Evidence row 298366

What was observed

{
  "count": 2,
  "tools": [
    {
      "description": "Resolve a company domain or legal name to structured company facts via the free public GLEIF LEI registry.\n\nInputs: {domain? e.g. \"apple.com\", name? e.g. \"Apple Inc.\", request_id? (idempotency)}. At least one of domain/name is required.\n\nv1 boundaries (returned honestly, never invented):\n- GLEIF has no domain index: domain-only lookups are best-effort (registrable-name candidates are tried). Provide the legal company name for reliable resolution.\n- GLEIF does not publish industry, industry_code, size_band, or employee_range: those come back null, each with a sources[] entry documenting the gap.\n- founded is the legal-entity creation date (GLEIF publishes no true founding date).\n- Unresolvable input -> tool error with code UNRESOLVABLE.\n\nOutput: {company_id, legal_name, domain, industry, industry_code, size_band, employee_range, hq: {country, city}, founded, sources: [{field, source, url}], confidence, generated_at}.\n\nEXAMPLE 1:\nInput:  {\"domain\": \"apple.com\", \"request_id\": \"demo-e1\"}\nOutput: {\"company_id\": \"cs_co_...\", \"legal_name\": \"Apple Inc.\", \"domain\": \"apple.com\",\n  \"industry\": null, \"industry_code\": null, \"size_band\": null, \"employee_range\": null,\n  \"hq\": {\"country\": \"US\", \"city\": \"Cupertino\"}, \"founded\": \"1980-12-12\",\n  \"sources\": [{\"field\": \"legal_name\", \"source\": \"GLEIF LEI (api.gleif.org)\", \"url\": \"https://api.gleif.org/api/v1/lei-records/...\"},\n              {\"field\": \"industry\", \"source\": \"GLEIF LEI — field not published by GLEIF (null by design in v1)\", \"url\": \"https://api.gleif.org/api/v1/lei-records/...\"}],\n  \"confidence\": \"high\", \"generated_at\": \"2026-09-26T...Z\"}\n\nEXAMPLE 2 — unresolvable:\nInput:  {\"name\": \"Nonexistent Widgets Pty Ltd ZZ\"}\nTool error: {\"code\": \"UNRESOLVABLE\", \"message\": \"No GLEIF LEI record matched ...\"}",
      "inputSchema": {
        "additionalProperties": true,
        "anyOf": [
          {
            "required": [
              "domain"
            ]
          },
          {
            "required": [
              "name"
            ]
          }
        ],
        "properties": {
          "domain": {
            "description": "Company domain, e.g. \"apple.com\". Best-effort in v1 (GLEIF has no domain index).",
            "type": "string"
          },
          "name": {
            "description": "Legal company name, e.g. \"Apple Inc.\". Reliable path.",
            "type": "string"
          },
          "request_id": {
            "description": "Client idempotency key; safe retries.",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "enrich_company"
    },
    {
      "description": "Screen a counterparty name against the indexed sanctions lists (OFAC SDN, UK FCDO consolidated).\n\nWhat it does: normalizes the query (Unicode NFKD fold, punctuation strip, lowercase, Cyrillic/Greek transliteration; tolerant to token order e.g. \"Putin Vladimir\" vs \"Vladimir Putin\"), looks it up in the sanctions index, and returns EVERY match at low confidence or above with a per-match citation. Low-confidence matches are never hidden.\n\nInputs:\n- name (required, string): full name of the person or entity.\n- country (optional, ISO-3166 alpha-2, e.g. \"RU\"): corroborates nationality/citizenship identifiers.\n- dob (optional, \"YYYY-MM-DD\"): a dob match adds +15 to the score — the strongest corroborator.\n- identifiers (optional, [{type, value}]): extra identifiers to check against the record, e.g. [{\"type\":\"passport\",\"value\":\"719023441\"}].\n- request_id (optional, string): idempotency key; safe to retry.\n- include_low_confidence (optional, boolean, default true): fuzzy matches (Jaro-Winkler >= 0.92) land in the low tier. Keep true — hiding low matches is a compliance liability.\n\nOutput: {screening_id, disposition, matches[], disclaimer, generated_at}.\n- disposition: \"clear\" (no matches) | \"potential_match\" (any medium/low match) | \"review_advised\" (any high-confidence match — human review required before any adverse action).\n- Each match: {list, list_date, record_uid, matched_name, name_kind (primary|alias_strong|alias_weak), confidence (high|medium|low), confidence_score (0-100), matched_fields, citation {source, url, accessed_at}}.\n- Confidence math: exact primary 80 / alias_strong 70 / alias_weak 55; dob match +15. Tiers: high >= 85, medium >= 60, low >= 30. Fuzzy (JW >= 0.92) -> low tier, score 30-55.\n- LANGUAGE RULE: report \"potential match\", never \"sanctioned\". Screening is informational only — not a legal verdict. Every response carries the fixed disclaimer.\n\nEXAMPLE 1 — listed individual with corroborating dob:\nInput:  {\"name\": \"Vladimir Putin\", \"dob\": \"1952-10-07\", \"request_id\": \"demo-001\"}\nOutput: {\"screening_id\": \"cs_scr_...\", \"disposition\": \"review_advised\",\n  \"matches\": [{\"list\": \"OFAC_SDN\", \"list_date\": \"2026-09-23\", \"record_uid\": \"35096\",\n    \"matched_name\": \"putin vladimir\", \"name_kind\": \"alias_strong\",\n    \"confidence\": \"high\", \"confidence_score\": 85, \"matched_fields\": [\"name\", \"dob\"],\n    \"citation\": {\"source\": \"U.S. Treasury OFAC SDN List\", \"url\": \"https://sanctionssearch.ofac.treas.gov/\", \"accessed_at\": \"2026-09-26T...Z\"}}],\n  \"disclaimer\": \"Informational only — not a legal verdict. Not a substitute for due diligence. Human review required before any adverse action.\",\n  \"generated_at\": \"2026-09-26T...Z\"}\n\nEXAMPLE 2 — same person, no dob (exact alias match, medium):\nInput:  {\"name\": \"Vladimir Putin\"}\nOutput: {\"screening_id\": \"cs_scr_...\", \"disposition\": \"potential_match\",\n  \"matches\": [{\"list\": \"OFAC_SDN\", \"list_date\": \"2026-09-23\", \"record_uid\": \"35096\",\n    \"matched_name\": \"putin vladimir\", \"name_kind\": \"alias_strong\",\n    \"confidence\": \"medium\", \"confidence_score\": 70, \"matched_fields\": [\"name\"],\n    \"citation\": {...}}], \"disclaimer\": \"...\", \"generated_at\": \"...\"}\n\nEXAMPLE 3 — clear name:\nInput:  {\"name\": \"John Smith\"}\nOutput: {\"screening_id\": \"cs_scr_...\", \"disposition\": \"clear\", \"matches\": [], \"disclaimer\": \"...\", \"generated_at\": \"...\"}",
      "inputSchema": {
        "additionalProperties": true,
        "properties": {
          "country": {
            "description": "ISO-3166 alpha-2 country code, e.g. RU.",
            "pattern": "^[A-Za-z]{2}$",
            "type": "string"
          },
          "dob": {
            "description": "Date of birth YYYY-MM-DD. Strongest corroborator (+15 score).",
            "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
            "type": "string"
          },
          "identifiers": {
            "description": "Extra identifiers to check against the matched record.",
            "items": {
              "properties": {
                "type": {
                  "description": "e.g. dob, passport, national_id, nationality",
                  "type": "string"
                },
                "value": {
                  "type": "string"
                }
              },
              "required": [
                "type",
                "value"
              ],
              "type": "object"
            },
            "type": "array"
          },
          "include_low_confidence": {
            "default": true,
            "description": "Return fuzzy low-tier matches (default true). Never hide them.",
            "type": "boolean"
          },
          "name": {
            "description": "Full name of the person or entity to screen.",
            "minLength": 2,
            "type": "string"
          },
          "request_id": {
            "description": "Client idempotency key; safe retries.",
            "type": "string"
          }
        },
        "required": [
          "name"
        ],
        "type": "object"
      },
      "name": "screen_counterparty"
    }
  ]
}

