Evidence row 532239

What was observed

{
  "count": 2,
  "tools": [
    {
      "description": "Describe the problem in your own words, for example \"let users upload images\" or \"send transactional email\". Returns the vendors we have measured in that category, split by whether an unattended run clears every barrier we test, stops at one, or was never measurable, each with the date and a link to the evidence. This is not a recommendation: it does not know whether a vendor suits your job, only where an agent stops. Routing a sentence to a category is by far the weakest thing here, and the numbers below are the ones to plan around. Measured on 40 questions written by an agent with no access to this repository and no sight of the category list, labelled before the first run, and built to be hard: fourteen of them ask about the caller own code in commercial words (a billing module, a payments table, a notifications worker), and six ask for something real that a catalogue this size does not hold. It got 29 of the 40 right, said nothing on 8 it should have answered, sent 0 to the wrong category and answered 3 that it should have refused. Put another way: it gave an answer to 14 of the 40, and 3 of those answers were wrong, while refusing 18 of the 21 it should have refused. It is deliberately quiet. One vocabulary word inside a long question decides nothing, and a question shaped like a request for code rather than for a vendor is refused outright. Silence means we could not read the question, not that the category is empty. The tool reads English. Name the category yourself when you know it.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "job": {
            "description": "The problem to solve, in your own words.",
            "type": "string"
          }
        },
        "required": [
          "job"
        ],
        "type": "object"
      },
      "name": "find_providers"
    },
    {
      "description": "Scores a domain across 5 funnel stages using 16 deterministic HTTP checks. 18 points exist on paper; the score is out of the points that both applied to the domain and could be evaluated. Returns a per-check breakdown with the reason for each result and a permanent link.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "domain": {
            "description": "Bare domain, for example example.com",
            "type": "string"
          },
          "format": {
            "default": "summary",
            "description": "summary is the readable breakdown. agent returns markdown instructions you can act on directly, each task carrying the measurement behind it. sarif returns SARIF 2.1.0 for a code-scanning pipeline.",
            "enum": [
              "summary",
              "agent",
              "sarif"
            ],
            "type": "string"
          }
        },
        "required": [
          "domain"
        ],
        "type": "object"
      },
      "name": "scan_domain"
    }
  ]
}

What the leaf hashes

{"body":"1f65491f8030cba01dcac4020cfc215dc99807ffebe3420cb4ef0bfc6429d51a","id":532239,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793126996450179,"prev":null,"subject":"8b3a51a9-0c7b-40c6-9970-ad1539a43930","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. 0x2ac23ab442c5ee05bdcc3f069bf70fa3f9834015cb8b50e2441a00b0a4b6cab6
2. 0xd568168f12c64dfa907d4fa9740c5450230b48b715ee0f82b43d2f031e87622f
3. 0x18357720c4046053b7cfeb05cf7ec3b19368e0fab621de954c519753910357d8
4. 0x2fe34963fac581392566b275746b66550f45e68963df5d3f7c7ce929231f174a
5. 0xbd602b20ec5ff75ef981460b43f27211b65279519908352b4205433c3582fea3
6. 0xbb21e73a8e3aba1fb962a03c620ea8ac1962ebc5a5035c0da4a2ba0163af2799
7. 0x9c0f634c69d5b3c3710862c7d9fbfa03aee6cbeb6135b0740c117d38c1f56110
8. 0x8616be81fbcfc893b6ec16f408dbf4100debfea75d27efdffe5ffbc9db8a514c
9. 0x1c83f5b6ae447deecc4ad51ddbce0a9e5d76703b4f7248094766f194bd5e4007
10. 0x4d8c0a652311a9beb5604c5c980355730cfe574dd0775e932e535b872742683b
11. 0xec8e4ccca73ad575591e2aae8a6d2bf4bfef826240c40728c9fc6d960b63ff0f
12. 0x7ba1b835277802a22a6f62a758420094404a75d3c14f34dd88b403fbf174b26b
13. 0xf9e544d10b80657275e1e196da89ba5336a7cc49eaa0d6d801fb5d632cf5deec
14. 0x8ff18b1523f9fbdd16a5796cbe184b46854c06256508af8de5509b598370c725
15. 0xa383a1cfe9b3f6af67eb4c7642564b9424d46d7fca90e7ba175d549f8b67dd0c
16. 0x52efa60e0c3d8525486d2310eb3b6b566c9677c64fd1f819edb072cf101bcbdb
17. 0x22c1fb9487ee0b9732fa017a0cc321eb27a60c08450d112f755089796e12cb1c
18. 0xa20d48798a34aba12eb9c7297722982d910f06c148f5e27ac59307422964a585
19. 0x9fc354c0ea3efc3f1b6548bb77ea902a50f2c9647647ea61592efce2bd795699

Day root

0xdd77e5e99da32c3f154180d63e3c3e6fe11e896a2c6896412ef6b5c4bcf7e795

Chained

0x23bb4dfd09f55c15ac3962f53578e02c6114d5bfd9bb451cf8794fb6e2817ef4

Published

On Arc Testnet, block 69414147: 0xb2ebd83aafeb765a0ce66e76aefb133ed06606c98038fd56191e2bcd1dcb77b4