feat: Harden research system with hierarchical KV, phase profiling, matched budgets, and counterfactual validation

feat(benchmarks): Add comprehensive baseline comparison system with 14 architectures, 17 metrics, Pareto frontiers, and provenance tags

Implement top-tier research features: PID Dual Controller, GQA, Roofline Analyzer, Early-Exit, Meyer-Wallach Entanglement, and Interactive Visual Dashboard

Transform Q-TensorFormer into an Information-Value Adaptive Resource Allocation Architecture

Upload tests/test_v4.py

v3.0.0: Tests