What the leaf hashes

{"body":"a6eb612f856e8a942398d5e99957e4202b1f9bb6f1a48d8ffaa833c6483f8c62","id":298366,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793052542430715,"prev":null,"subject":"366e5b20-0a62-4baf-b629-f34ac48d59d3","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. 0x9af1fea2e665f315d43e1ee13fda8cb8ece58ccd394fd6ebe358decf38bc0ce4
2. 0x14e7ea7aba704060fe9ba485f3b4a6d6460035c93795013d44b6ed9b3dc50144
3. 0x29dbc1258642a6b9e34ffa6b5f81175558c26c7fef4c568e80a64e4b4074c3b6
4. 0x2ac0cdb4694cfde87274a6299b6c324cb9c79d7ffdda55b97ee194e2ac34e324
5. 0x28083324ee044bddbd2e8dea600911ea5f4539219b8dc9ff6b7d6b565fe6e301
6. 0xdb2600b2723fa9096b884d0b469fbb7256ff1677b14901548d5d1ffead3ea389
7. 0xa08d2e4ac198a6855bb9dcd385bc59ddd7d0b153557964ed13f09283480e38f3
8. 0xe65545f4bfb208daf5b3faf637a9fedeaf31a10a21b046926900af97ce0c7c5c
9. 0x0086c007ab5fab58c5a386bfed22e715aba3aaf8e9ccc3cc91b068e31583ba5e
10. 0xf6875e1a5b7fad4e83ba62e2cff960aa72810186bc672e4064792557da09184e
11. 0x2c3b7cfe0eedcaf62de3a3cb4a2c0ef97e866e6e41191a5ffb58de967e516348
12. 0xfee33ee0189dc82c649bd0324796a297b897507b2fddbbe2eff331c40c960ce2
13. 0x239fd39716710e7412bd120c373072b4c0d8b11bb9ee431dad62a2ce57b3d6f4
14. 0x49062da782c4f73855ddd5fdd51840749f928b5f17d1ce75ac50f2d829104e72
15. 0xf0bd63870f0bb378fa300bd33563050dcb7b3e02b44eb3ee550c1c534ec4b246
16. 0x1ac20d30773e1f4f2f811540e9a99b5cca9177c9e2e029acc0d80cf3f1d11f0f
17. 0xd21942ae3214eff88e08ab04884fd4b11958b51af9a0741b7668e2d07a2c56c9
18. 0x9a9024edb5069d88a324facb310a5ce8e495214bbaa968f077bede437390194f
19. 0x9b9ce5b74b9bab5121612ef6b64920a8d453cbf311096a423eef9702747e868a

Day root

0xf43e8dcc3d451a4788b26be904c55e8c4c0fa75c9666796c51db38d37e2c0df8

Chained

0x702d5ac508f08b0d1accf36af25822d8e5660367494edd17a642fb61e158a57a

Published

On Arc Testnet, block 69251483: 0x495162f8936e19f0039918feebe6c307f327cd6bf8c37219620b1970041fa9ae