Evidence row 308139

What was observed

{
  "count": 6,
  "tools": [
    {
      "description": "Ranks AI models for one task by performance only (price shown, never used for the rank). Tasks cover text, coding, agents, websites/UI/games/data viz, image generation and editing, video from text or image, video editing, text to speech, transcription, music and embeddings.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "license": {
            "default": "all",
            "description": "open = open weights only, closed = proprietary only",
            "enum": [
              "all",
              "open",
              "closed"
            ],
            "type": "string"
          },
          "limit": {
            "default": 10,
            "maximum": 25,
            "minimum": 1,
            "type": "integer"
          },
          "task": {
            "description": "Task slug",
            "enum": [
              "overall",
              "coding",
              "agents",
              "websites",
              "ui-components",
              "game-development",
              "data-visualization",
              "3d-scenes",
              "svg-graphics",
              "web-apps",
              "full-stack",
              "mobile-apps",
              "image-generation",
              "image-editing",
              "graphics-and-logos",
              "text-to-video",
              "image-to-video",
              "video-editing",
              "text-to-speech",
              "transcription",
              "music",
              "embeddings"
            ],
            "type": "string"
          }
        },
        "required": [
          "task"
        ],
        "type": "object"
      },
      "name": "best_for_task"
    },
    {
      "description": "For a model you use today, finds a cheaper model at most five performance-index points lower for the same usage.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "input_tokens": {
            "default": 1000000,
            "minimum": 0,
            "type": "integer"
          },
          "model": {
            "type": "string"
          },
          "output_tokens": {
            "default": 250000,
            "minimum": 0,
            "type": "integer"
          }
        },
        "required": [
          "model"
        ],
        "type": "object"
      },
      "name": "cheaper_alternative"
    },
    {
      "description": "Monthly API cost at base rates for up to five models and a token volume, with the volume translated into words and pages.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "input_tokens": {
            "default": 1000000,
            "minimum": 0,
            "type": "integer"
          },
          "models": {
            "items": {
              "type": "string"
            },
            "maxItems": 5,
            "minItems": 1,
            "type": "array"
          },
          "output_tokens": {
            "default": 250000,
            "minimum": 0,
            "type": "integer"
          }
        },
        "required": [
          "models"
        ],
        "type": "object"
      },
      "name": "estimate_cost"
    },
    {
      "description": "Searches and filters the catalog of language models by name, provider, licence and privacy, sorted by performance, coding, agentic index, price or context.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "license": {
            "default": "all",
            "enum": [
              "all",
              "open",
              "closed"
            ],
            "type": "string"
          },
          "limit": {
            "default": 10,
            "maximum": 25,
            "minimum": 1,
            "type": "integer"
          },
          "privacy": {
            "default": "any",
            "enum": [
              "any",
              "zdr",
              "eu"
            ],
            "type": "string"
          },
          "query": {
            "description": "Part of a name, id or provider",
            "type": "string"
          },
          "sort": {
            "default": "performance",
            "enum": [
              "performance",
              "coding",
              "agentic",
              "price",
              "context"
            ],
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "find_models"
    },
    {
      "description": "Price, context window, performance/coding/agentic index with rank, licence, privacy, cost for a usage volume and cheaper or open alternatives for one language model.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "input_tokens": {
            "default": 1000000,
            "minimum": 0,
            "type": "integer"
          },
          "model": {
            "description": "Model id like \"anthropic/claude-opus-5.5\" or a name like \"Claude Opus 5.5\"",
            "type": "string"
          },
          "output_tokens": {
            "default": 250000,
            "minimum": 0,
            "type": "integer"
          }
        },
        "required": [
          "model"
        ],
        "type": "object"
      },
      "name": "get_model"
    },
    {
      "description": "Returns the best-fitting language models for a use case and monthly API budget using the published AgentKernel Fit Score (performance, cost, context, features), with optional privacy and licence requirements.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "include_free": {
            "default": false,
            "type": "boolean"
          },
          "input_tokens": {
            "default": 1000000,
            "description": "Input tokens per month",
            "minimum": 0,
            "type": "integer"
          },
          "monthly_budget_usd": {
            "default": 10,
            "minimum": 0,
            "type": "number"
          },
          "needs_vision": {
            "default": false,
            "type": "boolean"
          },
          "open_weights_only": {
            "default": false,
            "type": "boolean"
          },
          "output_tokens": {
            "default": 250000,
            "description": "Output tokens per month",
            "minimum": 0,
            "type": "integer"
          },
          "priority": {
            "default": "balanced",
            "enum": [
              "balanced",
              "quality",
              "saving"
            ],
            "type": "string"
          },
          "privacy": {
            "default": "any",
            "description": "zdr = zero data retention, eu = zero retention in an EU region",
            "enum": [
              "any",
              "zdr",
              "eu"
            ],
            "type": "string"
          },
          "use_case": {
            "enum": [
              "everyday",
              "coding",
              "agents",
              "documents"
            ],
            "type": "string"
          }
        },
        "required": [
          "use_case"
        ],
        "type": "object"
      },
      "name": "recommend_models"
    }
  ]
}

