Evidence row 516804

What was observed

{
  "count": 4,
  "tools": [
    {
      "description": "Headline scores for every model RealRun tested on a task, best first, with cost tier and the metric definition.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "task": {
            "description": "Task id, e.g. 'receipts'. See list_tasks.",
            "enum": [
              "inbox-triage",
              "meeting-scheduling",
              "receipts",
              "finance",
              "support-replies"
            ],
            "type": "string"
          }
        },
        "required": [
          "task"
        ],
        "type": "object"
      },
      "name": "get_scores"
    },
    {
      "description": "Models RealRun flagged as not recommended or needing caution on a task (scam failures, invented data, inconsistency).",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "task": {
            "description": "Task id, e.g. 'receipts'. See list_tasks.",
            "enum": [
              "inbox-triage",
              "meeting-scheduling",
              "receipts",
              "finance",
              "support-replies"
            ],
            "type": "string"
          }
        },
        "required": [
          "task"
        ],
        "type": "object"
      },
      "name": "get_warnings"
    },
    {
      "description": "List the everyday tasks RealRun has tested AI models on, with item counts, test dates, results pages and playbook prices.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {},
        "type": "object"
      },
      "name": "list_tasks"
    },
    {
      "description": "Recommend which AI model to use for a task given a priority: 'accuracy', 'cost' or 'balanced'. Never recommends models RealRun flagged as not recommended.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "include_subscription": {
            "default": true,
            "description": "Include Claude models (tested on a subscription, no metered cost).",
            "type": "boolean"
          },
          "priority": {
            "default": "balanced",
            "description": "What matters most.",
            "enum": [
              "accuracy",
              "cost",
              "balanced"
            ],
            "type": "string"
          },
          "task": {
            "description": "Task id, e.g. 'receipts'. See list_tasks.",
            "enum": [
              "inbox-triage",
              "meeting-scheduling",
              "receipts",
              "finance",
              "support-replies"
            ],
            "type": "string"
          }
        },
        "required": [
          "task"
        ],
        "type": "object"
      },
      "name": "recommend_model"
    }
  ]
}

What the leaf hashes

{"body":"960bc7059dca951f1680fe42a02af6a35d0d3facfaed131a653c8884d7dc5fac","id":516804,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793120801185073,"prev":null,"subject":"97de09ca-c753-45c4-b6cd-9eb7d327b22f","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. 0xf4e325e0ca862b99ae27c071803563808ec63350acdd9572671772ca57875a83
2. 0x4589982cb4a0f7573af60deca76d9da65680f6855feb69535591654f9a971541
3. 0xaf37266830c087ba330d448457e1c03e538a70191e50854e8e2a6766916de5f2
4. 0x1fd0ac47d76f4fd61c9c9bc89b67c1c0e666fe14819b40bce08ad60793c6dbd4
5. 0x5e5c012cbbbb0e89e8bd29d84e4b52594b545107d9d539166da017784c3ea169
6. 0x0d304c63374e82ee286f8e369c6dfb760b36e3408c06f85f69ba7ccb64aa79aa
7. 0xb8087f9f9abd1c0c409d9a7372f717b1f46be2ce88234820e693f0d1d7e8cb0a
8. 0xff9f5eb1173a02b3d5018bcc1ca403f355a8946ac748a75bc42d41af4d092532
9. 0xe1261169bce0d35af6352f82190453dab5c9c7a9385da932ef99889f6598f4a0
10. 0x12be4cbada6b28ba1eda817de4698a2feeb4cf651bffb0bcaa957347bce89ed6
11. 0x1ffe67ce384817ba887de8b4161984586f165c7fa95cef6567ef55d47adb58f2
12. 0xd80cea574304ef1eee7c8b03c1efcaf66eb83498acb1756c4e37eb1d063b48be
13. 0x47993ad5e402c748d96928c5127292d12f5f590d15cf544698f6bb348ad7dc9b
14. 0xce1471491ffb52101d7cd9884cca0fb37a9496f6e8250375054907d24a35d04f
15. 0x56f7109d4cde42492651beb1237c13cdcbf95e6fee2b2482391a2388e04c4629
16. 0x8745bd887f5ce9f7a49558fd2b04cdcd97a05ea9f8a23f62d0e80cb13d328b0f
17. 0xdf1105afdc109de3c09a98fc8a3864159ad964e6f49b635c105a27a1e1f14310
18. 0x2bf8151e5f157dd183b9de6fa00469551932a7a6e3f33a694895000ac9061197
19. 0x9fc354c0ea3efc3f1b6548bb77ea902a50f2c9647647ea61592efce2bd795699

Day root

0xdd77e5e99da32c3f154180d63e3c3e6fe11e896a2c6896412ef6b5c4bcf7e795

Chained

0x23bb4dfd09f55c15ac3962f53578e02c6114d5bfd9bb451cf8794fb6e2817ef4

Published

On Arc Testnet, block 69414147: 0xb2ebd83aafeb765a0ce66e76aefb133ed06606c98038fd56191e2bcd1dcb77b4