Auditor Comment Extractor

Pull the independent auditor's report — opinion, basis, key audit matters, and emphasis-of-matter — into a structured document.

Request early access →See the SourceGraph pipeline

auditor-comment-extractor.run

> extract --auditor ar_FY24.pdf
INDEPENDENT AUDITOR'S REPORT
Opinion type:           Unmodified
Basis for opinion:      [text block]
Key Audit Matters:      3
  KAM 1  Revenue recognition
  KAM 2  Impairment of goodwill
  KAM 3  Litigation provisions
Emphasis of Matter:     1
Other matters:          —

source: ar_FY24.pdf · p.110-117

// EXAMPLE INPUT

command

$ extract --auditor ar_FY24.pdf

// EXAMPLE OUTPUT

output

INDEPENDENT AUDITOR'S REPORT
Opinion type:           Unmodified
Basis for opinion:      [text block]
Key Audit Matters:      3
  KAM 1  Revenue recognition
  KAM 2  Impairment of goodwill
  KAM 3  Litigation provisions
Emphasis of Matter:     1
Other matters:          —

source: ar_FY24.pdf · p.110-117

// EXTRACTION LOGIC

Auditor's report sections are identified by ISA-700 / SA-700 headings. Opinion type is classified as Unmodified, Qualified, Adverse, or Disclaimer.

// SOURCE-LINKED OUTPUT

Each section keeps its PDF page range. Every KAM keeps its full text and the 'how the matter was addressed in our audit' paragraph as separate fields.

anchor (per value)

{ file, page, table_id, row_id, cell_id, label, value, unit, period }

// FAQ

Are qualifications and modifications flagged?

Yes. The opinion type is classified and any qualifications are extracted with their full text.

Are KAMs kept as separate items?

Yes — each Key Audit Matter is a row with title, description, and the auditor's response.

Is CARO covered?

Yes. The Companies (Auditor's Report) Order annexure is extracted as a separate structured section.

// RELATED TOOLS

Financial Statements

Notes to Accounts Extractor

Pull individual notes from the Notes-to-Accounts section into structured tables and text blocks.

Financial Statements

Financial Statement Extractor

Pull the three core financial statements — Balance Sheet, P&L, and Cash Flow — into a clean, comparable workbook.

Transcripts

Management Commentary Extractor

Pull the management discussion section — opening remarks and segment commentary — from earnings calls and annual reports.

// EARLY ACCESS

Get early access to the Auditor Comment Extractor

Paper Data is currently in private beta. Request access to start converting your financial documents into source-linked tables.

Request early access →See the SourceGraph framework