What the leaf hashes

{"body":"8798bd8c707c21fdd5088a59c313e3523b7396c3b2b2c79cf09a6a53bfcaee86","id":308139,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793058085795331,"prev":null,"subject":"f77348c4-6560-464a-adc7-fbd7aba03960","subject_kind":"endpoint"}

Proof

Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of 2026-10-26 (296695 rows).

1. 0x8e665d9915a3104f6bf9cc7aeba1c01090656f5c2dc56b2a2528fa1d18655d3e
2. 0x53a31869b0e7f81878e447cb3de36299d20e3adf838b2c306c82bebc1ae1591b
3. 0x92c66ed8d449e1f1394572c43c6518fe548df07255f58da15efbedf4f93efdb7
4. 0xb9bbc06a7a581afbb2700266c2c041a22cfd704f71fd1efec279271862eb28da
5. 0xadc530fba7a983e044f1620ed8b1ae8e2311527e3187f4df55dcc57373803f6e
6. 0xea1cb5e779fc7df9ab8031977063b694a1d594056daaa7169331fad1702b8fc0
7. 0x46ec69e06eb941c349d719ca79f1d5cdb77d9d750ffb7be4e672db1dd7b0ec80
8. 0x757511393895bf8bf50d38611820fefdc01b2e59615840642fc8ebe3bc0a80b5
9. 0xa2dbfbb305c76bbf2107c06571bf81e6175882b7efa54da7a6353e5a8936d68c
10. 0xb45d7f3c0bbf1dbd174936f74bee2215bba98889ae1b45f88dec07545b773ee4
11. 0xf44f104cf96a81c75851a644746103fcbe6ade398683a18e789cc91eff4537ff
12. 0x59a4efa65a01e4e2abdb3b8b7bb673db6d1c72e0f9d52dd2f94777b14a5b061c
13. 0xc0cb184c9bdf71abcf18fda97bd59289153d120dbf8fee9f517b63bf303deb95
14. 0xf0edabbb9ba0d643e5505d19d07637eb6f6aed0a1c7356af43ae7d84ae9ef0c5
15. 0xf0bd63870f0bb378fa300bd33563050dcb7b3e02b44eb3ee550c1c534ec4b246
16. 0x1ac20d30773e1f4f2f811540e9a99b5cca9177c9e2e029acc0d80cf3f1d11f0f
17. 0xd21942ae3214eff88e08ab04884fd4b11958b51af9a0741b7668e2d07a2c56c9
18. 0x9a9024edb5069d88a324facb310a5ce8e495214bbaa968f077bede437390194f
19. 0x9b9ce5b74b9bab5121612ef6b64920a8d453cbf311096a423eef9702747e868a

Day root

0xf43e8dcc3d451a4788b26be904c55e8c4c0fa75c9666796c51db38d37e2c0df8

Chained

0x702d5ac508f08b0d1accf36af25822d8e5660367494edd17a642fb61e158a57a

Published

On Arc Testnet, block 69251483: 0x495162f8936e19f0039918feebe6c307f327cd6bf8c37219620b1970041fa9ae