Class: File

name: File
description: A single file within a dataset or file collection. Represents an individual
  data file, code file, documentation file, etc. Maps to RO-Crate File entities.
from_schema: https://w3id.org/bridge2ai/data-sheets-schema
aliases:
- data file
- file
- file object
exact_mappings:
- schema:DigitalDocument
is_a: Information
slots:
- bytes
- path
- format
- encoding
- compression
- media_type
- hash
- md5
- sha256
- dialect
attributes:
  file_type:
    name: file_type
    description: Semantic type or purpose of this file (e.g., data_file, code_file,
      documentation_file, metadata_file).
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema/file-collection
    rank: 1000
    slot_uri: d4d:fileType
    domain_of:
    - File
    range: FileTypeEnum
class_uri: schema:MediaObject

name: File
description: A single file within a dataset or file collection. Represents an individual
  data file, code file, documentation file, etc. Maps to RO-Crate File entities.
from_schema: https://w3id.org/bridge2ai/data-sheets-schema
aliases:
- data file
- file
- file object
exact_mappings:
- schema:DigitalDocument
is_a: Information
attributes:
  file_type:
    name: file_type
    description: Semantic type or purpose of this file (e.g., data_file, code_file,
      documentation_file, metadata_file).
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema/file-collection
    rank: 1000
    slot_uri: d4d:fileType
    alias: file_type
    owner: File
    domain_of:
    - File
    range: FileTypeEnum
  bytes:
    name: bytes
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: '10485760'
    description: Size of the data in bytes.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcat:byteSize
    alias: bytes
    owner: File
    domain_of:
    - File
    range: integer
  path:
    name: path
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: data/example_cohort/participants.csv
    description: The file path or URL where the content is located.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: schema:contentUrl
    alias: path
    owner: File
    domain_of:
    - File
    - FileCollection
    range: string
  format:
    name: format
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: CSV
    description: The file format, physical medium, or dimensions of a resource. This
      should be a file extension or MIME type.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:format
    alias: format
    owner: File
    domain_of:
    - DistributionFormat
    - File
    range: FormatEnum
  encoding:
    name: encoding
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: UTF-8
    description: The character encoding of the data.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: d4d:characterEncoding
    alias: encoding
    owner: File
    domain_of:
    - File
    range: EncodingEnum
  compression:
    name: compression
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: zip
    description: Compression format used, if any (e.g., gzip, bzip2, zip).
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcat:compressFormat
    alias: compression
    owner: File
    domain_of:
    - Information
    - File
    - FileCollection
    range: CompressionEnum
  media_type:
    name: media_type
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: text/csv
    description: The media type of the data. This should be a MIME type.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    exact_mappings:
    - schema:encodingFormat
    rank: 1000
    slot_uri: dcat:mediaType
    alias: media_type
    owner: File
    domain_of:
    - DistributionFormat
    - File
    range: MediaTypeEnum
  hash:
    name: hash
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855
    description: Cryptographic hash value of the data for integrity verification,
      where the algorithm is recorded alongside or implied by context. Prefer the
      specific `sha256` slot when the algorithm is known. State the algorithm with
      the value when using this slot, since a bare digest cannot be verified without
      knowing what produced it.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    broad_mappings:
    - dcterms:identifier
    rank: 1000
    slot_uri: d4d:hashValue
    alias: hash
    owner: File
    domain_of:
    - File
    range: string
  md5:
    name: md5
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: d41d8cd98f00b204e9800998ecf8427e
    description: DEPRECATED. MD5 hash value of the data (128-bit). MD5 is not collision-resistant
      and is unsuitable for integrity verification; it is retained only so that records
      written before this deprecation remain readable. Use `sha256`, or `hash` where
      the algorithm varies.
    deprecated: Use sha256 instead; MD5 is not collision-resistant.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    broad_mappings:
    - dcterms:identifier
    rank: 1000
    slot_uri: d4d:md5Checksum
    alias: md5
    owner: File
    domain_of:
    - File
    range: string
  sha256:
    name: sha256
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855
    description: SHA-256 hash value of the data (256-bit cryptographic hash, recommended).
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: schema:sha256
    alias: sha256
    owner: File
    domain_of:
    - File
    range: string
  dialect:
    name: dialect
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: RFC4180
    description: Specific format dialect or variation (e.g., CSV dialect, JSON-LD
      profile).
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: schema:encodingFormat
    alias: dialect
    owner: File
    domain_of:
    - File
    range: string
  conforms_to:
    name: conforms_to
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: Brain Imaging Data Structure (BIDS) v1.9.0
    description: 'A standard or specification the **dataset''s own content** follows
      — an imaging, waveform, file-layout or common-data-model standard such as DICOM,
      WFDB, BIDS, OMOP CDM, Open mHealth or ESDS. Not the schema this datasheet is
      written in: that is `conforms_to_schema`.'
