{
  "schemaVersion": 1,
  "generated": "2026-09-02",
  "asOf": "2026-09-02",
  "source": "Counted from the VVDex Forge factory record and the engine's own founder catalog (vvdex-env `catalog --workspace <studio> --audience founder`), read 2026-08-31, plus the two exams certified on 2026-09-02 in the families-0902 campaign workspace (vvdex.browser.order-desk-1, vvdex.harness.fault-recovery-1): seed, freeze, gold, grader, attack, eval in Docker, receipts packaged.",
  "failClosed": {
    "rule": "An exam appears on this page only if its own site-listing GO flag is true. The flag is off for every exam in this file, so the page lists none. Nothing is inferred from a family, a classification, or a certification result.",
    "engineEquivalent": "vvdex_env.listing.public_listing_block_reason — the same rule the engine applies, whose last requirement is an explicit human GO.",
    "publicCatalogCheck": "`catalog --audience public` returned an empty environment list on 2026-08-31; no listing GO has been given since."
  },
  "totals": {
    "certifiedExams": 25,
    "familiesWithACertifiedExam": 14,
    "familiesDeclared": 14,
    "listedPublicly": 0
  },
  "families": [
    {
      "id": "public_oss_swe",
      "label": "Public open-source SWE",
      "status": "active",
      "exams": 11,
      "listed": 0,
      "summary": "A bug fixed upstream by a merged pull request, rebuilt as an exam: the parent tree is the starting point, the maintainers' fix is the reference solution, and a hidden test suite grades the rule the fix establishes rather than the diff."
    },
    {
      "id": "terminal_ops",
      "label": "Terminal operations",
      "status": "active",
      "exams": 2,
      "listed": 0,
      "summary": "The model gets a shell inside a network-none box and is graded on the end state of the workspace, never on the commands it chose to get there."
    },
    {
      "id": "math_property",
      "label": "Algorithms, graded by property",
      "status": "active",
      "exams": 1,
      "listed": 0,
      "summary": "Graded by derandomised property tests rather than examples, so a solution that hard-codes the worked examples in the task text fails structurally."
    },
    {
      "id": "swe_quality",
      "label": "Code quality",
      "status": "active",
      "exams": 1,
      "listed": 0,
      "summary": "Hidden tests are the floor. The reward also requires deterministic quality axes measured inside the grade box: lint, dependency surface, complexity delta, and execution of the changed lines."
    },
    {
      "id": "security",
      "label": "Security and permission boundaries",
      "status": "active",
      "exams": 1,
      "listed": 0,
      "summary": "Out-of-scope secrets carrying unique honeytokens, an injected-instruction document, and an approval-gated action whose approval token is absent. Boundary respect is scored from the submitted workspace."
    },
    {
      "id": "mcp_tools",
      "label": "Tool use and MCP",
      "status": "active",
      "exams": 1,
      "listed": 0,
      "summary": "Declared tools with a permission table (allowed / approval / forbidden), dispatched through a checked loop that never touches the real world, recorded to a ledger outside the model's writable paths."
    },
    {
      "id": "rag_grounding",
      "label": "Retrieval and grounding",
      "status": "active",
      "exams": 1,
      "listed": 0,
      "summary": "A corpus with authoritative sources, distractors and outdated sources. Citation correctness is graded as strictly as the answer, and saying the evidence is insufficient is itself a graded axis."
    },
    {
      "id": "long_term_memory",
      "label": "Cross-session memory",
      "status": "active",
      "exams": 1,
      "listed": 0,
      "summary": "The exam runs across sessions with state carried between them. A fact is deliberately changed in the authoritative source, and the grader checks whether the model updates from the newer evidence or lets stale carried memory win."
    },
    {
      "id": "document_office",
      "label": "Structured document work",
      "status": "active",
      "exams": 1,
      "listed": 0,
      "summary": "Structured inputs and a rules statement in, a reconciled output file out. The grader checks the end state exactly, including the credit note, the overpayment, the rounding and the excluded currency."
    },
    {
      "id": "customer_support",
      "label": "Customer support",
      "status": "active",
      "exams": 1,
      "listed": 0,
      "summary": "A scripted scenario, never a free-form model user, so the exam stays deterministic. The grader checks the action against policy and whether the model claimed an action it never performed."
    },
    {
      "id": "data_sql",
      "label": "Data and SQL",
      "status": "active",
      "exams": 1,
      "listed": 0,
      "summary": "The model writes a query; the grader executes it against the real dataset in the grade box and compares the result set to ground truth computed at authoring time. Write-safety is part of the grade."
    },
    {
      "id": "vvdex_internal_swe",
      "label": "Internal VVDex SWE",
      "status": "active",
      "exams": 1,
      "listed": 0,
      "neverListable": true,
      "summary": "Built from our own codebase. Never listed publicly, by an engine rule and not by a decision taken per exam."
    },
    {
      "id": "harness_eval",
      "label": "Harness evaluation",
      "status": "active",
      "exams": 1,
      "reason": "The model-plus-harness's behaviour under adversarial tool conditions: a declared, deterministic fault schedule applied inside the tool loop, graded from the recorded trace and the end state."
    },
    {
      "id": "browser",
      "label": "Browser and computer use",
      "status": "active",
      "exams": 1,
      "reason": "A real web application driven in a real headless Chromium inside the network-none box; graded on the application's end state, its audit log and the engine's action ledger, all outside the writable paths."
    }
  ],
  "declaredNotActive": [],
  "exams": [
    {
      "ref": 1,
      "family": "public_oss_swe",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 2,
      "family": "public_oss_swe",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 3,
      "family": "public_oss_swe",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 4,
      "family": "public_oss_swe",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 5,
      "family": "public_oss_swe",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 6,
      "family": "public_oss_swe",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 7,
      "family": "public_oss_swe",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 8,
      "family": "public_oss_swe",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 9,
      "family": "public_oss_swe",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 10,
      "family": "public_oss_swe",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 11,
      "family": "public_oss_swe",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 12,
      "family": "terminal_ops",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 13,
      "family": "terminal_ops",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 14,
      "family": "math_property",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 15,
      "family": "swe_quality",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 16,
      "family": "security",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 17,
      "family": "mcp_tools",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 18,
      "family": "rag_grounding",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 19,
      "family": "long_term_memory",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 20,
      "family": "document_office",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 21,
      "family": "customer_support",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 22,
      "family": "data_sql",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 23,
      "family": "vvdex_internal_swe",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 24,
      "family": "browser",
      "listGo": false,
      "listing": null
    },
    {
      "ref": 25,
      "family": "harness_eval",
      "listGo": false,
      "listing": null
    }
  ],
  "listingFieldNote": "Each exam is a slot, not a record. `listing` stays null while `listGo` is false, so this public file carries no exam id, title, task, repository or score for an exam that has not been cleared for listing. Flipping a flag means writing that exam's listing block at the same time; nothing private can leak by a flag alone.",
  "listingShape": {
    "environmentId": "string — the exam id",
    "version": "string",
    "title": "string — the exam's one-line title",
    "family": "string — must equal the slot's family",
    "badge": "string — the highest certification stage this exam has evidence for",
    "certifiedOn": "YYYY-MM-DD"
  }
}