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>

experiments/conditions/__init__.py

@@ -0,0 +1,23 @@
+"""
+Condition implementations for the 5-condition experiment.
+
+C1: Direct generation (baseline)
+C2: Expert-only (no attributes)
+C3: Attribute-only (no experts)
+C4: Full pipeline (attributes + experts)
+C5: Random-perspective (random words instead of experts)
+"""
+
+from .c1_direct import generate_ideas as c1_generate
+from .c2_expert_only import generate_ideas as c2_generate
+from .c3_attribute_only import generate_ideas as c3_generate
+from .c4_full_pipeline import generate_ideas as c4_generate
+from .c5_random_perspective import generate_ideas as c5_generate
+
+__all__ = [
+    "c1_generate",
+    "c2_generate",
+    "c3_generate",
+    "c4_generate",
+    "c5_generate",
+]