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:conformsTo
    alias: conforms_to
    owner: File
    domain_of:
    - Information
    range: string
  conforms_to_class:
    name: conforms_to_class
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: Dataset
      d4d:perRecord:
        tag: d4d:perRecord
        value: true
    description: The class within `conforms_to_schema` that this record instantiates
      — `Dataset` for a full datasheet, `CoreDataset` for a core one. Like `conforms_to_schema`,
      a statement about the record rather than the data.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    broad_mappings:
    - dcterms:conformsTo
    rank: 1000
    slot_uri: d4d:conformsToClass
    alias: conforms_to_class
    owner: File
    domain_of:
    - Information
    range: string
  conforms_to_schema:
    name: conforms_to_schema
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: https://w3id.org/bridge2ai/data-sheets-schema
      d4d:perRecord:
        tag: d4d:perRecord
        value: true
    description: The metadata schema **this record itself** is written in — normally
      `https://w3id.org/bridge2ai/data-sheets-schema`. A statement about the datasheet,
      not about the data it describes; a standard the *data* follows belongs in `conforms_to`.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    broad_mappings:
    - dcterms:conformsTo
    rank: 1000
    slot_uri: d4d:conformsToSchema
    alias: conforms_to_schema
    owner: File
    domain_of:
    - Information
    range: string
  conforms_to_standard:
    name: conforms_to_standard
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: BIDS
    description: 'Which registered data standard `conforms_to` names, where one applies
      — a term rather than prose, so the corpus can be queried for "what standards
      does this follow?" (#403).

      `conforms_to` records what the sources say, in their words. This records which
      standard that is. Populate both for the same standard: one is verbatim evidence,
      the other is the normalized term, and they answer different questions.

      Use `OTHER` when the sources name a standard this vocabulary lacks, and keep
      the name in `conforms_to` so nothing is lost. Never pick a near-neighbour —
      reporting BIDS because a dataset is neuroimaging, when the sources say otherwise,
      is an invention.'
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:conformsTo
    alias: conforms_to_standard
    owner: File
    domain_of:
    - Information
    range: DataStandardEnum
    multivalued: true
  created_by:
    name: created_by
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: orcid:0000-0002-1234-5678
    description: The person or organization primarily responsible for creating the
      resource.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:creator
    alias: created_by
    owner: File
    domain_of:
    - Information
    range: string
  created_on:
    name: created_on
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: '2021-03-01T00:00:00Z'
    description: The date and time when the resource was created. Requires a UTC offset
      (`…T00:00:00Z`); RFC 3339 `date-time` rejects a naive timestamp.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:created
    alias: created_on
    owner: File
    domain_of:
    - Information
    range: datetime
  doi:
    name: doi
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: 10.xxxxx/example.1234
    description: 'Digital Object Identifier (DOI) in format 10.xxxx/xxxxx — a registrant
      prefix, a slash, a suffix — providing persistent identification. The bare DOI
      only — not the doi: CURIE and not the doi.org resolver URL. The pattern is anchored
      (#646): unanchored, JSON Schema''s search semantics accepted all three surface
      forms, and one v5 record carried the same DOI three ways. The 2026-08-20b arm
      already writes the bare form; records written before the anchor keep the validation
      verdicts they were pinned with (#426) and are not rewritten (#520).'
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    exact_mappings:
    - schema:identifier
    broad_mappings:
    - dcterms:identifier
    rank: 1000
    slot_uri: d4d:doiIdentifier
    alias: doi
    owner: File
    domain_of:
    - Information
    range: string
    pattern: ^10\.\d{4,}\/.+$
  download_url:
    name: download_url
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: https://example.org/datasets/example-cohort/download
    description: URL from which the data can be downloaded. This is not the same as
      the landing page, which is a page that describes the dataset. Rather, this URL
      points directly to the data itself.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    exact_mappings:
    - schema:url
    rank: 1000
    slot_uri: dcat:downloadURL
    alias: download_url
    owner: File
    domain_of:
    - Information
    - DistributionFormat
    range: uri
  issued:
    name: issued
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: '2022-06-30T00:00:00Z'
    description: Date of formal issuance or publication of the resource. A `datetime`
      renders as RFC 3339 `date-time`, which **requires a UTC offset** — write `2024-11-15T00:00:00Z`,
      not `2024-11-15T00:00:00`. A date alone is also rejected.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:issued
    alias: issued
    owner: File
    domain_of:
    - Information
    range: datetime
  keywords:
    name: keywords
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: chronic disease, medical imaging, multimodal, clinical data
    description: Keywords or tags describing the resource for discovery and classification.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcat:keyword
    alias: keywords
    owner: File
    domain_of:
    - Information
    range: string
    multivalued: true
  language:
    name: language
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: en
    description: Language in which the information is expressed.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    exact_mappings:
    - schema:inLanguage
    rank: 1000
    slot_uri: dcterms:language
    alias: language
    owner: File
    domain_of:
    - Information
    range: string
  last_updated_on:
    name: last_updated_on
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: '2022-06-30T00:00:00Z'
    description: The date and time when the resource was most recently modified or
      updated. Requires a UTC offset (`…T00:00:00Z`); RFC 3339 `date-time` rejects
      a naive timestamp.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:modified
    alias: last_updated_on
    owner: File
    domain_of:
    - Information
    range: datetime
  license:
    name: license
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: CC-BY-NC-4.0
    description: The legal license under which the resource is made available (e.g.,
      "MIT", "CC-BY-4.0").
