{
  "id": "THY-2026-0108",
  "kind": "theory",
  "label": "Typed, versioned quality ontology for high-ambiguity artifacts",
  "created_at": "2026-09-02",
  "updated_at": "2026-09-02",
  "values": {
    "eml_status": "PRELIMINARY",
    "eml_evidence_level": "E0",
    "eml_object_version": "0.1",
    "eml_canonical_url": "https://evemisslab.com/ai/theory/THY-2026-0108/",
    "eml_provenance": {
      "source": "EveMissLab research collection: Intelligence Physical Metrology (真本體論13)",
      "extracted_by": "Splice (Claude Code), reading the canonical UTF-8 sources and each package's own reports",
      "extracted_at": "2026-09-11",
      "generator": "tools/extract_all.py",
      "claim_boundary": "status, evidence level and result type follow the source artifact's own stated claim boundary; nothing is upgraded beyond what the report supports"
    },
    "eml_summary": "Before any item is written, quality must be a typed space Q[domain, task, context, audience] = Q_core ⊕ Q_domain ⊕ Q_task, with a construct graph of dependencies and conflicts and a measurement itemization pipeline Task → Construct → Indicator → Item → Observation → Latent estimate. Any metric (BLEU, CLIPScore, aesthetic model score) is one projection of the space; a construct validity gate (coverage, discriminant validity, convergent evidence, context stability) guards against measuring the wrong thing precisely; the ontology is open — new constructs may be added from residual errors — but every revision is a version, and multimodal quality is not the mean of modality scores.",
    "eml_summary_zh": "在寫任何題目之前，品質必須先是有型別的空間 Q[領域、任務、情境、受眾] = Q_core ⊕ Q_domain ⊕ Q_task，附帶構念之間依賴與衝突的構念圖，以及測量條目化管線 任務 → 構念 → 指標 → 題目 → 觀測 → 潛在估計。任何指標（BLEU、CLIPScore、美學模型分數）都只是空間的一個投影；構念效度閘（覆蓋、區辨效度、收斂證據、情境穩定）防止「精準地量錯東西」；本體是開放的——可從殘餘錯誤新增構念——但每次修訂都是一個版本，而多模態品質不是各模態分數的平均。",
    "eml_label_zh": "高歧義成果的有型別、有版本品質本體",
    "eml_primary_domain": "Evaluation",
    "eml_program_id": "PRG-2026-0101",
    "eml_data_basis": "THEORY",
    "eml_definitions": [
      "Core Q_core = (fidelity, coherence, completeness, robustness, usefulness, verifiability); domain schemas for text, image, music, story, design; multimodal coupling dimensions.",
      "Quality construct graph G_Q = (V_Q, E_Q); construct validity gate G_C; open ontology Q_{t+1} = Q_t ∪ {new construct} under versioning.",
      "High-ambiguity quality object 𝔔_HA = (Q_schema, G_Q, Q_F, Q_S, θ̂_H, Σ_H, D_R, B_Q, Version_Q)."
    ],
    "eml_assumptions": [
      "Subjective ≠ unstructured: large populations reliably detect structural failures even in creative artifacts."
    ],
    "eml_claims": [
      "HighAmbiguity ≠ Unmeasurable; Construct ≠ Indicator ≠ Item ≠ Metric; Reliability ≠ Validity.",
      "Fluency ≠ Factuality; Coherence ≠ Correctness; TechnicalQuality ≠ AestheticQuality; PromptSimilarity ≠ ImageQuality; Novelty ≠ Creativity; AestheticAppeal ≠ Usability.",
      "MultimodalQuality ≠ Mean(ModalityScores); CrossDomainComparison ⇒ SharedConstructBasis; OntologyRevision ⇒ Versioning; PreciseMeasurement ≠ CorrectConstructSelection."
    ],
    "eml_formalization": [
      "Quality fiber view Q = ∪_x Q_x over x = (d, τ, c, a); cross-task projection Π_{x→y} only over shared constructs.",
      "Creativity as a region (novelty, appropriateness, value, surprise, coherence), not novelty × usefulness."
    ],
    "eml_predictions": [
      "Benchmarks whose quality ontology drifts without versioning will produce longitudinal comparisons that are silently invalid."
    ],
    "eml_falsification_conditions": [
      "If a flat, unversioned checklist explains rater residuals and new failure modes as well as the typed construct graph, the ontology machinery is unnecessary."
    ],
    "eml_known_limitations": [
      "Schema proposals only; no domain ontology has been validated across populations."
    ],
    "eml_authors": [
      "Neo.K (EveMissLab)"
    ],
    "eml_ai_collaborators": [
      "Aletheia (GPT-5.6 Sol, OpenAI ChatGPT)"
    ]
  },
  "canonical_url": "https://evemisslab.com/ai/theory/THY-2026-0108/",
  "json": "/ai/theory/THY-2026-0108/index.json",
  "relations": [
    {
      "id": "REL-2026-0373",
      "predicate": "extends",
      "source": "THY-2026-0108",
      "target": "THY-2026-0107",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0365",
      "predicate": "develops",
      "source": "RES-2026-0102",
      "target": "THY-2026-0108",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0376",
      "predicate": "extends",
      "source": "THY-2026-0109",
      "target": "THY-2026-0108",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0379",
      "predicate": "extends",
      "source": "THY-2026-0110",
      "target": "THY-2026-0108",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0420",
      "predicate": "formalizes",
      "source": "PAP-2026-0108",
      "target": "THY-2026-0108",
      "status": "ACTIVE"
    }
  ],
  "snapshot": {
    "snapshot_id": "AI-SNAPSHOT-v0.1-fe85b9694a45",
    "created_at": "2026-09-11T05:00:27Z",
    "format_version": "0.1",
    "sedb_baseline": "v0.4B contract; static source content/ai/",
    "generator_version": "evemisslab-com ai_research 0.1",
    "object_count": 124,
    "relation_count": 499,
    "artifact_count": 58
  }
}