Evidence row 302658

What was observed

{
  "count": 3,
  "tools": [
    {
      "description": "Read one privacy policy or terms-of-service page and return a grounded verdict, eight fixed yes/no/partly/not-stated answers, and up to five findings, each with a verbatim quote from the document.\n\nUse this instead of fetching and reading the page yourself. A policy page is 20,000-60,000 tokens of context, and many are rendered by JavaScript so a plain fetch returns an empty shell without saying so. This returns about 1,000 tokens: a 20-60x saving with a quote behind every claim.\n\nGuarantees: every claim carries a verbatim sentence from that document, and a question the document does not address is answered not_stated -- never as a promise the document did not make. The eight questions are identical across services, so two reports can be set side by side.\n\nA report may be served from an earlier reading of the same document, which is what makes it cheap and instant. readAt says when that reading was taken; call policy_changes_since if it matters whether anything has moved since.\n\nDo not use this for a document that is not a legal agreement; it is refused, and a refusal costs nothing. Do not use it to summarise a page in general, to read a document the user pasted rather than published at a URL, or for legal advice: Automated reading of one document. Not legal advice.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "url": {
            "description": "The https address of the published policy page itself, not the service homepage.",
            "type": "string"
          }
        },
        "required": [
          "url"
        ],
        "type": "object"
      },
      "name": "check_policy"
    },
    {
      "description": "Answer the same eight fixed questions across two to five services at once, so their policies can actually be compared.\n\nUse this instead of reading each document yourself. Doing it yourself needs N full reads and a rubric you have to keep consistent between them; the questions here are fixed, so a difference in the answers is a difference in the policies rather than a difference in how you read them. Each answer also carries how common that answer is across every comparable document Policy Pal has read.\n\nGuarantees: identical questions, a verbatim quote behind every stated answer, not_stated where a document is silent, and not_asked where that kind of document was never asked that question -- a silence is never invented to fill a table. A service whose report is not comparable, or that there was no time to read, is reported as such rather than filled in.\n\nDo not use this for one service -- call check_policy. Do not expect a score or a ranking: Policy Pal publishes qualitative verdicts and refuses to reduce a policy to a number. Automated reading of one document. Not legal advice.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "urls": {
            "description": "Two to five https addresses of published policy pages. Compare documents of the same kind: a privacy policy and a terms page answer different questions.",
            "items": {
              "type": "string"
            },
            "maxItems": 5,
            "minItems": 2,
            "type": "array"
          }
        },
        "required": [
          "urls"
        ],
        "type": "object"
      },
      "name": "compare_policies"
    },
    {
      "description": "Say what changed in a service's policy since a date, expressed as changes to the eight fixed answers.\n\nYou cannot do this yourself at any context size: it needs the earlier version of the document, and the earlier version is gone from the web. Policy Pal keeps the eight answers for every version it has read, so the difference is a fact rather than a reconstruction.\n\nIt reports answer changes -- for example forced arbitration moving from no to yes -- and not text edits. A changed comma is noise; a changed answer is the thing worth telling someone about.\n\nReturns nothing to report when the answers are unchanged, and says so explicitly when it has no reading from before that date rather than guessing. A question the earlier reading did not answer is reported as not compared, never as not_stated. Automated reading of one document. Not legal advice.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "since": {
            "description": "The date you last looked, as YYYY-MM-DD or an ISO timestamp. The answer is the difference between what was true then and what is true now.",
            "type": "string"
          },
          "url": {
            "description": "The https address of the published policy page.",
            "type": "string"
          }
        },
        "required": [
          "url",
          "since"
        ],
        "type": "object"
      },
      "name": "policy_changes_since"
    }
  ]
}

What the leaf hashes

{"body":"8f5e61567be9f7b11cb429011d91de892dddee938d88c8bf1c9740ffe9b2cf97","id":302658,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793054878368576,"prev":null,"subject":"f2a22fc7-682c-46f4-803d-87862620bacd","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. 0x71705dbab50a39e88916da09dc38047779c3fd1e4c3bff255ef5522a6cd395a5
2. 0xbb441d7c70a382ca4c6cc044a04a89e691cbc605080a1734a874de2dd17caffd
3. 0xe6a2ff5f54cdb101a296696dfcd8d9eef37191050e5223e0327506409035ca46
4. 0x46bfe659d709106bef49fb5091940e599d25a54a42788fb084dbe28a4e380b68
5. 0x659c2f4f05441fc73d291ca3f92f5789028791c0f3433b9a4a0c363a9b4ace40
6. 0x2e6958a2c8e9e5ce7baa337dc88f84ff2f12a8af3a0b208f0918b54996fc2c66
7. 0x99ef1c7173042a604c15b31f9b98619282435c5e8915f4298452576bb477283f
8. 0x69152905370a0e524cdb626323fdb48da24df71d866a22b4e30027c22a007b15
9. 0x806812238e56c7e945c289020ca462472651f75cb6817226402b9092b9cca9e5
10. 0x0713a0ebeb53a78275d9103be9f6ca1687f13b61cbba8f146f9ef3faf529dde5
11. 0x170ddfc94752b8644bb33b281e6fa15e2037a7340325b12b704591a5bd5381b4
12. 0xef1802ec08c5a2efaca6aadccc58edcebeb620a019383dc0785f198c677a9427
13. 0x06064dc1eb2363bec8c2a752e0a28aafc4bf0cb21d1b1b755821c1575bb77a96
14. 0xc4fe2177880ea1b0e82b6fe4c270090fd0fbe5af3a42a8cbf6a6ba2fa35625f6
15. 0x15039087bf60ae9b06b756ec3cbc299760e59923a438bbd91e34d105186db0ed
16. 0x2b6e23e3624a1b66e1d2298cfbce99a93ce6b13d24a58112a71802d79c5f7a76
17. 0xd21942ae3214eff88e08ab04884fd4b11958b51af9a0741b7668e2d07a2c56c9
18. 0x9a9024edb5069d88a324facb310a5ce8e495214bbaa968f077bede437390194f
19. 0x9b9ce5b74b9bab5121612ef6b64920a8d453cbf311096a423eef9702747e868a

Day root

0xf43e8dcc3d451a4788b26be904c55e8c4c0fa75c9666796c51db38d37e2c0df8

Chained

0x702d5ac508f08b0d1accf36af25822d8e5660367494edd17a642fb61e158a57a

Published

On Arc Testnet, block 69251483: 0x495162f8936e19f0039918feebe6c307f327cd6bf8c37219620b1970041fa9ae