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/assessment/stop.sh

@@ -0,0 +1,13 @@
+#!/bin/bash
+
+# Stop the assessment system
+
+echo "Stopping assessment system..."
+
+# Kill backend (uvicorn on port 8002)
+pkill -f "uvicorn app:app.*8002" 2>/dev/null && echo "Backend stopped" || echo "Backend not running"
+
+# Kill frontend (vite on port 5174)
+pkill -f "vite.*5174" 2>/dev/null && echo "Frontend stopped" || echo "Frontend not running"
+
+echo "Done"