Verify a claimed statistic against the official source
verify_statVerify economic claims against official World Bank, IMF, ECB data. Receive verdict, official value, error diagnostics, and citation to prevent publishing wrong statistics.
Instructions
Check a claimed economic figure (from a draft, article, or memory) against the official statistical series and get a verdict: match, close, mismatch, or cannot_verify — with the official value, the difference, diagnostics for classic errors (wrong year, percent-vs-decimal, unit scaling), and a full citation for the correct number. Honesty contract: when the official source cannot support a judgment (source down, no published value, fallback vintage risk), the verdict is cannot_verify with the reason — never a guess. Supports historical IMF-vintage checks via as_of. Use this before publishing any economic statistic in a report, brief, or article.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| as_of | No | Historical IMF-vintage verification: judge the claim against the dated IMF WEO edition resolved from this date — e.g. '2019-04', '2019' — instead of today's live data. Resolution is a conservative month calendar (editions flip May 1 / Nov 1, not the IMF's exact release days) and always verifies against a dated WEO edition even when the indicator's live primary is World Bank WDI or the IMF Fiscal Monitor — the response's as_of object and notes disclose both, so present results as 'matched the IMF WEO {vintage} edition', never 'was true at the time'. Recent editions serve from the IMF's own dated vintage dataflows (api.imf.org) directly, with DBnomics's dated editions as the deep archive — the citation names which one served. Only supported for the six WEO-dated registry indicators (gdp_growth, current_account_gdp, govt_debt_gdp, fiscal_balance_gdp, govt_revenue_gdp, govt_expenditure_gdp); rejects with advice otherwise, and impossible calendar dates are rejected. | |
| period | Yes | Period of the claim, usually a year: '2024'. | |
| country | No | Country for registry indicators / World Bank series. | |
| indicator | Yes | Registry key ('inflation_cpi', 'gdp_growth', …) or explicit series id ('worldbank/FP.CPI.TOTL.ZG', 'imf/NGDP_RPCH', 'dbnomics/IMF/WEO:latest/USA.NGDP_RPCH.pcent_change'). | |
| claimed_value | Yes | The value as claimed (in the series' own units). | |
| strict_source | No | Reproducibility mode: never verify against a fallback source — error instead if the primary source fails. Default false; without it, a verify served from a transient-failure fallback returns cannot_verify with the fallback value as indicative (fallback_used=true), while a fallback for a series the primary permanently lacks (e.g. Taiwan in WDI) is judged normally with disclosure. | |
| tolerance_abs | No | Optional absolute tolerance in series units (e.g. 0.1 percentage points). | |
| tolerance_pct | No | Optional relative tolerance in percent. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| notes | Yes | ||
| period | Yes | ||
| series | Yes | ||
| verdict | Yes | ||
| citation | Yes | ||
| difference | Yes | ||
| diagnostics | Yes | ||
| explanation | Yes | ||
| claimed_value | Yes | ||
| is_projection | Yes | ||
| status_method | Yes | ||
| official_value | Yes | ||
| observation_status | Yes | ||
| relative_difference_pct | Yes |