> ## Documentation Index
> Fetch the complete documentation index at: https://docs.onera.app/llms.txt
> Use this file to discover all available pages before exploring further.

# Us Pds Normalized Text

> Return bounded bytes for an exact active PDS-derived normalized-text proof.

The bytes are base64 encoded so an arbitrary byte range remains lossless even when its edge
splits a UTF-8 code point. ``content_end_byte`` is exclusive. This surface is deliberately
separate from canonical filing content and never falls back to a bare normalization ledger,
a stale derivative, or ``/us/filings/{accession}/content``.
OCR parser suffixes are accepted only with matching source-provenance pipeline evidence.



## OpenAPI

````yaml /openapi.json get /us/pds/submissions/{accession_number}/normalized
openapi: 3.1.0
info:
  title: Corpus API
  description: >-
    Point-in-time financial and governed-document data for the US, India, and
    China.
  version: '2026-07-20'
servers:
  - url: https://corpus-api.onera.app
    description: Production
security: []
paths:
  /us/pds/submissions/{accession_number}/normalized:
    get:
      tags:
        - US · SEC PDS
      summary: Us Pds Normalized Text
      description: >-
        Return bounded bytes for an exact active PDS-derived normalized-text
        proof.


        The bytes are base64 encoded so an arbitrary byte range remains lossless
        even when its edge

        splits a UTF-8 code point. ``content_end_byte`` is exclusive. This
        surface is deliberately

        separate from canonical filing content and never falls back to a bare
        normalization ledger,

        a stale derivative, or ``/us/filings/{accession}/content``.

        OCR parser suffixes are accepted only with matching source-provenance
        pipeline evidence.
      operationId: >-
        us_pds_normalized_text_us_pds_submissions__accession_number__normalized_get
      parameters:
        - name: accession_number
          in: path
          required: true
          schema:
            type: string
            pattern: ^\d{10}-\d{2}-\d{6}$
            title: Accession Number
        - name: start_byte
          in: query
          required: false
          schema:
            type: integer
            minimum: 0
            default: 0
            title: Start Byte
        - name: max_bytes
          in: query
          required: false
          schema:
            type: integer
            maximum: 75000
            minimum: 1
            default: 50000
            title: Max Bytes
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/PdsNormalizedTextResponse'
        '400':
          description: Invalid parameter combination
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Missing or invalid API key
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '403':
          description: Insufficient jurisdiction or scope
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '404':
          description: Unknown resource
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '416':
          description: Byte range starts past EOF
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '422':
          description: Request schema validation failed
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '429':
          description: Rate limit exceeded
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '503':
          description: Source content is unavailable or still processing
          content:
            application/json:
              schema:
                oneOf:
                  - $ref: '#/components/schemas/FilingProcessingErrorResponse'
                  - $ref: '#/components/schemas/ErrorResponse'
      security:
        - X-API-KEY: []
components:
  schemas:
    PdsNormalizedTextResponse:
      properties:
        resource:
          type: string
          const: sec_pds_normalized_text
          title: Resource
          default: sec_pds_normalized_text
        accession_number:
          type: string
          title: Accession Number
        filing_type:
          type: string
          title: Filing Type
        filing_date:
          anyOf:
            - type: string
              format: date
            - type: 'null'
          title: Filing Date
        normalized_sha256:
          type: string
          title: Normalized Sha256
        normalized_byte_size:
          type: integer
          exclusiveMinimum: 0
          title: Normalized Byte Size
        normalized_parser_version:
          type: string
          title: Normalized Parser Version
        content_type:
          type: string
          const: text/plain; charset=utf-8
          title: Content Type
          default: text/plain; charset=utf-8
        encoding:
          type: string
          const: base64
          title: Encoding
          default: base64
        content:
          type: string
          title: Content
        content_start_byte:
          type: integer
          minimum: 0
          title: Content Start Byte
        content_end_byte:
          type: integer
          minimum: 0
          title: Content End Byte
        returned_bytes:
          type: integer
          minimum: 0
          title: Returned Bytes
        total_bytes:
          type: integer
          exclusiveMinimum: 0
          title: Total Bytes
        content_truncated:
          type: boolean
          title: Content Truncated
        next_start_byte:
          anyOf:
            - type: integer
              minimum: 0
            - type: 'null'
          title: Next Start Byte
        content_range_sha256:
          type: string
          title: Content Range Sha256
        source:
          $ref: '#/components/schemas/PdsNormalizedTextSource'
        primary_selection:
          $ref: '#/components/schemas/PdsNormalizedTextPrimarySelection'
        provenance:
          $ref: '#/components/schemas/PdsNormalizedTextProvenance'
