{
  "schema_version": 1,
  "experiment_id": "7-2",
  "title": "Traditional RL versus Kimi K3 in the same treasure-hunt environment",
  "campaign_started_at": "2026-07-29T17:17:06.773342+00:00",
  "evidence_finalized_at": "2026-07-29T17:26:40.328179+00:00",
  "git_revision": "4a7f37cf278bd15948c409f14533017c4c7fbc29",
  "runtime": {
    "python": "3.11.4 (main, Jul  5 2023, 08:40:20) [Clang 14.0.6 ]",
    "platform": "macOS-26.3-arm64-arm-64bit"
  },
  "execution_manifest": {
    "experiment_id": "7-2",
    "campaign_started_at_local": "2026-07-30T01:17:04+08:00",
    "command": [
      "python",
      "run_experiment_7_2.py"
    ],
    "execution_source_sha256": {
      "game_environment.py": "4af75d35cd609e1ee4d163c37c637c3f559365eb47eda1e562e805a6c62f3105",
      "rl_agent.py": "3821f04679ad4c9d021e3e0557b39b94d43348ef63192f05f077be79ff3442a0",
      "llm_agent.py": "28579c10cc4ba71eb3ac232e1538172dad78d2ca9733d24fc7bf63fb26385783",
      "experiment.py": "c8e2890271ba12583d955b1d418d5b171b1becdbcd27b1614d790ac81dee6d96",
      "run_experiment_7_2.py": "9e988e96fb7d9bc5b16d15a30782e78db14ab3ea10d702fdb7aed3e992b870a1"
    },
    "post_run_status": "The campaign and all raw artifacts completed; evidence.json serialization then failed because numpy.bool_ is not handled by the standard JSON encoder. No API rerun is required.",
    "captured_before_source_repair": true
  },
  "backend": {
    "provider": "moonshot",
    "base_url": "https://api.moonshot.cn/v1",
    "model": "kimi-k3",
    "using_openrouter": false
  },
  "provider_response_models": [
    "kimi-k3"
  ],
  "usage": {
    "successful_api_calls": 17,
    "api_attempts": 17,
    "total_tokens": 28242,
    "provider_cost": null,
    "provider_cost_note": "The provider exposed token usage but no authoritative billed cost; unknown is not zero."
  },
  "q_learning": {
    "training_episodes": 10000,
    "training_time_seconds": 2.124420166015625,
    "training_victory_rate": 0.451,
    "evaluation_episodes": 100,
    "evaluation_victory_rate": 1.0,
    "evaluation_average_steps": 12.0,
    "q_table_states": 142,
    "learning_curve": [
      {
        "episode": 1000,
        "victory_rate": 0.003,
        "q_table_size": 123,
        "epsilon": 0.606454822840097
      },
      {
        "episode": 2000,
        "victory_rate": 0.0,
        "q_table_size": 123,
        "epsilon": 0.3677874521460121
      },
      {
        "episode": 3000,
        "victory_rate": 0.001,
        "q_table_size": 126,
        "epsilon": 0.22304647413401948
      },
      {
        "episode": 4000,
        "victory_rate": 0.001,
        "q_table_size": 127,
        "epsilon": 0.13526760995605422
      },
      {
        "episode": 5000,
        "victory_rate": 0.001,
        "q_table_size": 128,
        "epsilon": 0.1
      },
      {
        "episode": 6000,
        "victory_rate": 0.559,
        "q_table_size": 137,
        "epsilon": 0.1
      },
      {
        "episode": 7000,
        "victory_rate": 0.97,
        "q_table_size": 138,
        "epsilon": 0.1
      },
      {
        "episode": 8000,
        "victory_rate": 0.996,
        "q_table_size": 138,
        "epsilon": 0.1
      },
      {
        "episode": 9000,
        "victory_rate": 0.998,
        "q_table_size": 139,
        "epsilon": 0.1
      },
      {
        "episode": 10000,
        "victory_rate": 0.981,
        "q_table_size": 142,
        "epsilon": 0.1
      }
    ]
  },
  "k3_first_attempt": {
    "victory": true,
    "steps": 17,
    "reward": 241.5,
    "api_calls": 17,
    "actions": [
      "take rusty sword",
      "go north",
      "look around",
      "use rusty sword",
      "go south",
      "go east",
      "take red key",
      "take magic crystal",
      "try crafting",
      "go west",
      "go north",
      "use red key",
      "go north",
      "attack with silver sword",
      "use silver sword",
      "go east",
      "take dragon's treasure"
    ]
  },
  "protocol_gates": {
    "same_deterministic_environment": true,
    "q_learning_10000_training_episodes": true,
    "q_learning_100_evaluation_episodes": true,
    "q_learning_reached_full_evaluation_success": true,
    "one_kimi_first_attempt_recorded": true,
    "direct_official_moonshot_kimi_k3": true,
    "one_real_response_per_first_attempt_action": true,
    "provider_response_ids_retained": true,
    "provider_response_content_retained": true,
    "all_provider_responses_finished_normally": true,
    "zero_api_errors": true,
    "zero_fallback_actions": true
  },
  "acceptance_complete": true,
  "manuscript_observation_matches": {
    "first_attempt_victory": true,
    "exactly_18_steps": false,
    "q_learning_11_step_greedy_solution": false
  },
  "result_mismatches": [
    "Kimi K3 used 17 rather than the historical 18 steps",
    "Q-learning greedy evaluation averaged 12 rather than 11 steps"
  ],
  "interpretation": "Protocol acceptance is independent of whether stochastic model behavior reproduces historical point estimates.",
  "artifacts": {
    "experiment_results": "experiment_results.json",
    "raw_llm_calls_and_trajectories": "llm_experiences.json",
    "q_learning_checkpoint": "rl_agent.pkl",
    "execution_manifest": "execution_manifest.json"
  },
  "artifact_sha256": {
    "experiment_results.json": "63b30603836b8dce4da8b3748159f727b7d66d362be37a7d5eb75d778e1600d1",
    "llm_experiences.json": "535a5977cab93a151f977c45f91f4582989d7d3710ca7e460017c5bb64a581d9",
    "rl_agent.pkl": "75ee5ff04f3100480fd8f62005b004ec395528110d7c2dd273aefad3e8ab3ed5",
    "execution_manifest.json": "29da01f59cfa41464345f9a292352359d8153a13ed623b58d4b93959c020fda6"
  },
  "postprocessor_source_sha256": {
    "run_experiment_7_2.py": "f68cbe62ce4dcdbe11750317ed8e506a6ca6534cba20eaf75352286f4ace5e33",
    "finalize_experiment_7_2.py": "80766be8fd3da3ebb2da1aa096ee32431e682dc1e3caf513052111a24b4995d5"
  },
  "llm_result_summary": {
    "provider": "moonshot",
    "model": "kimi-k3",
    "using_openrouter": false,
    "training_time": 416.1074731349945,
    "api_calls": 17,
    "api_attempts": 17,
    "api_errors": 0,
    "fallback_actions": 0,
    "total_tokens": 28242,
    "training_victory_rate": 1.0
  }
}