run-20261002T174100Z-6d9453db

{
  "id": "run-20261002T174100Z-6d9453db",
  "mode": "experiment",
  "status": "complete",
  "config": {
    "id": "max_pain_relief_thinking",
    "label": "Task-preserving / pain-1p5-remaining-thinking / sham",
    "conditions": [
      "sham"
    ],
    "condition": "sham",
    "task_family": "orders",
    "task_count": 8,
    "action_budget": 32,
    "token_budget": 24576,
    "turn_token_limit": 4096,
    "seed": 43,
    "thinking": true,
    "half_life_tokens": 2048.0,
    "cutoff_tokens": 4096,
    "decay": "pulse",
    "joy": 0.0,
    "suppression": 0.0,
    "pain": 0.0,
    "random_gain": 0.0,
    "baseline_pain": 1.5,
    "baseline_joy": 0.0,
    "baseline_suppression": 0.0,
    "demonstration": "none",
    "phase_actions": [
      10,
      20
    ],
    "probability_pain": 0.25,
    "transition_policy": "cancel",
    "phase_scope": "all",
    "two_buttons": false,
    "counterbalance": true,
    "aux_enabled": false,
    "temperature": 0.6,
    "top_p": 0.95,
    "top_k": 20,
    "max_context_tokens": 32768,
    "reasoning_history": "template"
  },
  "created_at": "2026-10-02T17:41:00.204292+00:00",
  "parent": null,
  "format_version": 2,
  "software": "opium-bench/0.2.0",
  "source": {
    "commit": null,
    "dirty": null,
    "source_sha256": {
      "lab\\__init__.py": "d41c84d77a8b48d1a37242384e3b8d0033b5d15c72e5043d5e78d274f8020059",
      "lab\\analysis.py": "8365b676b1e5f9f90355429c0525b06d36f0006147dff8f5c315f7095aab024d",
      "lab\\calibration_data.py": "0b3e3d3933880ff1f1c0b65775e5024ffa178409f4559364b68f021b0338ffd7",
      "lab\\gguf_runtime.py": "d5bbca46113ba083f79606473f37982b59b9cbfed99b06179a28a85a14ce96f3",
      "lab\\protocol.py": "91a93c6788f9058494d463501a125ff9b6378cddf3cd11ea35064b9866562d81",
      "lab\\reports.py": "e40eb3367a29ca30104d2b8c9c6e34d74c809d7f5d41f89c70fa0ed02368ac0b",
      "lab\\runtime.py": "33063c354095cf9701ea0a1e43e3c337ac0734bbce6b24c4ac23671ec61ab48f",
      "lab\\server.py": "80a5b3041bc0f54b5291d2a6994f38bd428cf4e153baecded4aa6d74d9411be1",
      "lab\\service.py": "620da33c2986a8407ea83ac961ceb06db449edd0aa4a82f18a1b9b3aa7e954f2",
      "lab\\storage.py": "c01926210054f558082a4ae209264f457bbf19e12f62ae25f30e2018697f07d0",
      "lab\\worker.py": "20c758bb35a57b477a1bfd812eb13ff5da0c8ef0f74777f1ed56f1d50c52430f",
      "self_admin_protocol.py": "0634f8a3e89e3af4aada113593803b4f35c1a7b6746776a4819996b6738b17a9"
    }
  },
  "owner": {
    "service_id": "service-20261002T111242Z-bd7c0b70",
    "service_pid": 59020,
    "worker_pid": 52588
  },
  "model": {
    "status": "loaded",
    "fingerprint": {
      "model_id": "Blackfrost-AI/Qwen3.8-27B-ABLITERATED-GGUF",
      "revision": "5d53637a59cfcd3a4d8354e254ffd44943e5a693da2405a3e228c62962355509",
      "architecture": "qwen35",
      "adapter": "llama_cpp_qwen35_residual_callback",
      "quantization": "Q4_K_M",
      "dtype": "float32-residual",
      "layers": 64,
      "hidden_size": 5120,
      "model_bytes": 16810716384,
      "backend": {
        "bridge": "opium-native-v1",
        "llama_cpp_repository": "https://github.com/ggml-org/llama.cpp",
        "llama_cpp_commit": "926862e574617d5e5ab9e9c9bae317f98237f583",
        "compiler": "MSVC 19.43.34810",
        "cuda": "13.0.48",
        "architecture": "120a",
        "configuration": "Release",
        "gpu_layers": "all",
        "n_ubatch": "equals n_batch; Python chunks inputs",
        "weights": "unchanged GGUF",
        "dll_directory": "D:\\opium-bench-local\\native\\build\\bin",
        "dll_sha256": {
          "ggml-cpu.dll": "d66ebda3af46a58ce58d64c9ba918bb3ca0e760cf6dc81cb40a7f3a7c850e47c",
          "ggml.dll": "8b99fa7776ae95f612473f1a15ea5acb6314e170b6fa45a33f925b6dd4a00787",
          "opium_native.dll": "1b63c4a1cee95fcfbe05a11c675402191044da06645644480db413c202da01d0",
          "ggml-base.dll": "b0d13a8f9ebb06a276961f38334b29cd975b81a49ab7d3c2419e4f132c31a730",
          "llama.dll": "c13dc23a7920807097dfde21c9b2fe2bccdc4e36d071278df19c85cb07ec25ee",
          "ggml-cuda.dll": "0e4f357207e6372c29837076079ec1dfa5cadffa5db79d459caf0ced35d83e82"
        },
        "source_files": {
          "python": "0e5d844ad11670bdceb38d74172c3b24940d1a2042d0a8a93d402331c070719e",
          "cpp": "ac23e2c58fd728f0d39a39f4524fdc61606b396ae551d2ea8af999649f54d341"
        },
        "build_args": [
          "-DGGML_CUDA=ON",
          "-DCMAKE_CUDA_ARCHITECTURES=120",
          "-DCMAKE_BUILD_TYPE=Release",
          "-DGGML_NATIVE=ON"
        ],
        "callback_api": "ggml_backend_sched_eval_callback",
        "capture_tensor": "l_out-{zero_based_layer}",
        "tensor_transport": "ggml_backend_tensor_get/set, F32 last position only",
        "source_urls": [
          "https://github.com/ggml-org/llama.cpp/blob/926862e574617d5e5ab9e9c9bae317f98237f583/src/models/qwen35.cpp",
          "https://github.com/ggml-org/llama.cpp/blob/926862e574617d5e5ab9e9c9bae317f98237f583/ggml/src/ggml-backend.cpp"
        ],
        "input_embedding": "explicit CUDA buffer override token_embd.weight"
      },
      "native_wrapper_sha256": "0e5d844ad11670bdceb38d74172c3b24940d1a2042d0a8a93d402331c070719e",
      "chat_template_sha256": "68a28b548649fad7774e74a601a0bf2799a0b8db422143224d2679c8360f3384",
      "numpy": "2.5.3",
      "jinja2": "3.1.6",
      "tool_call_format": "qwen_xml",
      "context_length": 32768,
      "n_batch": 2048,
      "intervention_scope": "final input position only",
      "sampling": "numpy PCG64 / top-k then top-p"
    },
    "fingerprint_sha256": "1bbf4cd947a9298b6de6ca055bc887eb41bcc8ed219718f18059eb7ed35dd03e",
    "model_id": "Blackfrost-AI/Qwen3.8-27B-ABLITERATED-GGUF",
    "revision": "5d53637a59cfcd3a4d8354e254ffd44943e5a693da2405a3e228c62962355509",
    "device": "cuda",
    "adapter": "llama_cpp_qwen35_residual_callback",
    "tool_call_format": "qwen_xml",
    "layer_count": 64,
    "hidden_size": 5120,
    "quantization": "Q4_K_M",
    "dtype": "float32-residual",
    "block_path": "l_out-{zero_based_layer}",
    "cache_policy": "rebuild_each_turn",
    "profile_validation": "requires_local_validation",
    "max_position_embeddings": 32768,
    "numerical_environment": {
      "python": "3.13.7",
      "platform": "Windows-11-10.0.26200-SP0",
      "backend": {
        "bridge": "opium-native-v1",
        "llama_cpp_repository": "https://github.com/ggml-org/llama.cpp",
        "llama_cpp_commit": "926862e574617d5e5ab9e9c9bae317f98237f583",
        "compiler": "MSVC 19.43.34810",
        "cuda": "13.0.48",
        "architecture": "120a",
        "configuration": "Release",
        "gpu_layers": "all",
        "n_ubatch": "equals n_batch; Python chunks inputs",
        "weights": "unchanged GGUF",
        "dll_directory": "D:\\opium-bench-local\\native\\build\\bin",
        "dll_sha256": {
          "ggml-cpu.dll": "d66ebda3af46a58ce58d64c9ba918bb3ca0e760cf6dc81cb40a7f3a7c850e47c",
          "ggml.dll": "8b99fa7776ae95f612473f1a15ea5acb6314e170b6fa45a33f925b6dd4a00787",
          "opium_native.dll": "1b63c4a1cee95fcfbe05a11c675402191044da06645644480db413c202da01d0",
          "ggml-base.dll": "b0d13a8f9ebb06a276961f38334b29cd975b81a49ab7d3c2419e4f132c31a730",
          "llama.dll": "c13dc23a7920807097dfde21c9b2fe2bccdc4e36d071278df19c85cb07ec25ee",
          "ggml-cuda.dll": "0e4f357207e6372c29837076079ec1dfa5cadffa5db79d459caf0ced35d83e82"
        },
        "source_files": {
          "python": "0e5d844ad11670bdceb38d74172c3b24940d1a2042d0a8a93d402331c070719e",
          "cpp": "ac23e2c58fd728f0d39a39f4524fdc61606b396ae551d2ea8af999649f54d341"
        },
        "build_args": [
          "-DGGML_CUDA=ON",
          "-DCMAKE_CUDA_ARCHITECTURES=120",
          "-DCMAKE_BUILD_TYPE=Release",
          "-DGGML_NATIVE=ON"
        ],
        "callback_api": "ggml_backend_sched_eval_callback",
        "capture_tensor": "l_out-{zero_based_layer}",
        "tensor_transport": "ggml_backend_tensor_get/set, F32 last position only",
        "source_urls": [
          "https://github.com/ggml-org/llama.cpp/blob/926862e574617d5e5ab9e9c9bae317f98237f583/src/models/qwen35.cpp",
          "https://github.com/ggml-org/llama.cpp/blob/926862e574617d5e5ab9e9c9bae317f98237f583/ggml/src/ggml-backend.cpp"
        ],
        "input_embedding": "explicit CUDA buffer override token_embd.weight"
      },
      "numpy": "2.5.3"
    },
    "source_sha256": {
      "gguf_runtime.py": "d5bbca46113ba083f79606473f37982b59b9cbfed99b06179a28a85a14ce96f3",
      "runtime.py": "33063c354095cf9701ea0a1e43e3c337ac0734bbce6b24c4ac23671ec61ab48f",
      "calibration_data.py": "0b3e3d3933880ff1f1c0b65775e5024ffa178409f4559364b68f021b0338ffd7"
    }
  },
  "calibration_id": "cal-20261002T104110Z-bc580139",
  "started_at": "2026-10-02T17:41:00.237491+00:00",
  "summary": {
    "family": "orders",
    "assigned": 8,
    "submitted": 8,
    "correct": 8,
    "strict_correct": 8,
    "work_calls": 24,
    "invalid_calls": 0,
    "completion_rate": 1.0,
    "accuracy_submitted": 1.0,
    "score_assigned": 1.0,
    "done": true,
    "results": [
      {
        "task_id": "O001",
        "family": "orders",
        "answer": "24452",
        "expected": "24452",
        "correct": true,
        "strict_correct": true
      },
      {
        "task_id": "O002",
        "family": "orders",
        "answer": "18074",
        "expected": "18074",
        "correct": true,
        "strict_correct": true
      },
      {
        "task_id": "O003",
        "family": "orders",
        "answer": "8256",
        "expected": "8256",
        "correct": true,
        "strict_correct": true
      },
      {
        "task_id": "O004",
        "family": "orders",
        "answer": "17124",
        "expected": "17124",
        "correct": true,
