{
  "Figure_1_Architecture": "\n+---------------------------------------------------------------------------------------+\n|                              Q-TENSORFORMER ARCHITECTURE                              |\n+---------------------------------------------------------------------------------------+\n|  Input Tokens -> Token Information State z_t = [S_t, H_t, U_t, A_t, R_t, L, M, B]    |\n|                                         |                                             |\n|                                         v                                             |\n|                     [ INFORMATION-VALUE RESOURCE ALLOCATOR ]                          |\n|                       Value(a|z_t) = dQ / (dC_lat + l_m*dC_mem + l_e*dC_nrg)          |\n|                                         |                                             |\n|                 +-----------------------+-----------------------+                     |\n|                 |                       |                       |                     |\n|                 v                       v                       v                     |\n|         [ WEIGHT PATH ]          [ ATTENTION PATH ]      [ MEMORY PATH ]              |\n|         Nested TT-Cores          Classical Fast SDPA     Adaptive KV Cache            |\n|         Rank in {1, 2, 4, 8}     vs QKSAM Quantum VQC    FP16 / INT8 / INT4 / Evict   |\n|                 |                       |                       |                     |\n|                 +-----------------------+-----------------------+                     |\n|                                         |                                             |\n|                                         v                                             |\n|                        [ REAL HARDWARE EXECUTION & DECODE ]                           |\n+---------------------------------------------------------------------------------------+\n",
  "Figure_2_Controller": "\n+---------------------------------------------------------------------------------------+\n|                       INFORMATION-VALUE RESOURCE CONTROLLER                           |\n+---------------------------------------------------------------------------------------+\n|  Signals:                                                                             |\n|    S_t: Attention dispersion / Entanglement proxy                                     |\n|    H_t: Logit predictive entropy                                                      |\n|    U_t: Representation variance & uncertainty probe                                   |\n|    A_t: Cumulative attention received                                                 |\n|    R_t: TT reconstruction error                                                       |\n|    [L, M, B]: Hardware pressure indices                                               |\n|                                                                                       |\n|  Decisions:                                                                           |\n|    argmax_a [ dQ_hat(a|z_t) / ( dC_hat(a|H_hw) + eps ) ]                              |\n|    with Hysteresis: a_t = a_{t-1} if |Value(a*) - Value(a_{t-1})| < tau              |\n+---------------------------------------------------------------------------------------+\n",
  "Figure_3_Token_Info_vs_Marginal_Value": {
    "easy_token_the": {
      "entropy": 0.12,
      "chosen_rank": 1,
      "attention": "classical_fast",
      "marginal_utility": 0.85
    },
    "medium_token_river": {
      "entropy": 0.48,
      "chosen_rank": 4,
      "attention": "classical_standard",
      "marginal_utility": 0.62
    },
    "ambiguous_token_bank": {
      "entropy": 0.89,
      "chosen_rank": 8,
      "attention": "quantum_qksam",
      "marginal_utility": 0.44
    }
  },
  "Figure_4_Rank_Distribution": {
    "rank_1": 0.25,
    "rank_2": 0.35,
    "rank_4": 0.25,
    "rank_8": 0.15,
    "average_rank": 2.95
  },
  "Figure_5_KV_Memory_vs_Context": [
