feat: Add experiments framework and novelty-driven agent loop

- Add complete experiments directory with pilot study infrastructure
  - 5 experimental conditions (direct, expert-only, attribute-only, full-pipeline, random-perspective)
  - Human assessment tool with React frontend and FastAPI backend
  - AUT flexibility analysis with jump signal detection
  - Result visualization and metrics computation

- Add novelty-driven agent loop module (experiments/novelty_loop/)
  - NoveltyDrivenTaskAgent with expert perspective perturbation
  - Three termination strategies: breakthrough, exhaust, coverage
  - Interactive CLI demo with colored output
  - Embedding-based novelty scoring

- Add DDC knowledge domain classification data (en/zh)
- Add CLAUDE.md project documentation
- Update research report with experiment findings

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

backend/app/services/embedding_service.py

@@ -26,7 +26,7 @@ class EmbeddingService:
 
     def __init__(self):
         self.base_url = settings.ollama_base_url
-        self.default_model = "nomic-embed-text"  # Ollama 預設的 embedding 模型
+        self.default_model = "qwen3-embedding:4b"  # Qwen3 embedding model for better semantic understanding
         self.client = httpx.AsyncClient(timeout=120.0)
 
     async def get_embedding(self, text: str, model: Optional[str] = None) -> List[float]: