Evidence row 1478920

What was observed

{
  "count": 7,
  "tools": [
    {
      "description": "查某张 GPU 过去 30 天每日价格序列：每日全平台最低价、当日市场中位价、最低价来自哪个平台、库存状态、当日报价家数。示例: gpu_history(gpu='H100 80GB', limit=7) → 2026-10-20 最低 8.28 元（paperspace）、中位 23.04、有货、9 家报价。按次计费 $0.02 USDC。",
      "inputSchema": {
        "properties": {
          "gpu": {
            "title": "Gpu",
            "type": "string"
          },
          "limit": {
            "default": 30,
            "title": "Limit",
            "type": "integer"
          }
        },
        "required": [
          "gpu"
        ],
        "title": "gpu_historyArguments",
        "type": "object"
      },
      "name": "gpu_history"
    },
    {
      "description": "查某张 GPU 现在的全平台最低价（元/小时），含报价平台、30 天最低/最高/均价、当前价与 30 天最低价的差距。示例: gpu_price(gpu='RTX 4090') → 当前最低 1.24 元/小时（算家云）、市场中位 1.99、30 天最低 1.24、今日 8 家报价。按次计费 $0.002 USDC。",
      "inputSchema": {
        "properties": {
          "gpu": {
            "title": "Gpu",
            "type": "string"
          }
        },
        "required": [
          "gpu"
        ],
        "title": "gpu_priceArguments",
        "type": "object"
      },
      "name": "gpu_price"
    },
    {
      "description": "列出所有可查询的 GPU 卡型（免费）。付费查询前先调这个拿准确名称。",
      "inputSchema": {
        "properties": {},
        "title": "list_gpu_modelsArguments",
        "type": "object"
      },
      "name": "list_gpu_models"
    },
    {
      "description": "近 30 天 GPU 行情涨跌榜：按区间涨跌幅排序的降价/涨价卡型，含当前价与 30 天最低价。示例: market_movers(top=3) → 降价榜 A6000 48GB 2.52 元(-28.6%)、A100 80GB 5.47 元(-21.6%)、RTX 3090 0.80 元(-19.2%)。按次计费 $0.005 USDC。",
      "inputSchema": {
        "properties": {
          "top": {
            "default": 5,
            "title": "Top",
            "type": "integer"
          }
        },
        "title": "market_moversArguments",
        "type": "object"
      },
      "name": "market_movers"
    },
    {
      "description": "健康检查，免费。返回服务状态、收款地址、网络与价目表。",
      "inputSchema": {
        "properties": {},
        "title": "pingArguments",
        "type": "object"
      },
      "name": "ping"
    },
    {
      "description": "各 GPU 租用平台的数据监测覆盖度评分（A~E）：自动抓取成功率、收录天数、库存充足率、覆盖卡型数。注意：衡量的是本数据源对该平台的价格监测覆盖度，不代表平台自身的服务质量。示例: platform_reliability() → 29 家平台评分，如 gpushare 100 分 A 级（抓取成功率 100%、覆盖 6 张卡、30/30 天）。按次计费 $0.005 USDC。",
      "inputSchema": {
        "properties": {},
        "title": "platform_reliabilityArguments",
        "type": "object"
      },
      "name": "platform_reliability"
    },
    {
      "description": "按任务推荐最便宜的 GPU 租用方案：输入任务（如'微调 7B'/'视频生成'，或英文 finetune-7b/video-gen），返回推荐卡型、最便宜平台、每小时单价与估算任务总成本。覆盖 8 类任务：微调、推理、绘图、视频、渲染、学生练手、70B 训练、多卡集群。示例: recommend_for_task(task='微调 7B') → 最便宜卡 + 平台 + 单价 × 8 小时的总成本。这是别处没有的'按任务问价'能力。按次计费 $0.01 USDC。",
      "inputSchema": {
        "properties": {
          "task": {
            "title": "Task",
            "type": "string"
          }
        },
        "required": [
          "task"
        ],
        "title": "recommend_for_taskArguments",
        "type": "object"
      },
      "name": "recommend_for_task"
    }
  ]
}

What the leaf hashes

{"body":"705d18bdd5a0df08d8379f8da2e05e9bc02b8f2969ace9ecf0a86dcda6d6d73c","id":1478920,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793429218139042,"prev":814829,"subject":"93b34229-546b-4728-b33c-91c67381e1ee","subject_kind":"endpoint"}

Proof

Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of 2026-10-31 (246033 rows).

1. 0x7290dfaa4ca2cbf4f4448cab3c33cd71ee51bbd25e5d0df1f61b2d50ed825327
2. 0x32781999222a555a6941e5c0417dde7e798bf7f9c50fefe33662b0f7ca045e1c
3. 0xa91c0ea913dc148efb62856966f5d255cda994401b85feabd230feb37a2b95d5
4. 0x4b77118930a2358a4ec2d991568afb5e360ed1c519ef5e76953027c79eed9630
5. 0x1ce2ef2433a475c7da729c05dd02ed115cacd5539f6c9e5c2fd54cc46a0a1443
6. 0x62af517420fac1d782ecc0807e61bdff7708f0c9d0f4058ba72a99fabe88d924
7. 0x6f5bc8bc29831e8da8ff19dbb338f8c2f3084b2bc4ea6775f54b30713a1297ff
8. 0x0f528ea232698e4e17e3017402e01908882ff4ca7f9db0f44240ee27909c47ae
9. 0x812558af53894743d310ac971e0ab0972deaff45c411d5cc3c95674cc9c2b476
10. 0xb144aceea6d1669c62c0c5583e3dcd9db643d8abb93dd56548fad86942ef65fb
11. 0x1877d208b3b33b1ba06f0ae8cca1be4f99909183265a6afaf66f8ea507d870ca
12. 0x814878fb61963225d212f065c4627f50baa38320fe9eaa2470206752508252c4
13. 0xcd5e7734bd8848fcbd68ddd77d7fb326e0e8f4beccfaf7423728dad7030eeb6f
14. 0x41e1f7c43ac5b235ed2b70fcc7418dedf8f488e17dfa6d5347558c4b213497ea
15. 0xda82240eda32eeb01478d5898342fa15b35b5682549347c7a22660b37913617f
16. 0x919f237dec4df392868ab95f1d4300b185479ae64464cbc2e7385ad1fd6ab390
17. 0xa00a931d72706fa2402bfc9b441a12eb7c6a61ff42a542916106e3637177f101
18. 0x59f83f7228f07febe2780660e422e171b0359b8aa031ee3be07e991118130c15

Day root

0x24463725d1c0d9894bd6123691d532547aaa79f0762c0e45aa6a68acf1fd71ab

Chained

0x7d4824ff313dee7252a46f9d5c37b452851deb6c9f24a40c2f74ee0e53c82980

Published

On Arc Testnet, block 70093156: 0xedb7b832f4ebf6781b5ecd2ed241c435b862f4d3761541fa31adc1831b8c44a0