2nd/10_Wiki/Topics/Other/Hypostatic-Abstraction.md

id, title, category, status, canonical_id, aliases, duplicate_of, source_trust_level, confidence_score, verification_status, tags, raw_sources, last_reinforced, github_commit, tech_stack

id	title	category	status	canonical_id	aliases	duplicate_of	source_trust_level	confidence_score	verification_status	tags	raw_sources	last_reinforced	github_commit	tech_stack
wiki-2026-0508-hypostatic-abstraction	Hypostatic Abstraction	10_Wiki/Topics	verified	self	Hypostasis Reification Subjectal Abstraction	none	A	0.9	applied	logic semiotics philosophy peirce abstraction		2026-05-10	pending	language framework en peircean-logic

Hypostatic Abstraction

매 한 줄

"매 predicate 의 subject 으로 transformation — 'X is honest' → 'X has honesty'". 매 Peirce (1903) 의 logical operation — 매 first-order property 의 second-order entity 의 conversion. 매 2026 의 ontology engineering, semantic web RDF, type theory 의 reification, LLM 의 conceptual blending 의 modern instances.

매 핵심

매 정의 (Peirce)

• Operation: 매 "p(x)" → "x has property P" — 매 P 의 noun-form entity.
• 예:
  • "honey is sweet" → "honey has sweetness"
  • "the function returns int" → "the function has return-type int"
  • "atom is heavy" → "atom has mass"

매 distinction from related

• vs. prescissive abstraction: 매 prescission = attention 의 isolation (color from shape) — 매 hypostasis = entity 의 creation.
• vs. reification fallacy: 매 hypostasis = legitimate logical move; reification fallacy = mistakenly treating abstraction as concrete causal agent.
• vs. nominalization (linguistics): 매 grammatical analog — "destroy" → "destruction".

매 utility

• Reasoning vehicle: 매 abstract entity 의 quantification 가능 ("there exists a virtue that...").
• Theory building: 매 mass, energy, information 의 hypostatic origin.
• Ontology: 매 OWL class 의 RDF resource 화.

매 응용

1. Math: "function f returns int" → "f has signature ℤ→ℤ".
2. Physics: "object is hot" → "object has temperature T".
3. Law: "act is criminal" → "act has criminality" (mens rea 분석).
4. Programming: type inference 의 reification.
5. Knowledge graph: predicate → resource.

💻 패턴

Predicate to RDF resource (hypostatize)

from rdflib import Graph, URIRef, Literal, RDF
EX = "http://ex.org/"
g = Graph()

# "Alice is honest" → "Alice has honesty(value=true)"
g.add((URIRef(EX + "Alice"), URIRef(EX + "hasVirtue"), URIRef(EX + "Honesty")))
g.add((URIRef(EX + "Honesty"), RDF.type, URIRef(EX + "Virtue")))

Type-level reification (TypeScript)

// Before: "f returns number"
function f(x: number): number { return x * 2; }

// Hypostatized: extract the type
type SignatureOf<F> = F extends (...args: infer A) => infer R ? { args: A; ret: R } : never;
type FSig = SignatureOf<typeof f>;  // { args: [number]; ret: number }

Predicate → entity (Peircean diagram)

from dataclasses import dataclass

@dataclass
class HypostaticAbstraction:
    original_predicate: str        # "X is red"
    subject_var: str               # "X"
    abstracted_entity: str         # "redness"
    relation: str                  # "has"

    def express(self, subject: str) -> tuple[str, str]:
        return (
            f"{subject} {self.original_predicate.split(' is ')[1]}",   # original
            f"{subject} {self.relation} {self.abstracted_entity}",    # hypostatized
        )

h = HypostaticAbstraction("X is red", "X", "redness", "has")
print(h.express("the apple"))  # ("the apple red", "the apple has redness")

Detect reification fallacy

def reification_check(claim: str, entity: str) -> bool:
    """Flag if abstract entity assigned causal agency."""
    causal_verbs = {"caused", "did", "decided", "wanted", "forced"}
    return any(f"{entity} {v}" in claim.lower() for v in causal_verbs)

reification_check("Inflation caused the recession", "inflation")  # True (suspect)

Knowledge graph property reification

# Direct edge: <Alice> <employs> <Bob>
# Reified (allow metadata on the edge):
:edge1 a rdf:Statement ;
       rdf:subject :Alice ;
       rdf:predicate :employs ;
       rdf:object :Bob ;
       :startDate "2024-01-15" ;
       :salary 90000 .

LLM hypostatization assistant

from anthropic import Anthropic
client = Anthropic()

def hypostatize(claim: str) -> str:
    return client.messages.create(
        model="claude-opus-4-7",
        max_tokens=500,
        system=("Apply Peircean hypostatic abstraction: convert the predicate "
                "into a subject-form entity. Then list questions you can now "
                "ask of that entity."),
        messages=[{"role": "user", "content": claim}],
    ).content[0].text

매 결정 기준

상황	When to hypostatize
Theory building, want to quantify property	yes
Need ontology / KG class	yes
Reasoning about types, signatures	yes
Granting causal agency to abstraction	NO (reification fallacy)
Eliminate redundancy in logic	yes (factor predicate)

기본값: 매 hypostatize 의 explicit + reversible. 매 abstract entity 의 causal agent 화 X.

🔗 Graph

• 변형: Reification
• 응용: Ontology Engineering · Type Theory
• Adjacent: Conceptual Blending · Knowledge Graph

🤖 LLM 활용

언제: 매 ontology class 의 candidate 의 surface, 매 vague claim 의 quantifiable property 의 reformulation, 매 nominalization 의 unwind. 언제 X: 매 reification fallacy 의 detection 의 final arbiter — 매 domain context 의 human review.

❌ 안티패턴

• Reification fallacy: 매 abstract entity 의 causal agent 의 treatment ("inflation decided to rise"). 매 actual mechanism 의 obscure.
• Hypostatic explosion: 매 every adjective 의 entity 화 — 매 ontology bloat.
• Lost reversibility: 매 hypostatized form 만 의 retain — 매 original predicate 의 access 어려움.
• Confusing with prescission: 매 attention isolation 의 entity creation 의 동일시.

🧪 검증 / 중복

• Verified (Peirce CP 4.235, 5.534; Stanford Encyclopedia of Philosophy "Peirce's Logic"; Sowa "Knowledge Representation" 2000).
• 신뢰도 A.

🕓 Changelog

날짜	변경
2026-05-08	Phase 1
2026-05-10	Manual cleanup — Peircean operation, RDF/type reification, fallacy distinction 추가