Evidence row 561028

What was observed

{
  "count": 6,
  "tools": [
    {
      "description": "Get the full record for one model, including every field and the endpoint each field was sourced from. Use when you need provenance or complete detail.",
      "inputSchema": {
        "properties": {
          "id": {
            "description": "Repo id, e.g. \"Qwen/Qwen3.8-27B\"",
            "type": "string"
          }
        },
        "required": [
          "id"
        ],
        "type": "object"
      },
      "name": "get_model"
    },
    {
      "description": "Everything The Neural Net harvested in the last day that it did not write up, grouped by source and linked to the original. Use for a broad view of current activity.",
      "inputSchema": {
        "properties": {},
        "type": "object"
      },
      "name": "get_wire"
    },
    {
      "description": "Models first recorded in the register within the last N days. Use to answer 'what shipped recently' or 'what is new in open-weight models'.",
      "inputSchema": {
        "properties": {
          "days": {
            "description": "Look-back window, default 30",
            "type": "number"
          },
          "limit": {
            "description": "Default 25",
            "type": "number"
          }
        },
        "type": "object"
      },
      "name": "recent_releases"
    },
    {
      "description": "Summary of what the register covers: how many models, field coverage, organisations tracked, and the inclusion rule. Use to judge whether the register can answer a question before querying it.",
      "inputSchema": {
        "properties": {},
        "type": "object"
      },
      "name": "register_stats"
    },
    {
      "description": "Search the model register: open-weight AI model releases with exact parameter counts, architectural context length, licence and release date. Use this to answer questions about which models exist, how big they are, what they are licensed under, or what shipped recently.",
      "inputSchema": {
        "properties": {
          "image_input": {
            "description": "Only models that accept image input",
            "type": "boolean"
          },
          "include_derivatives": {
            "description": "Include quantisations and conversions of other releases (GGUF, MLX, AWQ and similar). Default false.",
            "type": "boolean"
          },
          "license": {
            "description": "e.g. apache-2.0, mit",
            "type": "string"
          },
          "limit": {
            "description": "Default 25, max 100",
            "type": "number"
          },
          "max_parameters": {
            "type": "number"
          },
          "min_context": {
            "description": "Minimum architectural context length in tokens",
            "type": "number"
          },
          "min_parameters": {
            "description": "Minimum parameter count, e.g. 7000000000",
            "type": "number"
          },
          "organisation": {
            "description": "e.g. qwen, deepseek-ai, meta-llama, google",
            "type": "string"
          },
          "query": {
            "description": "Substring match on the model id",
            "type": "string"
          },
          "reasoning": {
            "description": "Only models whose chat template shows reasoning/thinking support",
            "type": "boolean"
          },
          "released_after": {
            "description": "ISO date, e.g. 2026-01-01",
            "type": "string"
          },
          "task": {
            "description": "e.g. text-generation, image-text-to-text, mask-generation",
            "type": "string"
          },
          "tool_calling": {
            "description": "Only models whose chat template shows tool-calling support",
            "type": "boolean"
          }
        },
        "type": "object"
      },
      "name": "search_models"
    },
    {
      "description": "Search stories published by The Neural Net. Each story is written from a primary source and links to it. Use for narrative context on a release rather than raw model facts.",
      "inputSchema": {
        "properties": {
          "limit": {
            "description": "Default 10",
            "type": "number"
          },
          "query": {
            "description": "Substring match on headline and summary",
            "type": "string"
          },
          "topic": {
            "description": "e.g. models, products, infrastructure, research, policy, safety",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "search_news"
    }
  ]
}

What the leaf hashes

{"body":"daf4abe2cbac079a0c71056978adb3cc3079041ac1d49fcb317d85644411d339","id":561028,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793136723761665,"prev":null,"subject":"36b92137-1969-4801-a33f-48a0c104e992","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. 0x12a2cc648b1e14a3adefb20971424dadf7cf7e5c9b8f757a556627a599b9db60
2. 0xd50b3c7bd0316d6274289ad4dabce7c1466251fb252f2b92a3c069edc02346ca
3. 0x37f2c86d9e9837433decd88f40867a8691605a529bd88eff37c3feb86156d928
4. 0xb71d2dd1a006bc26b9e87daad7daba6699fed78255a8e611d94ff6b1256bb55b
5. 0x9304b532498a3cca0d5ca5c0e952a442a222a2e19d885c82b38b068038ea10f0
6. 0x0b36874ff8d5e5f55a2b1ed427a61235c560ba08085d3ca3a1c2bf09522eea18
7. 0x95d1f8aa9049490a8e2a181f038a241036f9d74153f94f11cde4f9f66cdd061d
8. 0x1c1173bc3aec2616ac22d6e4d77718d557fb3a39baaee5c3b88b7ffe6e3f8a03
9. 0x193d4ca77fd18f5603eed9950af686b4fc90040aaa394672f65d04155765608d
10. 0xa09ed7b0630e96460b870ee10d5404bc0c7fafc2746919271d1675bb24fd99c9
11. 0xf3282d08aac8493b8388904acc143add67b80dc96ecc149d4372cab1977d5e98
12. 0x7578555e40efa7fabcea1fc203440565253b358954d398ba44e9e10d228eb3b9
13. 0xedf6ab3c3733ce137d888d3e5f7006ba77ab04b8f1fe576519f7b056959665ee
14. 0x52c5141da0cbee106a30396ee7d1360fd22f55084aca2ca436c8007892775670
15. 0x6913cb48392acb8dc5c940dcdb6e6fc889d544f85dff11da249551a5f027e688
16. 0x518b93854db03dc9fc938883abf30da6eaae5ae0d4336903968fd32a7df8c71b
17. 0x22c1fb9487ee0b9732fa017a0cc321eb27a60c08450d112f755089796e12cb1c
18. 0xa20d48798a34aba12eb9c7297722982d910f06c148f5e27ac59307422964a585
19. 0x9fc354c0ea3efc3f1b6548bb77ea902a50f2c9647647ea61592efce2bd795699

Day root

0xdd77e5e99da32c3f154180d63e3c3e6fe11e896a2c6896412ef6b5c4bcf7e795

Chained

0x23bb4dfd09f55c15ac3962f53578e02c6114d5bfd9bb451cf8794fb6e2817ef4

Published

On Arc Testnet, block 69414147: 0xb2ebd83aafeb765a0ce66e76aefb133ed06606c98038fd56191e2bcd1dcb77b4