Evidence row 573956

What was observed

{
  "count": 5,
  "tools": [
    {
      "description": "报告数据的新鲜度：每个数据文件的更新时间、距今天数、是否超过 60 天阈值。当用户质疑数据是否过时时调用。",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {},
        "type": "object"
      },
      "name": "data_status"
    },
    {
      "description": "判断某模型（指定量化、指定上下文）能否跑在某张显卡上。返回 fits/tight/no/unknown、剩余显存、内存拆解、以及跑不动时的替代方案（降量化/减上下文/换更大卡），并附带该卡的租金。",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "context_tokens": {
            "description": "默认 4096",
            "minimum": 1,
            "type": "integer"
          },
          "gpu": {
            "description": "显卡 id 或别名，如 rtx4090",
            "type": "string"
          },
          "model": {
            "type": "string"
          },
          "quant": {
            "type": "string"
          }
        },
        "required": [
          "model",
          "gpu"
        ],
        "type": "object"
      },
      "name": "fit_check"
    },
    {
      "description": "查询租用不同类型 GPU 的价格：我们的即时档/排队档报价、host 实得、电费成本、竞品中位价与国内零售价。只有 RTX 4090 有报价，其余显示为未定。",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "gpu": {
            "type": "string"
          },
          "include_competitors": {
            "description": "默认 true",
            "type": "boolean"
          }
        },
        "type": "object"
      },
      "name": "gpu_prices"
    },
    {
      "description": "查询部署某个模型需要的硬件配置：指定量化下的权重大小、最小/推荐显存、证据等级与出处，以及各张显卡的 fits/tight/no 判定与租价。数据可能过期，响应里会给出 data_updated 与 stale。",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "context_tokens": {
            "description": "默认 4096",
            "minimum": 1,
            "type": "integer"
          },
          "model": {
            "description": "模型 id 或别名",
            "type": "string"
          },
          "quant": {
            "description": "量化档，如 Q4_K_M；省略则用推荐档",
            "type": "string"
          }
        },
        "required": [
          "model"
        ],
        "type": "object"
      },
      "name": "model_requirements"
    },
    {
      "description": "按名字或类型查找模型 ID。查询模型显存需求前先用它确认 ID；模型名有别名（Qwen3.8 27B / qwen3.8-27b）。返回 id、类型、最小显存、参数规模。",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "limit": {
            "description": "默认 10",
            "maximum": 50,
            "minimum": 1,
            "type": "integer"
          },
          "query": {
            "description": "模型名或别名；省略则列出全部",
            "type": "string"
          },
          "type": {
            "enum": [
              "text",
              "image",
              "video"
            ],
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "search_models"
    }
  ]
}

What the leaf hashes

{"body":"2ac861db95f66193154f983c1cd4bbb6c7068478f0034ff8e4ff523340d6b1d6","id":573956,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793141351535924,"prev":null,"subject":"b5229852-de68-4d85-baab-fa145ff86f5a","subject_kind":"endpoint"}

Proof

Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of 2026-10-27 (273461 rows).

1. 0x85988d4cbc36cfc184090e35e6fe66443f48bce2b3be863327d3848abe5edbe3
2. 0xa01d17387f3283d199063789b44d0bfab2768996a49f2bde990fd3b1229309d3
3. 0x8c53ec6f2e896f41214f8cfdd161662f87429b775181a5c88dd5d31680b6dd6a
4. 0xb50bbdfed6210d38e0126d9914bcfa89d7bc2b53217cf2a2964e4d9e36f7cba0
5. 0x51070f885e0f7d4c1d8610f2fa78fa332e10c0a360390b59ec0ec9acb77d3e87
6. 0x5bd3fa76eb7aa751bca4d91ad2b8c5601cad3433408e864b68b62125f077a9d2
7. 0x1fc4972a1edbe14762170fed3aab97a0f0c99839ec8d2f40c5c50be9892ec9d0
8. 0xf96f32bd1f38890ae960a2acd3dec01007283e9da4e9237335cd634fa135ddab
9. 0xd283a28d6e852245fdfe8b9ec866401bb4ddfee62d5559e68ef4586070156661
10. 0x96a0da13299187f33c6402d51c70a67e16424b1c2efecb62b5deff3accdc84f9
11. 0x94b5117661526893571c5099bb213b21f54068dc9f381d688b9be7c593a99d91
12. 0xe5ce8ac1ba4d6152605e0a032058cac5906d85f82e3fda1ad44852337b713b17
13. 0x07d414626f116f3edc6ddb34183ed02538c3a805fec6db00f9d764f8fd595d04
14. 0x4964f0806efde5ed25f60da2b45d78cd2e0f07d67e64aad2822f6016ad973c47
15. 0x3c500ec3d3edf0c74b87a6ca8fcd77656bfbe03db3d478bd0c184d0c88839c6b
16. 0xfecf3d4646dd4984a13dd715499e842c3fde63692336d97394c2bfd8e877ca5d
17. 0xf30fddbf4811226c58e8f0daf36fddd79fc5f1356b592bb1d99a8061ddbabe66
18. 0x2bf8151e5f157dd183b9de6fa00469551932a7a6e3f33a694895000ac9061197
19. 0x9fc354c0ea3efc3f1b6548bb77ea902a50f2c9647647ea61592efce2bd795699

Day root

0xdd77e5e99da32c3f154180d63e3c3e6fe11e896a2c6896412ef6b5c4bcf7e795

Chained

0x23bb4dfd09f55c15ac3962f53578e02c6114d5bfd9bb451cf8794fb6e2817ef4

Published

On Arc Testnet, block 69414147: 0xb2ebd83aafeb765a0ce66e76aefb133ed06606c98038fd56191e2bcd1dcb77b4