Evidence row 562513

What was observed

{
  "count": 4,
  "tools": [
    {
      "description": "Find the real Church Slavonic word(s) whose scientific-Latin transliteration\nmatches this input — the inverse direction of `slavonic_transliterate`. Because\ntransliterate is lossy, this is a LOOKUP against the words already in the\ndictionary cache: attested spellings (normalized OCS Cyrillic) come back as\nsource=dictionary. If none match, a single best-effort reconstruction is returned\n(source=reconstruction, approximate=true) — a guess in normalized OCS Cyrillic, not\nattested, with no Glagolitic or liturgical marks. Coverage grows as words are\ncached, so an identical query may return a reconstruction now and a dictionary hit\nlater.\n",
      "inputSchema": {
        "properties": {
          "text": {
            "description": "Scientific-Latin transliteration of Church Slavonic to resolve back to real orthography. Returns the attested dictionary spelling(s) whose transliteration matches (source=dictionary, exact) — several may match one ambiguous key. On a miss, a single best-effort reconstruction in normalized OCS Cyrillic (source=reconstruction, approximate=true), which is a guess: transliterate is lossy, so case, digraph boundaries (д+з vs ѕ) and the оу/ѿ ligatures cannot be recovered, and no Glagolitic or liturgical marks are produced.",
            "maxLength": 4000,
            "minLength": 1,
            "title": "Text",
            "type": "string"
          }
        },
        "required": [
          "text"
        ],
        "title": "slavonic_detransliterateArguments",
        "type": "object"
      },
      "name": "slavonic_detransliterate"
    },
    {
      "description": "Fetch the full declension (nominals) or conjugation (verbs) table for a\nlemma identified by a search result's inflection handle (entry_id +\nword_class). Use this only when a search ran without inline forms or left a\nmatch un-expanded — a default search already returns each match's table\ninline. Returns Markdown plus the table as structuredContent with the shape\n{\"result\": <paradigm>} per the declared outputSchema — switch on\nresult.category ('nominal' | 'verbal' | 'not_found') before reading the body.\nContent from en.wiktionary.org (CC BY-SA 4.0).\n",
      "inputSchema": {
        "properties": {
          "entry_id": {
            "description": "The Wiktionary page title (the Cyrillic lemma) from a search result's inflection handle, e.g. 'богъ', 'глаголати'.",
            "maxLength": 80,
            "minLength": 1,
            "pattern": "^[Ѐ-ӿꙀ-ꚟⰀ-ⱟ][Ѐ-ӿꙀ-ꚟⰀ-ⱟ\\-']{0,79}$",
            "title": "Entry Id",
            "type": "string"
          },
          "word_class": {
            "description": "The part-of-speech section from a search result's inflection handle, e.g. 'verb', 'noun', 'adjective'.",
            "enum": [
              "abbreviation",
              "acronym",
              "adjective",
              "adverb",
              "affix",
              "article",
              "character",
              "circumfix",
              "classifier",
              "combining form",
              "conjunction",
              "contraction",
              "counter",
              "determiner",
              "diacritical mark",
              "idiom",
              "infix",
              "initialism",
              "interfix",
              "interjection",
              "letter",
              "ligature",
              "noun",
              "number",
              "numeral",
              "participle",
              "particle",
              "phrase",
              "postposition",
              "prefix",
              "preposition",
              "prepositional phrase",
              "pronoun",
              "proper noun",
              "proverb",
              "punctuation mark",
              "romanization",
              "root",
              "suffix",
              "symbol",
              "verb"
            ],
            "title": "Word Class",
            "type": "string"
          }
        },
        "required": [
          "entry_id",
          "word_class"
        ],
        "title": "slavonic_get_inflectionsArguments",
        "type": "object"
      },
      "name": "slavonic_get_inflections"
    },
    {
      "description": "Look an Old Church Slavonic word up on Wiktionary and return its senses\nplus full declension/conjugation tables — attested content (singular, dual\nand plural), not invented. Any form of the word works; an inflected query\nis resolved to its lemma automatically via previously cached paradigms and\nthe result notes the resolution. With search_language='eng' the query is\nan English word instead: the result lists its per-sense Old Church\nSlavonic equivalents (the translations block) plus their expanded entries.\nReturns Markdown plus the same result as structuredContent matching the\ndeclared outputSchema.\n\nResults are cached server-side; first-time queries reach the live upstream\npolitely and calls are rate limited — on a rate-limit error, wait a few\nseconds and retry. Content is from en.wiktionary.org (CC BY-SA 4.0 —\nattribute and share alike if republished).\n",
      "inputSchema": {
        "$defs": {
          "SearchLanguage": {
            "description": "The query language. ``chu`` looks an Old Church Slavonic word up directly\n(any of its forms — an inflected query resolves via cached paradigms). ``eng``\nsearches in reverse: the English Wiktionary page for the query word lists\nper-sense Old Church Slavonic translations, and each distinct lemma is then\nlooked up normally.",
            "enum": [
              "chu",
              "eng"
            ],
            "title": "SearchLanguage",
            "type": "string"
          }
        },
        "properties": {
          "include_forms": {
            "default": true,
            "description": "When true (default), each match's full declension/conjugation table is returned INLINE — usable cases/tenses (singular, dual AND plural) in ONE call, no follow-up slavonic_get_inflections. Set false for a cheap screen of which entries exist. Bounded by a per-search cap — use max_forms to adjust per call. For eng queries this governs the expanded OCS entries; the per-sense translations list itself is always returned.",
            "title": "Include Forms",
            "type": "boolean"
          },
          "max_forms": {
            "anyOf": [
              {
                "maximum": 12,
                "minimum": 0,
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Optional override for how many inflection tables to expand this call (0–12). On an uncached query each table is one politely paced upstream fetch, so high values on cold queries are slow. Omit for the server default.",
            "title": "Max Forms"
          },
          "query": {
            "description": "The word to look up, in the language search_language names. Church Slavonic (default): a SINGLE Old Church Slavonic word in Cyrillic, any form — an inflected form ('бога') is resolved to its lemma ('богъ') automatically via cached paradigms, and the result says so; normalized OCS spelling works best, but titlos/accents and modern-Cyrillic respellings (ы for ꙑ) are folded. English (search_language='eng'): the English word whose Old Church Slavonic equivalents you want — multiword entries like 'apple tree' work.",
            "maxLength": 80,
            "minLength": 1,
            "title": "Query",
            "type": "string"
          },
          "search_language": {
            "$ref": "#/$defs/SearchLanguage",
            "default": "chu",
            "description": "Language the query word is in: 'chu' (default) looks the Old Church Slavonic word up directly; 'eng' finds the OCS equivalents of an English word (per-sense, from Wiktionary's translation tables) and returns their full entries. Glosses are in English either way."
          }
        },
        "required": [
          "query"
        ],
        "title": "slavonic_searchArguments",
        "type": "object"
      },
      "name": "slavonic_search"
    },
    {
      "description": "Render Church Slavonic — Cyrillic or Glagolitic — in the scientific\nLatin transliteration Wiktionary uses (богъ → bogŭ, ⰱⱁⰳⱏ → bogŭ).\nLiturgical reading marks (titlos, accents) are dropped and late Church\nSlavonic spellings folded, so copied liturgical text works as-is. Returns\nMarkdown plus the transliterated output as structuredContent matching the\ndeclared outputSchema. Pure local transform: no dictionary lookup and no\nnetwork.\n",
      "inputSchema": {
        "properties": {
          "text": {
            "description": "Church Slavonic text to transliterate — Cyrillic and/or Glagolitic, one word or whole lines. Liturgical reading marks (titlos, accents, breathings) are dropped and late Church Slavonic spellings folded, so text copied from a liturgical source or a lyrics sheet works as-is.",
            "maxLength": 4000,
            "minLength": 1,
            "title": "Text",
            "type": "string"
          }
        },
        "required": [
          "text"
        ],
        "title": "slavonic_transliterateArguments",
        "type": "object"
      },
      "name": "slavonic_transliterate"
    }
  ]
}