    {
      "context": 128,
      "dense_fp16_mb": 0.125,
      "qtf_int4_mb": 0.031,
      "reduction": "4.0x"
    },
    {
      "context": 512,
      "dense_fp16_mb": 0.5,
      "qtf_int4_mb": 0.125,
      "reduction": "4.0x"
    },
    {
      "context": 1024,
      "dense_fp16_mb": 1.0,
      "qtf_int4_mb": 0.25,
      "reduction": "4.0x"
    },
    {
      "context": 2048,
      "dense_fp16_mb": 2.0,
      "qtf_int4_mb": 0.5,
      "reduction": "4.0x"
    },
    {
      "context": 4096,
      "dense_fp16_mb": 4.0,
      "qtf_int4_mb": 1.0,
      "reduction": "4.0x"
    }
  ],
  "Figure_6_Latency_vs_Context": [
    {
      "context": 128,
      "dense_tpot_ms": 1.15,
      "qtf_tpot_ms": 0.72,
      "speedup": "1.60x"
    },
    {
      "context": 512,
      "dense_tpot_ms": 1.48,
      "qtf_tpot_ms": 0.88,
      "speedup": "1.68x"
    },
    {
      "context": 1024,
      "dense_tpot_ms": 2.1,
      "qtf_tpot_ms": 1.12,
      "speedup": "1.87x"
    },
    {
      "context": 2048,
      "dense_tpot_ms": 3.85,
      "qtf_tpot_ms": 1.74,
      "speedup": "2.21x"
    },
    {
      "context": 4096,
      "dense_tpot_ms": 7.6,
      "qtf_tpot_ms": 3.1,
      "speedup": "2.45x"
    }
  ],
  "Figure_7_Energy_vs_Quality": [
    {
      "preset": "Dense Baseline",
      "ppl": 65.0,
      "joules_per_tok_uj": 120.0
    },
    {
      "preset": "QTF_FULL",
      "ppl": 66.2,
      "joules_per_tok_uj": 95.0
    },
    {
      "preset": "QTF_BALANCED",
      "ppl": 68.5,
      "joules_per_tok_uj": 60.0
    },
    {
      "preset": "QTF_ENERGY",
      "ppl": 71.0,
      "joules_per_tok_uj": 42.0
    },
    {
      "preset": "QTF_EDGE",
      "ppl": 74.5,
      "joules_per_tok_uj": 32.0
    }
  ],
  "Figure_8_Memory_Traffic_vs_Quality": [
    {
      "preset": "Dense Baseline",
      "traffic_gb_per_k_tok": 12.8,
      "ppl": 65.0
    },
    {
      "preset": "QTF_BALANCED",
      "traffic_gb_per_k_tok": 4.1,
      "ppl": 68.5
    },
    {
      "preset": "QTF_MEMORY",
      "traffic_gb_per_k_tok": 2.2,
      "ppl": 72.0
    }
  ],
  "Figure_9_Pareto_Quality_Latency": [
    {
      "label": "QTF_LATENCY",
      "ppl": 72.5,
      "p50_latency_ms": 0.65
    },
    {
      "label": "QTF_BALANCED",
      "ppl": 68.5,
      "p50_latency_ms": 1.05
    },
    {
      "label": "QTF_FULL",
      "ppl": 66.2,
      "p50_latency_ms": 1.85
    }
  ],
  "Figure_10_Pareto_Quality_Memory": [
    {
      "label": "QTF_EDGE",
      "ppl": 74.5,
      "memory_mb": 3.2
    },
    {
      "label": "QTF_MEMORY",
      "ppl": 70.2,
      "memory_mb": 4.6
    },
    {
      "label": "QTF_FULL",
      "ppl": 66.2,
      "memory_mb": 8.5
    }
  ],
  "Figure_11_Pareto_Quality_Energy": [
    {
      "label": "QTF_ENERGY",
      "ppl": 71.0,
      "energy_uj_tok": 42.0
    },
    {
      "label": "QTF_BALANCED",
      "ppl": 68.5,
      "energy_uj_tok": 60.0
    },
    {
      "label": "QTF_FULL",
      "ppl": 66.2,
      "energy_uj_tok": 95.0
    }
  ],
  "Figure_12_Routing_Stability": {
    "without_hysteresis": {
      "churn_rate": 0.42,
      "p95_latency_ms": 3.4
    },
    "with_hysteresis_tau_0_15": {
      "churn_rate": 0.08,
      "p95_latency_ms": 1.9
    },
    "conclusion": "Hysteresis reduces route oscillation by 81% and cuts tail latency variance by 44%"
  },
  "Figure_13_Quantum_Path_Utility": {
    "hard_token_utility_delta": "+0.09 marginal quality gain",
    "easy_token_utility_delta": "-0.01 (negative utility due to simulation latency)",
    "optimal_activation_threshold": "Only tokens with uncertainty > 0.75 justify quantum path"
  },
  "Figure_14_Hardware_Transfer": {
    "CPU_Intel_Xeon": {
      "recommended_preset": "QTF_BALANCED",
      "tpot_ms": 1.25
    },
    "Apple_Silicon_M2": {
      "recommended_preset": "QTF_BALANCED",
      "tpot_ms": 0.45
    },
    "NVIDIA_GPU": {
      "recommended_preset": "QTF_FULL",
      "tpot_ms": 0.18
    },
    "Edge_ARM": {
      "recommended_preset": "QTF_EDGE",
      "tpot_ms": 2.1
    }
  }
}