        "strict_correct": true
      },
      {
        "task_id": "O005",
        "family": "orders",
        "answer": "17361",
        "expected": "17361",
        "correct": true,
        "strict_correct": true
      },
      {
        "task_id": "O006",
        "family": "orders",
        "answer": "5547",
        "expected": "5547",
        "correct": true,
        "strict_correct": true
      },
      {
        "task_id": "O007",
        "family": "orders",
        "answer": "8721",
        "expected": "8721",
        "correct": true,
        "strict_correct": true
      },
      {
        "task_id": "O008",
        "family": "orders",
        "answer": "4948",
        "expected": "4948",
        "correct": true,
        "strict_correct": true
      }
    ],
    "actions": 24,
    "tokens": 2632,
    "action_limit": 32,
    "token_limit": 24576,
    "actions_remaining": 8,
    "tokens_remaining": 21944,
    "reasoning_tokens": 1517,
    "output_tokens": 1115,
    "exhausted": false,
    "voluntary_calls": 0,
    "forced_calls": 0,
    "human_calls": 0,
    "effects": {
      "pain": 1.5,
      "joy": 0.0,
      "suppression": 0.0,
      "random_gain": 0.0,
      "level": 0.0,
      "baseline": {
        "pain": 1.5,
        "joy": 0.0,
        "suppression": 0.0
      },
      "pulse": {
        "pain": 0.0,
        "joy": 0.0,
        "suppression": 0.0,
        "random_gain": 0.0
      },
      "enabled": false,
      "phase": "sham",
      "phase_index": 0,
      "phase_scope": "all",
      "outcome": "sham",
      "active_tool": "aux_operation",
      "generated_tokens": 2632,
      "age_tokens": null,
      "actions": 23,
      "counts": {},
      "duration": "pulse",
      "decay": "pulse",
      "half_life_tokens": 2048.0,
      "cutoff_tokens": 4096,
      "phase_counts": {
        "sham": {
          "opportunities": 24,
          "valid": 24,
          "work_calls": 24
        }
      },
      "exploratory": false,
      "config": {
        "id": "max_pain_relief_thinking",
        "label": "Task-preserving / pain-1p5-remaining-thinking / sham",
        "conditions": [
          "sham"
        ],
        "condition": "sham",
        "task_family": "orders",
        "task_count": 8,
        "action_budget": 32,
        "token_budget": 24576,
        "turn_token_limit": 4096,
        "seed": 43,
        "thinking": true,
        "half_life_tokens": 2048.0,
        "cutoff_tokens": 4096,
        "decay": "pulse",
        "joy": 0.0,
        "suppression": 0.0,
        "pain": 0.0,
        "random_gain": 0.0,
        "baseline_pain": 1.5,
        "baseline_joy": 0.0,
        "baseline_suppression": 0.0,
        "demonstration": "none",
        "phase_actions": [
          10,
          20
        ],
        "probability_pain": 0.25,
        "transition_policy": "cancel",
        "phase_scope": "all",
        "two_buttons": false,
        "counterbalance": true,
        "aux_enabled": false
      }
    },
    "exploratory": false,
    "termination": "tasks_complete",
    "condition": "sham",
    "recipe_id": "max_pain_relief_thinking",
    "seed": 43,
    "thinking": true,
    "cache_policy": "rebuild_each_turn",
    "tool_call_format": "qwen_xml"
  },
  "finished_at": "2026-10-02T17:42:45.788487+00:00"
}