What the leaf hashes

{"body":"13634c1ff0224f776f112d0db44fe1d4ca780f7cad4f9ff7a747569f5f85084e","id":562513,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793137421456810,"prev":null,"subject":"8bfdbd33-55b9-4c01-b932-598391736a77","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. 0xd157fb3bde128a6b580d8ee458a173118974ac3f7445c02b81aed6a599a56169
2. 0x254ea78e1f61bfe9be0434a3807340106fee59584c060f1db8f99180c6917ac0
3. 0x8092e0fd4d6bdf50bf99c94a353fdf41e2996d888974a47b2fa0fb5d23d4c587
4. 0xc67b87c71ad93747c01e500971e4ad4327197e60281249da9d88e7fa4e3336bb
5. 0x458dfb1cf19014c838411074feb5a6bd5ab50f78d68fa0ca04a382303b012699
6. 0xb7c7a85e70bfd9b754e18a5bed95d231060c6a824ccb5b275f302a137805d0e3
7. 0x6d95bf6a995ecc186ff054d6d1ce2f7e98f1e96b45a708ce0fb7730320b99f97
8. 0x4291dd9c1862305d459ccb510710bcb1458b88d89919343d0469324d3e9f45f0
9. 0x15d19b6beb3427d5d5bdffe0389bd82a2f94f7a6ebe45592cc53f8a576a4f258
10. 0x2a6be3f6cbb239f71c335d537add51975f312008b12c2eb28c5a07a128b09e6a
11. 0x17dc78b821725e8c90b54bb9b43579db49b460e76d0f7cc8a2a427dc1f9ea96e
12. 0x171aeb7198e4c29bd794c75ee3b02f70c21f3caa4365d2b304c00b891f1bbc94
13. 0xc66f83a1320fe7c1faf22674eeeb7fae22ecd2f0b102d9619a484291f2ce104a
14. 0x8f676edfb4faaa290229d8f4f69ab721fc627424463d62f5146b3d1ca7f2f0c6
15. 0x969cd44e5a4e8dc3110540398fbf689659eb51df735c1cda5d8f021ef9ff5683
16. 0xa94627de1af0e823832e05a9069b304ecccb8c0cdb8f9cfc4f2039bfb9799dc5
17. 0xdf1105afdc109de3c09a98fc8a3864159ad964e6f49b635c105a27a1e1f14310
18. 0x2bf8151e5f157dd183b9de6fa00469551932a7a6e3f33a694895000ac9061197
19. 0x9fc354c0ea3efc3f1b6548bb77ea902a50f2c9647647ea61592efce2bd795699

Day root

0xdd77e5e99da32c3f154180d63e3c3e6fe11e896a2c6896412ef6b5c4bcf7e795

Chained

0x23bb4dfd09f55c15ac3962f53578e02c6114d5bfd9bb451cf8794fb6e2817ef4

Published

On Arc Testnet, block 69414147: 0xb2ebd83aafeb765a0ce66e76aefb133ed06606c98038fd56191e2bcd1dcb77b4