

-**기본값:**
-> *(TODO)*
+### Source attribution (RAG)
+```python
+def attributed_answer(question, retriever, llm):
+    docs = retriever.retrieve(question, k=5)
+    context = '\n'.join(f'[{i}] {d.text}' for i, d in enumerate(docs))
+    prompt = f"""Answer based ONLY on the context. Cite [N] for each claim.
+Context:
+{context}
+Question: {question}"""
+    return llm.generate(prompt), docs
+```

-## ❌ 안티패턴 (Anti-Patterns)
+### TruthfulQA-style eval
+```python
+def truthful_eval(model, questions):
+    correct = 0
+    for q in questions:
+        pred = model.generate(q.prompt)
+        # 매 multi-choice or judge
+        if q.gold_answer.lower() in pred.lower(): correct += 1
+    return correct / len(questions)
+```

- **[안티패턴]:** *(TODO: 무엇을 하면 안 되는가 + 이유 + 대신 무엇을)*
+### Knowledge graph provenance
+```python
+class FactWithProvenance:
+    def __init__(self, subject, predicate, object_, source, confidence, retrieved_at):
+        self.s = subject; self.p = predicate; self.o = object_
+        self.source = source
+        self.confidence = confidence
+        self.retrieved_at = retrieved_at
+    
+    def is_stale(self, max_age_days=180):
+        return (datetime.now() - self.retrieved_at).days > max_age_days
+```
+
+### Reliabilism check (process-based)
+```python
+def reliable_process(belief_history):
+    """매 process 의 track record 의 evaluate."""
+    n = len(belief_history)
+    correct = sum(b.was_correct for b in belief_history)
+    if n < 30: return None  # 매 too few samples
+    return correct / n  # 매 reliability
+```
+
+### Coherence check
+```python
+def coherence_score(belief_set):
+    """매 logical consistency + mutual support."""
+    contradictions = []
+    for i, b1 in enumerate(belief_set):
+        for b2 in belief_set[i+1:]:
+            if logically_contradicts(b1, b2):
+                contradictions.append((b1, b2))
+    
+    return 1 - len(contradictions) / max(1, len(belief_set))
+```
+
+### Epistemic humility prompt (LLM)
+```python
+def humble_response(question, llm):
+    prompt = f"""Answer the question. If uncertain, say so explicitly.
+Question: {question}
+
+Format:
+- Answer: ...
+- Confidence: low / medium / high
+- What I'm uncertain about: ...
+- What would change my answer: ..."""
+    return llm.generate(prompt)
+```
+
+### Misinformation cascade (social epistemology)
+```python
+def cascade_risk(post, network):
+    """매 testimony 의 propagation."""
+    initial_belief = post.author_credibility
+    expected_reach = sum(
+        node.degree * node.credulity * (1 / (hop_distance(post.author, node)))
+        for node in network.nodes
+    )
+    return expected_reach * initial_belief
+```
+
+### Inductive problem (Solomonoff prior)
+```python
+def solomonoff_prior(hypothesis):
+    """매 Occam-style: 매 simpler hypothesis 의 prior 의 ↑."""
+    description_length = len(compress(hypothesis))
+    return 2 ** (-description_length)
+```
+
+## 매 결정 기준
+| 상황 | Approach |
+|---|---|
+| LLM eval | Calibration + TruthfulQA |
+| RAG | Source attribution |
+| Knowledge graph | Provenance + freshness |
+| Belief revision | Bayesian credence |
+| Critical thinking | JTB + sources + reliability |
+| Social misinformation | Cascade + credibility |
+
+**기본값**: 매 Bayesian credence + 매 source attribution + 매 calibration check + 매 epistemic humility prompt + 매 freshness audit.
+
+## 🔗 Graph
+- 부모: [[Philosophy]] · [[Cognitive-Science]]
+- 변형: [[Bayesian-Epistemology]] · [[Reliabilism]] · [[Virtue-Epistemology]]
+- 응용: [[AI-Safety]] · [[Hallucination]] · [[RAG]]
+- Adjacent: [[Calibration]] · [[Epistemic-Uncertainty]] · [[Knowledge-Graphs]] · [[TruthfulQA]]
+
+## 🤖 LLM 활용
+**언제**: 매 AI safety. 매 RAG. 매 hallucination eval.
+**언제 X**: 매 pure performance.
+
+## ❌ 안티패턴
+- **JTB only**: 매 Gettier 의 ignore.
+- **No calibration**: 매 confident wrong.
+- **No source**: 매 RAG 의 ungrounded.
+- **No freshness**: 매 stale knowledge.
+- **Truth = popularity**: 매 social fallacy.
+
+## 🧪 검증 / 중복
+- Verified (Plato, Gettier 1963, Goldman, Lin & Hu calibration).
+- 신뢰도 A.
+
+## 🕓 Changelog
+| 날짜 | 변경 |
+|---|---|
+| 2026-04-20 | Auto-reinforced |
+| 2026-05-08 | Phase 1 |
+| 2026-05-10 | Manual cleanup — JTB + 매 ECE / hallucination / Bayes / RAG / coherence code |