      type: object
      required:
        - accession_number
        - filing_type
        - normalized_sha256
        - normalized_byte_size
        - normalized_parser_version
        - content
        - content_start_byte
        - content_end_byte
        - returned_bytes
        - total_bytes
        - content_truncated
        - content_range_sha256
        - source
        - primary_selection
        - provenance
      title: PdsNormalizedTextResponse
    ErrorResponse:
      properties:
        error:
          type: string
          title: Error
        message:
          type: string
          title: Message
        request_id:
          anyOf:
            - type: string
            - type: 'null'
          title: Request Id
      type: object
      required:
        - error
        - message
      title: ErrorResponse
    FilingProcessingErrorResponse:
      properties:
        error:
          type: string
          title: Error
        message:
          type: string
          title: Message
        request_id:
          anyOf:
            - type: string
            - type: 'null'
          title: Request Id
        accession_number:
          type: string
          title: Accession Number
        retry_after_seconds:
          type: integer
          title: Retry After Seconds
      type: object
      required:
        - error
        - message
        - accession_number
        - retry_after_seconds
      title: FilingProcessingErrorResponse
    PdsNormalizedTextSource:
      properties:
        pds_sha256:
          type: string
          title: Pds Sha256
        pds_byte_size:
          type: integer
          exclusiveMinimum: 0
          title: Pds Byte Size
        pds_parser_version:
          type: string
          title: Pds Parser Version
        document_count:
          type: integer
          minimum: 0
          title: Document Count
        archive_id:
          type: string
          title: Archive Id
        archive_family:
          type: string
          title: Archive Family
        archive_url:
          type: string
          title: Archive Url
        archive_date:
          anyOf:
            - type: string
              format: date
            - type: 'null'
          title: Archive Date
        source_kind:
          type: string
          title: Source Kind
        member_ordinal:
          type: integer
          exclusiveMinimum: 0
          title: Member Ordinal
        member_name:
          type: string
          title: Member Name
        source_generation_id:
          type: string
          title: Source Generation Id
        inventory_generation_id:
          type: string
          title: Inventory Generation Id
      type: object
      required:
        - pds_sha256
        - pds_byte_size
        - pds_parser_version
        - document_count
        - archive_id
        - archive_family
        - archive_url
        - source_kind
        - member_ordinal
        - member_name
        - source_generation_id
        - inventory_generation_id
      title: PdsNormalizedTextSource
    PdsNormalizedTextPrimarySelection:
      properties:
        document_name:
          type: string
          title: Document Name
        document_type:
          anyOf:
            - type: string
            - type: 'null'
          title: Document Type
        sequence:
          anyOf:
            - type: string
            - type: 'null'
          title: Sequence
        synthetic_document_name:
          type: boolean
          title: Synthetic Document Name
        payload_derivation:
          anyOf:
            - type: string
            - type: 'null'
          title: Payload Derivation
        ocr_pipeline_contract:
          anyOf:
            - type: string
            - type: 'null'
          title: Ocr Pipeline Contract
        ocr_pipeline_fingerprint:
          anyOf:
            - type: string
            - type: 'null'
          title: Ocr Pipeline Fingerprint
        sha256:
          type: string
          title: Sha256
        byte_size:
          type: integer
          exclusiveMinimum: 0
          title: Byte Size
      type: object
      required:
        - document_name
        - synthetic_document_name
        - sha256
        - byte_size
      title: PdsNormalizedTextPrimarySelection
    PdsNormalizedTextProvenance:
      properties:
        provider:
          type: string
          const: SEC
          title: Provider
          default: SEC
        system:
          type: string
          const: EDGAR PDS
          title: System
          default: EDGAR PDS
        representation:
          type: string
          const: normalized_official_dissemination_submission
          title: Representation
          default: normalized_official_dissemination_submission
        canonical_filing_content:
          type: boolean
          const: false
          title: Canonical Filing Content
          default: false
        normalization_contract_version:
          type: string
          enum:
            - sec-edgar-pds-normalization/v1
            - sec-edgar-pds-residual-normalization/v1
          title: Normalization Contract Version
        source_generation_id:
          type: string
          title: Source Generation Id
        inventory_generation_id:
          type: string
          title: Inventory Generation Id
        completed_at:
          anyOf:
            - type: string
              format: date-time
            - type: 'null'
          title: Completed At
      type: object
      required:
        - normalization_contract_version
        - source_generation_id
        - inventory_generation_id
      title: PdsNormalizedTextProvenance
  securitySchemes:
    X-API-KEY:
      type: apiKey
      in: header
      name: X-API-KEY
      description: >-
        Provisioned Corpus API key with the required jurisdiction and operation
        scopes.

````