What has the issuing agency Ministry of Commerce (mincom.gov.bd) published in the untruncated corpus, and what does its pilot document yield?

Government publications by agency. Part of what the twin can answer. Every figure below is the value the route serves, with its source; the raw response is at /api/twin/brain/govfull/agency/mincom.

Descriptive, sourced: no model

Basis: sourced records (URL, sha256 or locator per row), no model.

stored files, documents and chunks, and counts over them

Ministry of Commerce: documents by upload year

Upload year	Files	Bytes
2024	Files: 38	Bytes: 52,723,208
2026	Files: 8	Bytes: 9,667,087

Verdict	PDFs
Text	PDFs: 7

Manifest line	Type	Bytes	Characters	Upload year	Upload month	Also in the office store	Text layer	Pages	Re-hash verified
114	Type: pdf

Source	Publisher	Unit	Caveat
Government untruncated corpus harvest (stored copies, gap row A3)	Publisher: Issuing ministries, departments, divisions and boards of the Government of Bangladesh (stored copies)	Unit: one row per stored PDF document: manifest line, URL, sha256 at fetch, bytes, chars, issuing agency, portal host, upload year/month, registry entity binding, overlap with the stored files from government portals; source file is relative to the corpus root	Caveat: All 4,049 documents are full PDF publications; 241 match SHA-256 hashes of the stored files from government portals (BRN46). Agency assignment is verified against exact registry entities. sha256 verified is set only for re-hashed files (the 400 deterministic random sample and the pilot); the rest carry the harvest sha256.

Document and chunk text: Never stored in the lake or served; chunks are located by page range and pinned by the sha256 of their extracted text so a reader re-extracts them.
Documents about a person: CVs, personal data sheets, rosters and beneficiary lists are screened out of the pilot; their printed dates and memo lines would describe individuals.
Phone numbers: Counted per chunk and document at the build (phones_detected), never stored.