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:license
    alias: license
    owner: File
    domain_of:
    - Software
    - Information
    range: string
  modified_by:
    name: modified_by
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: orcid:0000-0002-9876-5432
    description: A person or organization that contributed to modifying or updating
      the resource.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:contributor
    alias: modified_by
    owner: File
    domain_of:
    - Information
    range: string
  page:
    name: page
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: https://example.org/datasets/example-cohort
    description: A landing page or web page providing access to or information about
      the resource.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcat:landingPage
    alias: page
    owner: File
    domain_of:
    - Information
    range: string
  publisher:
    name: publisher
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: 'ROR:0xxxxxxxx  # a ROR CURIE (form only), a DOI, or a URL — not a
          plain name'
    description: The organization or entity responsible for making the resource available.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:publisher
    alias: publisher
    owner: File
    domain_of:
    - Information
    range: uriorcurie
  status:
    name: status
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: published
    description: The status of the resource (e.g., draft, published, deprecated).
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: d4d:publicationStatus
    alias: status
    owner: File
    domain_of:
    - Information
    range: string
  title:
    name: title
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: 'Example Cohort Study of Chronic Disease: Data Release 1.0'
    description: The official title of the element.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:title
    alias: title
    owner: File
    domain_of:
    - Information
    range: string
  version:
    name: version
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: 2.0.0
    description: The version identifier of the resource (e.g., "1.0", "2.3.1").
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: schema:version
    alias: version
    owner: File
    domain_of:
    - Software
    - Information
    range: string
  was_derived_from:
    name: was_derived_from
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: https://example.org/datasets/example-cohort/versions/1
    description: A resource from which this resource was derived, in whole or in part.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    exact_mappings:
    - dcterms:source
    rank: 1000
    slot_uri: prov:wasDerivedFrom
    alias: was_derived_from
    owner: File
    domain_of:
    - Information
    range: string
  id:
    name: id
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: https://example.org/dataset/my-dataset-001
    description: A unique identifier for a thing.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema/base
    rank: 1000
    slot_uri: schema:identifier
    identifier: true
    alias: id
    owner: File
    domain_of:
    - NamedThing
    - Organization
    - DatasetProperty
    - Grant
    range: uriorcurie
    required: true
  name:
    name: name
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: Example Cohort Dataset
    description: A human-readable name for a thing.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema/base
    rank: 1000
    slot_uri: schema:name
    alias: name
    owner: File
    domain_of:
    - NamedThing
    - Organization
    - DatasetProperty
    - Grant
    range: string
  description:
    name: description
    annotations:
      d4d:docExample:
        tag: d4d:docExample
        value: A multimodal dataset of 2,500 participants in a longitudinal cohort
          study.
    description: A human-readable description for a thing.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema/base
    rank: 1000
    slot_uri: schema:description
    alias: description
    owner: File
    domain_of:
    - NamedThing
    - Organization
    - DatasetProperty
    - Grant
    - DatasetRelationship
    range: string
  notes:
    name: notes
    description: Residual content only, after every fitting slot is used — structured
      slots first, then description; notes solely for what description cannot hold
      (#385). Never invent keys (#380).
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema/base
    rank: 1000
    slot_uri: schema:comment
    alias: notes
    owner: File
    domain_of:
    - NamedThing
    - Organization
    - DatasetProperty
    - Grant
    range: string
  source_caveats:
    name: source_caveats
    description: 'Commentary on the evidence behind this object''s values — source
      conflicts, what a value was transcribed from, questions the source material
      leaves unanswered (#385). A trust annotation about the sibling slots, not dataset
      content: content belongs in the structured slots, description or notes.'
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema/base
    rank: 1000
    slot_uri: dcterms:provenance
    alias: source_caveats
    owner: File
    domain_of:
    - NamedThing
    - Organization
    - DatasetProperty
    - Grant
    range: string
class_uri: schema:MediaObject