Class: Dataset

A single component of related observations and/or information that can be read, manipulated, transformed, and otherwise interpreted.

URI: dcat:Distribution

classDiagram class Dataset click Dataset href "../Dataset/" Information <|-- Dataset click Information href "../Information/" Dataset <|-- DataSubset click DataSubset href "../DataSubset/" Dataset : acquisition_methods Dataset --> "*" InstanceAcquisition : acquisition_methods click InstanceAcquisition href "../InstanceAcquisition/" Dataset : addressing_gaps Dataset --> "*" AddressingGap : addressing_gaps click AddressingGap href "../AddressingGap/" Dataset : annotation_analyses Dataset --> "*" AnnotationAnalysis : annotation_analyses click AnnotationAnalysis href "../AnnotationAnalysis/" Dataset : anomalies Dataset --> "*" DataAnomaly : anomalies click DataAnomaly href "../DataAnomaly/" Dataset : bytes Dataset : citation Dataset : cleaning_strategies Dataset --> "*" CleaningStrategy : cleaning_strategies click CleaningStrategy href "../CleaningStrategy/" Dataset : collection_mechanisms Dataset --> "*" CollectionMechanism : collection_mechanisms click CollectionMechanism href "../CollectionMechanism/" Dataset : collection_timeframes Dataset --> "*" CollectionTimeframe : collection_timeframes click CollectionTimeframe href "../CollectionTimeframe/" Dataset : compression Dataset --> "0..1" CompressionEnum : compression click CompressionEnum href "../CompressionEnum/" Dataset : confidential_elements Dataset --> "*" Confidentiality : confidential_elements click Confidentiality href "../Confidentiality/" Dataset : conforms_to Dataset : conforms_to_class Dataset : conforms_to_schema Dataset : content_warnings Dataset --> "*" ContentWarning : content_warnings click ContentWarning href "../ContentWarning/" Dataset : created_by Dataset : created_on Dataset : creators Dataset --> "*" Creator : creators click Creator href "../Creator/" Dataset : data_collectors Dataset --> "*" DataCollector : data_collectors click DataCollector href "../DataCollector/" Dataset : data_protection_impacts Dataset --> "*" DataProtectionImpact : data_protection_impacts click DataProtectionImpact href "../DataProtectionImpact/" Dataset : description Dataset : dialect Dataset : discouraged_uses Dataset --> "*" DiscouragedUse : discouraged_uses click DiscouragedUse href "../DiscouragedUse/" Dataset : distribution_dates Dataset --> "*" DistributionDate : distribution_dates click DistributionDate href "../DistributionDate/" Dataset : distribution_formats Dataset --> "*" DistributionFormat : distribution_formats click DistributionFormat href "../DistributionFormat/" Dataset : doi Dataset : download_url Dataset : encoding Dataset --> "0..1" EncodingEnum : encoding click EncodingEnum href "../EncodingEnum/" Dataset : errata Dataset --> "*" Erratum : errata click Erratum href "../Erratum/" Dataset : ethical_reviews Dataset --> "*" EthicalReview : ethical_reviews click EthicalReview href "../EthicalReview/" Dataset : existing_uses Dataset --> "*" ExistingUse : existing_uses click ExistingUse href "../ExistingUse/" Dataset : extension_mechanism Dataset --> "0..1" ExtensionMechanism : extension_mechanism click ExtensionMechanism href "../ExtensionMechanism/" Dataset : external_resources Dataset --> "*" ExternalResource : external_resources click ExternalResource href "../ExternalResource/" Dataset : format Dataset --> "0..1" FormatEnum : format click FormatEnum href "../FormatEnum/" Dataset : funders Dataset --> "*" FundingMechanism : funders click FundingMechanism href "../FundingMechanism/" Dataset : future_use_impacts Dataset --> "*" FutureUseImpact : future_use_impacts click FutureUseImpact href "../FutureUseImpact/" Dataset : hash Dataset : human_subject_research Dataset --> "0..1" HumanSubjectResearch : human_subject_research click HumanSubjectResearch href "../HumanSubjectResearch/" Dataset : id Dataset : imputation_protocols Dataset --> "*" ImputationProtocol : imputation_protocols click ImputationProtocol href "../ImputationProtocol/" Dataset : informed_consent Dataset --> "*" InformedConsent : informed_consent click InformedConsent href "../InformedConsent/" Dataset : instances Dataset --> "*" Instance : instances click Instance href "../Instance/" Dataset : intended_uses Dataset --> "*" IntendedUse : intended_uses click IntendedUse href "../IntendedUse/" Dataset : ip_restrictions Dataset --> "0..1" IPRestrictions : ip_restrictions click IPRestrictions href "../IPRestrictions/" Dataset : is_deidentified Dataset --> "0..1" Deidentification : is_deidentified click Deidentification href "../Deidentification/" Dataset : is_tabular Dataset : issued Dataset : keywords Dataset : known_biases Dataset --> "*" DatasetBias : known_biases click DatasetBias href "../DatasetBias/" Dataset : known_limitations Dataset --> "*" DatasetLimitation : known_limitations click DatasetLimitation href "../DatasetLimitation/" Dataset : labeling_strategies Dataset --> "*" LabelingStrategy : labeling_strategies click LabelingStrategy href "../LabelingStrategy/" Dataset : language Dataset : last_updated_on Dataset : license Dataset : license_and_use_terms Dataset --> "0..1" LicenseAndUseTerms : license_and_use_terms click LicenseAndUseTerms href "../LicenseAndUseTerms/" Dataset : machine_annotation_tools Dataset --> "*" MachineAnnotationTools : machine_annotation_tools click MachineAnnotationTools href "../MachineAnnotationTools/" Dataset : maintainers Dataset --> "*" Maintainer : maintainers click Maintainer href "../Maintainer/" Dataset : md5 Dataset : media_type Dataset --> "0..1" MediaTypeEnum : media_type click MediaTypeEnum href "../MediaTypeEnum/" Dataset : missing_data_documentation Dataset --> "*" MissingDataDocumentation : missing_data_documentation click MissingDataDocumentation href "../MissingDataDocumentation/" Dataset : modified_by Dataset : name Dataset : other_tasks Dataset --> "*" OtherTask : other_tasks click OtherTask href "../OtherTask/" Dataset : page Dataset : parent_datasets Dataset --> "*" Dataset : parent_datasets click Dataset href "../Dataset/" Dataset : participant_compensation Dataset --> "0..1" HumanSubjectCompensation : participant_compensation click HumanSubjectCompensation href "../HumanSubjectCompensation/" Dataset : participant_privacy Dataset --> "*" ParticipantPrivacy : participant_privacy click ParticipantPrivacy href "../ParticipantPrivacy/" Dataset : path Dataset : preprocessing_strategies Dataset --> "*" PreprocessingStrategy : preprocessing_strategies click PreprocessingStrategy href "../PreprocessingStrategy/" Dataset : prohibited_uses Dataset --> "*" ProhibitedUse : prohibited_uses click ProhibitedUse href "../ProhibitedUse/" Dataset : publisher Dataset : purposes Dataset --> "*" Purpose : purposes click Purpose href "../Purpose/" Dataset : raw_data_sources Dataset --> "*" RawDataSource : raw_data_sources click RawDataSource href "../RawDataSource/" Dataset : raw_sources Dataset --> "*" RawData : raw_sources click RawData href "../RawData/" Dataset : regulatory_restrictions Dataset --> "0..1" ExportControlRegulatoryRestrictions : regulatory_restrictions click ExportControlRegulatoryRestrictions href "../ExportControlRegulatoryRestrictions/" Dataset : related_datasets Dataset --> "*" DatasetRelationship : related_datasets click DatasetRelationship href "../DatasetRelationship/" Dataset : resources Dataset --> "*" Dataset : resources click Dataset href "../Dataset/" Dataset : retention_limit Dataset --> "0..1" RetentionLimits : retention_limit click RetentionLimits href "../RetentionLimits/" Dataset : sampling_strategies Dataset --> "*" SamplingStrategy : sampling_strategies click SamplingStrategy href "../SamplingStrategy/" Dataset : sensitive_elements Dataset --> "*" SensitiveElement : sensitive_elements click SensitiveElement href "../SensitiveElement/" Dataset : sha256 Dataset : status Dataset : subpopulations Dataset --> "*" Subpopulation : subpopulations click Subpopulation href "../Subpopulation/" Dataset : subsets Dataset --> "*" DataSubset : subsets click DataSubset href "../DataSubset/" Dataset : tasks Dataset --> "*" Task : tasks click Task href "../Task/" Dataset : title Dataset : updates Dataset --> "0..1" UpdatePlan : updates click UpdatePlan href "../UpdatePlan/" Dataset : use_repository Dataset --> "*" UseRepository : use_repository click UseRepository href "../UseRepository/" Dataset : variables Dataset --> "*" VariableMetadata : variables click VariableMetadata href "../VariableMetadata/" Dataset : version Dataset : version_access Dataset --> "0..1" VersionAccess : version_access click VersionAccess href "../VersionAccess/" Dataset : vulnerable_populations Dataset --> "0..1" VulnerablePopulations : vulnerable_populations click VulnerablePopulations href "../VulnerablePopulations/" Dataset : was_derived_from

