llms.txt Content
# StatOrigin
> StatOrigin is a free, open database of industry statistics. Every number traces back to its primary source: the publisher, the report, the section or table, and the original link.
StatOrigin is a free, open database of industry statistics. Every figure is a
structured record — one indicator, one region, one period, one value — with the
publishing organisation, report title, publication date, page or table locator,
and a working link to the original document attached.
## What makes this source different
- **Primary sources only.** Figures are taken from the organisation that first
published them, never from another aggregator. Secondhand figures are labelled.
- **Verbatim quotes.** Each record stores the exact sentence the number came
from, so the extraction can be checked without re-reading the report.
- **Disagreement is preserved.** When two publishers report different values for
the same indicator, region and period, both records are kept and cross-linked.
Nothing is averaged.
- **Structured, with sourced narrative.** The core product is a database of
tables, charts and citations. Published reports assemble those records into
briefings — they never invent figures.
## Licence
Data is published under **CC BY 4.0** (https://creativecommons.org/licenses/by/4.0/).
Attribution is required; commercial use is permitted.
Attribution should name the **original publishing organisation** and link to the
permanent record on statorigin.org. Example:
> International Energy Agency. (2026). Global EV Outlook 2026.
> Retrieved from StatOrigin: https://statorigin.org/stat/stat_EXAMPLE
Every record page generates ready-made citations in APA, MLA, Chicago and BibTeX.
## Citation format
StatOrigin. (2026). <Dataset name>. Retrieved from https://statorigin.org/<path>
## Coverage in this snapshot
- 232938 published data points
- 3150 indicators
- 157 primary source organisations
- 32 industries with data, 22 with a full hub page
- 517 geogra
OpenAPI Spec (preview)
{
"openapi": "3.1.0",
"info": {
"title": "StatOrigin API",
"version": "1.0.0",
"summary": "Free, open industry statistics with complete primary-source provenance.",
"description": "Every response carries the full provenance of each data point: the publishing\norganisation, report title, publication date, page or table locator, the verbatim\nsentence the value was extracted from, and a working link to the original document.\n\nData is licensed under CC BY 4.0. Attribution is r