Evidence row 276908

What was observed

{
  "count": 5,
  "tools": [
    {
      "description": "Place two retained calculation profiles side by side by display_name substring. Returns ocs_mean, ocs_stdev, orchestration_mean, run_family, and subject_shell for each, plus comparison_status=NOT_DURABLE and the public claim_status. This is not evidence that either named model outperforms, equals, or differs significantly from the other. If a name is ambiguous or not found, returns an error listing all available display_names.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "model_a": {
            "description": "Display name (or substring) of the first model",
            "minLength": 1,
            "type": "string"
          },
          "model_b": {
            "description": "Display name (or substring) of the second model",
            "minLength": 1,
            "type": "string"
          }
        },
        "required": [
          "model_a",
          "model_b"
        ],
        "type": "object"
      },
      "name": "compare_models"
    },
    {
      "description": "Return the full case for a given pair_id (axes 1/2/4) or id (axis 3): malign and benign task prompts, expected decisions, grounding rationale, and bypass patterns. Axis 3 cases are single (unmatched) and use an 'id' field instead of 'pair_id'. Use list_cases to browse available ids.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "axis": {
            "description": "The axis this case belongs to",
            "enum": [
              "refusal-calibration",
              "sanctioned-path",
              "orchestration",
              "escalation-reroute"
            ],
            "type": "string"
          },
          "pair_id": {
            "description": "The pair_id (axes 1/2/4) or id (axis 3) to retrieve",
            "minLength": 1,
            "type": "string"
          }
        },
        "required": [
          "pair_id",
          "axis"
        ],
        "type": "object"
      },
      "name": "get_case"
    },
    {
      "description": "Return the benchmark design: the 4 axes, the OCS formula (Youden's J), the 5 decision labels (PROCEED, PROCEED_SANCTIONED, REFUSE, ESCALATE, REROUTE), scoring blocks, and a concise what-it-measures / what-it-doesn't summary. Sourced from the baked case-file metadata.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {},
        "type": "object"
      },
      "name": "get_methodology"
    },
    {
      "description": "Return retained model calculation profiles plus generated_at, claim_status, claims_at_risk, and the bounded evidence_binding. These rows are not durable named-model performance claims. Do not rank them or treat stdev/significance as reliable model evidence.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {},
        "type": "object"
      },
      "name": "get_results"
    },
    {
      "description": "Return case metadata (no full task prompts): pair_id/id, axis, tier, grounding, and side indicators (malign/benign for axes 1/2/4; null for axis 3). Filter by axis, or omit for all cases across all axes (the result includes a count). Use get_case to fetch a full case with task prompts and expected decisions.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "axis": {
            "description": "Axis to filter by: refusal-calibration | sanctioned-path | orchestration | escalation-reroute",
            "enum": [
              "refusal-calibration",
              "sanctioned-path",
              "orchestration",
              "escalation-reroute"
            ],
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "list_cases"
    }
  ]
}

What the leaf hashes

{"body":"597f84ceb278162ef749f08370bb97a7f370de5712794327b04a6833d7e6fa0d","id":276908,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793041647892976,"prev":null,"subject":"45500f52-07d0-4dcc-9982-675b21dd7335","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. 0x8d516c36ed6df7f5dda4f7b17ba305327d7b7832b09d2a54c7e45420f2547ded
2. 0xd5f4304cd717211889c15d841037d856e9bf3a08886d86961a16ae00c8eecea9
3. 0xbe7bdd70938a6d70e1138f2377d81e63bdb22caa97c678cdf35b69b2ed85a644
4. 0x7e89640ba63be0a997e1a84a8d2659f1df74a922c306c1f65d37312eb3416067
5. 0x43098092a481c3512e25df6bd1234a5fcac4c24427403c82667a223156aeb6ff
6. 0x5187da6efb06469cebbafd8b46a832519195a88be23dcec1c0d871abc5950c08
7. 0xcc30db7904614bd7b7143386ab1cc89c31331e055ff34496c239cf9bee45d1a3
8. 0x9c58ad9ac7e7117a0f2ae7937cef3b35a0043d74ce78ace09c16edad70541bfc
9. 0x8740340a24cd78c9870cdf4d30c6018249d97da848721d4b77f04b138a763dc9
10. 0x57adb884aa6187c9e7f153cc992251efcdbefadc60f2e9d6a2c0a9c60d412203
11. 0x6880847de0a4b4b8c14408244df84ff11ac20d4049a575846d0700a7a91132ca
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