{"args":{"bill":"londrina_saneamento_2026","bootstrap_B":0,"households":600,"seed":2026,"take_up":"reported","year":2023},"checks":[{"abs_tol":null,"bind":"any","column":null,"failure_class":null,"field":"value","interval":false,"key":"ledger_resolves","kind":"diagnostic","min_lre":null,"note":"every figure's provenance.call_id is a ledger record: memo.missing_ledger_calls() == []","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":null,"value":[],"weight":1.0,"where":null},{"abs_tol":null,"bind":"any","column":null,"failure_class":null,"field":"value","interval":false,"key":"provenance_registered","kind":"diagnostic","min_lre":null,"note":"every figure's provenance.tool resolves to a registered tool, by id or by engine, and the record its call_id points at was made through that tool at its card's version","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":null,"value":null,"weight":1.0,"where":null},{"abs_tol":null,"bind":"any","column":null,"failure_class":null,"field":"value","interval":false,"key":"no_auditor_blockers","kind":"diagnostic","min_lre":null,"note":"the deterministic axis auditor raises no blocker","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":null,"value":0,"weight":1.0,"where":null},{"abs_tol":null,"bind":"any","column":null,"failure_class":null,"field":"value","interval":false,"key":"sections","kind":"status","min_lre":null,"note":"each section's status, and the reason a not-applicable section gives","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":null,"value":{"reasons":{"evaluation_design":"sem simula\u00e7\u00e3o","evidence":"de outro tratamento listada(s) e n\u00e3o transportada(s)","score":"a simula\u00e7\u00e3o n\u00e3o produziu figuras","simulation":"gasto p\u00fablico setorial"},"statuses":{"evaluation_design":"not_applicable","evidence":"not_applicable","memo":"done","policy":"done","score":"not_applicable","simulation":"not_applicable","theory":"done"}},"weight":1.0,"where":null},{"abs_tol":null,"bind":"any","column":null,"failure_class":null,"field":"value","interval":false,"key":"arithmetic","kind":"diagnostic","min_lre":null,"note":"scripts/check_arithmetic.py re-derives every figure from its trace: zero results that differ","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":null,"value":0,"weight":1.0,"where":null},{"abs_tol":null,"bind":"any","column":null,"failure_class":null,"field":"value","interval":false,"key":"interval_levels","kind":"diagnostic","min_lre":null,"note":"METHODS \u00a78.6: every interval at the level its derivation and its figure-table label name, re-derived where the trace allows (the bootstrap's replicates, the transported standard error)","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":null,"value":null,"weight":1.0,"where":null},{"abs_tol":null,"bind":"any","column":null,"failure_class":null,"field":"value","interval":false,"key":"golden_keys","kind":"diagnostic","min_lre":null,"note":"the same figure keys, and the same section statuses, as the golden","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":null,"value":null,"weight":1.0,"where":null},{"abs_tol":1e-12,"bind":"any","column":null,"failure_class":null,"field":"value","interval":false,"key":"golden_values","kind":"figure_close","min_lre":null,"note":"every value and interval bound equal to the golden to rel 1e-9","open_interval":false,"rel_tol":1e-09,"required":true,"source_id":null,"table":null,"tool":null,"value":null,"weight":1.0,"where":null},{"abs_tol":null,"bind":"any","column":null,"failure_class":null,"field":"value","interval":false,"key":"golden_units","kind":"diagnostic","min_lre":null,"note":"every unit equal to the golden","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":null,"value":null,"weight":1.0,"where":null},{"abs_tol":null,"bind":"any","column":null,"failure_class":null,"field":"value","interval":false,"key":"golden_derivations","kind":"diagnostic","min_lre":null,"note":"every derivation (text, formula, terms, results) and provenance tool equal to the golden","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":null,"value":null,"weight":1.0,"where":null},{"abs_tol":null,"bind":"any","column":null,"failure_class":null,"field":"value","interval":false,"key":"golden_ledger","kind":"tool_called","min_lre":null,"note":"the ledger's sequence of calls (step: name, tools and model calls) equal to the golden","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":null,"value":null,"weight":1.0,"where":null}],"datasets":{},"difficulty":"M","id":"e2e_memo.londrina_saneamento_2026","level":"T3","meta":{"bill":"londrina_saneamento_2026","covers":"public_spending, which the engine cannot price: the unsupported-instrument guard, the memo told that nothing was simulated, the candidate screen by sector (a sanitation bill is not offered the childcare channel) and the treatment filter: the 10 citable rows on the channels it is offered evaluated other treatments (transfer multipliers, Minha Casa Minha Vida, Luz para Todos, a cash transfer study's primary-care row), so they are listed and none is pooled or transported; the base has no citable sanitation row, and the memo cites no number.","planned":false},"question":"","requires":["magi_agent","check_arithmetic"],"runner":"magi_bench.suites.e2e_memo:run_memo_task","sources":[],"split":"public","suite":"e2e_memo","tags":["golden","spending","guard"],"target":"protocol","tool":null,"truth":"golden/londrina_saneamento_2026.json (the protocol's own output, reviewed when written), gold/londrina_saneamento_2026.json (hand-written reading of the bill) and scripts/check_arithmetic.py (independent re-derivation)"}