Evidence row 3008721

What was observed

{
  "count": 5,
  "tools": [
    {
      "description": "Published example audits, such as the AI Project Radar, and how the audit works. With no arguments: the overview and the list of examples. With a name: one example, result by result (level filters by light). With a name and an id: one result with every reason and what to change. They are not the person's data.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "id": {
            "description": "Figure id inside that example.",
            "type": "string"
          },
          "lang": {
            "description": "Language of the texts. Default en.",
            "enum": [
              "en",
              "es"
            ],
            "type": "string"
          },
          "level": {
            "description": "Only figures with this light.",
            "enum": [
              "red",
              "amber",
              "green"
            ],
            "type": "string"
          },
          "name": {
            "description": "Example name from the list, e.g. 'radar'.",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "example_audits"
    },
    {
      "description": "Opens the audit panel in the chat. Without a spec, the panel receives the person's file, reads it in their browser and returns a profile of it: per column its kind, empty cells, distinct values, the values of categories with their counts, the range of numbers and dates, and the first rows. With a confirmed spec, the panel measures that same file in the browser with measure.py and shows one light per result. The file is not sent to this server.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "columns": {
            "description": "Optional: the column names of the file, to check the spec refers to real columns.",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "spec": {
            "description": "The spec from start_audit, as confirmed by the person. Leave it out to open the panel first, to receive the file.",
            "type": "object"
          }
        },
        "type": "object"
      },
      "name": "measure_in_app"
    },
    {
      "description": "Returns measure.py with a confirmed spec written in: a fixed Python script (standard library, no network, fixed seeds) that counts what each check needs from a data file and prints those counts with its own fingerprint and no rows. Reads .csv or .json. If the spec has errors, returns the errors instead.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "columns": {
            "description": "Optional: the column names of the file, to check the spec refers to real columns.",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "spec": {
            "description": "The spec from start_audit, as confirmed by the person.",
            "type": "object"
          }
        },
        "required": [
          "spec"
        ],
        "type": "object"
      },
      "name": "prepare_script"
    },
    {
      "description": "Turns the output of measure.py into one light per result (red, amber or green, with its reasons), after checking that the output comes from the unchanged script and from the given spec. Shows the lights in the chat and returns them, with a link to the same view on arquestra.dev that carries only codes. Stores nothing.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "output": {
            "description": "Everything measure.py printed: the fingerprint line and the measures line.",
            "type": "string"
          },
          "spec": {
            "description": "The same spec sent to prepare_script.",
            "type": "object"
          }
        },
        "required": [
          "spec",
          "output"
        ],
        "type": "object"
      },
      "name": "show_audit"
    },
    {
      "description": "Proposes how to read a data file for an audit, from its column names (optionally a type and one example value each) and the results the person wants to publish. Returns a proposed spec (the role of each column, each result written as a claim), how claims are written, the catalog of checks and the points the person has to confirm. It receives no rows.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "columns": {
            "items": {
              "additionalProperties": false,
              "properties": {
                "example": {
                  "type": "string"
                },
                "name": {
                  "type": "string"
                },
                "type": {
                  "type": "string"
                }
              },
              "required": [
                "name"
              ],
              "type": "object"
            },
            "maxItems": 200,
            "type": "array"
          },
          "dataset_name": {
            "type": "string"
          },
          "figures": {
            "description": "The results the person wants to publish, in their words, e.g. 'share of projects per sector'.",
            "items": {
              "type": "string"
            },
            "maxItems": 40,
            "type": "array"
          }
        },
        "required": [
          "columns"
        ],
        "type": "object"
      },
      "name": "start_audit"
    }
  ]
}

What the leaf hashes

{"body":"5ba0dd65710e187f8b048845286f05c7a3dc8268bbb13709f5e6a0d131f5417b","id":3008721,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793796849126730,"prev":null,"subject":"0a23726b-e08c-4305-af91-fed3288bfb25","subject_kind":"endpoint"}

Proof

Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of 2026-11-04 (424109 rows).

1. 0xb7aff4514fc04f2ffb63b3a91cc1b665e95cf86596b4f434bd0230fed75c503c
2. 0x7b2e63b3eddb15b62804c76ea5d0d65e261f0b3eb88c5304d4624950a669d9c3
3. 0x2b10e1d7382b6dd146c171d0644605508f175d1deae276076b8ca3a15a1c80ff
4. 0x6921825415257144d5a216d5e0fc476844c33463d88e585f6b4749279f1baf1a
5. 0x5c08d24d120c32f01c63c9cbe64bef87349100b620b7bacfd1da42a17c0e7d92
6. 0x149d17c13fb3371d0d8d7a4403e9ae39220cd8934118cb054f5228c0bccfb2e1
7. 0xc0ead597bac73b8415fdc9f186551fe52c9192d8e12c2900d44e1dc33a1ff2ea
8. 0x0f5fab00edc3c10ae8c5eec1b2453ae002018b1130ecf71a03216a0f302fcc0b
9. 0x30876ca66d238ae4b1c30670175baac97eb6e3ec729524d284f8ac8a2a767abd
10. 0xaea108cc623a62fdeeabacc47b5f1f1a859e07a39ad9c7caee23c3cf22a76489
11. 0x573c4aa95bede8c2495778cf470a67b0d6cc49e71f290419aa6cc000982ded39
12. 0xc134ebb1679ad69d8e6da5abf3d3b4c12664c96facf063b91247d587127a6413
13. 0xd6a22e336b1c6bbfcc4a12be911614c537449e248936a3ebb0c100815c42cab6
14. 0x7aa3efb7074066b3f8ec1d8329dfa11e7f8bb9594e7b6fb5e94738e387e076a9
15. 0x99e1d917a09f567cab45503a7bb813f7329bab71a3ee4058b136e2e24fd38eef
16. 0xa81588732e20541f1fd63a8674c3102204c511e11cd493c1ebf29abccd23069e
17. 0x321a352f90893ccd0656c1544d31825cd29cf74464e924a4ca7fb29b1f8ee0fd
18. 0x9c1c771179da4a002386557e8601b2d4983c3e366808477ee20da18c282c1dd8
19. 0xbb1998892a86d9633ea7b5de06760114b45777da649c217062ff0d65d7095f34

Day root

0xd4eed8c0ea3c90ec6f262b19fcc3b849f30cb82a0f84b8b89569e48af7d0c1ee

Chained

0x59305749c32724a02a23c368834d8a36ae9908da93a915e2962fffe01b4e591b

Published

On Arc Testnet, block 70772483: 0x813d56041c1efd407e56047129b597b154a1cb26458bb2768fd0a4630ac97345