Every record in every BWB dataset follows this exact schema. Machine-ready, GICS-tagged, CC BY 4.0.
{
"omega_id": "string — unique record identifier (UUID)",
"source_family": "string — dataset family id",
"source_name": "string — human-readable source name",
"gics_sector": "string — GICS sector (e.g. 'Information Technology')",
"gics_industry": "string — GICS industry (e.g. 'Semiconductors')",
"data_type": "enum — news | government | biotech | tech | academic | signal | corpus | book | archive",
"timestamp": "ISO-8601 — publication or creation datetime",
"region": "string — country or region (e.g. 'United States', 'Global')",
"entities": "array<string> — named entities extracted from content",
"metadata": {
"update_frequency": "string — how often this family updates",
"confidence": "float 0-1 — guardian verification score",
"version": "string — dataset schema version",
"word_count": "integer — word count of payload body",
"guardian_verified": "boolean — passed BWB quality guardian",
"author": "string — Billy Odell Tucker-Robinson",
"license": "string — CC BY 4.0 — Banking With Billy"
},
"payload": {
"headline": "string — article headline or book title",
"lead": "string — opening paragraph",
"body": "string — full article body",
"why_it_matters": "string — Billy's analysis",
"source_url": "string — original source URL",
"chapters": "array — book chapters (Long-Form Books family only)"
}
}