Inheritance

NamedThing
- Information
  - Dataset
    - DataSubset

Slots

Name	Cardinality and Range	Description	Inheritance
bytes	0..1 Integer	Size of the data in bytes	direct
dialect	0..1 String		direct
encoding	0..1 EncodingEnum	the character encoding of the data	direct
format	0..1 FormatEnum	The file format, physical medium, or dimensions of a resource	direct
hash	0..1 String	hash of the data	direct
md5	0..1 String	md5 hash of the data	direct
media_type	0..1 MediaTypeEnum	The media type of the data	direct
path	0..1 String		direct
sha256	0..1 String	sha256 hash of the data	direct
external_resources	* ExternalResource	Links or identifiers for external resources	direct
resources	* Dataset	Sub-resources or component datasets that are part of this dataset	direct
purposes	* Purpose		direct
tasks	* Task		direct
addressing_gaps	* AddressingGap		direct
creators	* Creator		direct
funders	* FundingMechanism		direct
subsets	* DataSubset		direct
instances	* Instance		direct
anomalies	* DataAnomaly		direct
known_biases	* DatasetBias	Known biases present in the dataset that may affect fairness, representativen...	direct
known_limitations	* DatasetLimitation	Known limitations of the dataset that may affect its use or interpretation	direct
confidential_elements	* Confidentiality		direct
content_warnings	* ContentWarning		direct
subpopulations	* Subpopulation		direct
sensitive_elements	* SensitiveElement		direct
acquisition_methods	* InstanceAcquisition		direct
collection_mechanisms	* CollectionMechanism		direct
sampling_strategies	* SamplingStrategy		direct
data_collectors	* DataCollector		direct
collection_timeframes	* CollectionTimeframe		direct
missing_data_documentation	* MissingDataDocumentation	Documentation of missing data patterns and handling strategies	direct
raw_data_sources	* RawDataSource	Description of raw data sources before preprocessing	direct
ethical_reviews	* EthicalReview		direct
data_protection_impacts	* DataProtectionImpact		direct
human_subject_research	0..1 HumanSubjectResearch	Information about whether dataset involves human subjects research, including...	direct
informed_consent	* InformedConsent	Details about informed consent procedures, including consent type, documentat...	direct
participant_privacy	* ParticipantPrivacy	Privacy protections and anonymization procedures for human research participa...	direct
participant_compensation	0..1 HumanSubjectCompensation	Compensation or incentives provided to human research participants	direct
vulnerable_populations	0..1 VulnerablePopulations	Information about protections for vulnerable populations (e	direct
preprocessing_strategies	* PreprocessingStrategy		direct
cleaning_strategies	* CleaningStrategy		direct
labeling_strategies	* LabelingStrategy		direct
raw_sources	* RawData		direct
imputation_protocols	* ImputationProtocol	Data imputation methodology and techniques	direct
annotation_analyses	* AnnotationAnalysis	Analysis of annotation quality and inter-annotator agreement	direct
machine_annotation_tools	* MachineAnnotationTools	Automated annotation tools used in dataset creation	direct
existing_uses	* ExistingUse		direct
use_repository	* UseRepository		direct
other_tasks	* OtherTask		direct
future_use_impacts	* FutureUseImpact		direct
discouraged_uses	* DiscouragedUse		direct
intended_uses	* IntendedUse	Explicit intended and recommended uses for this dataset	direct
prohibited_uses	* ProhibitedUse	Explicitly prohibited or forbidden uses for this dataset	direct
distribution_formats	* DistributionFormat		direct
distribution_dates	* DistributionDate		direct
license_and_use_terms	0..1 LicenseAndUseTerms		direct
ip_restrictions	0..1 IPRestrictions		direct
regulatory_restrictions	0..1 ExportControlRegulatoryRestrictions		direct
maintainers	* Maintainer		direct
errata	* Erratum		direct
updates	0..1 UpdatePlan		direct
retention_limit	0..1 RetentionLimits		direct
version_access	0..1 VersionAccess		direct
extension_mechanism	0..1 ExtensionMechanism		direct
variables	* VariableMetadata	Metadata describing individual variables, fields, or columns in the dataset	direct
is_deidentified	0..1 Deidentification		direct
is_tabular	0..1 Boolean		direct
citation	0..1 String	Recommended citation for this dataset in DataCite or BibTeX format	direct
parent_datasets	* Dataset	Parent datasets that this dataset is part of or derived from	direct
related_datasets	* DatasetRelationship	Related datasets with typed relationships (e	direct
compression	0..1 CompressionEnum	compression format used, if any	Information
conforms_to	0..1 String		Information
conforms_to_class	0..1 String		Information
conforms_to_schema	0..1 String		Information
created_by	0..1 String		Information
created_on	0..1 Datetime		Information
doi	0..1 String	digital object identifier	Information
download_url	0..1 Uri	URL from which the data can be downloaded	Information
issued	0..1 Datetime		Information
keywords	* String		Information
language	0..1 String	language in which the information is expressed	Information
last_updated_on	0..1 Datetime		Information
license	0..1 String		Information
modified_by	0..1 String		Information
page	0..1 String		Information
publisher	0..1 Uriorcurie		Information
status	0..1 String		Information
title	0..1 String	the official title of the element	Information
version	0..1 String		Information
was_derived_from	0..1 String		Information
id	1 Uriorcurie	A unique identifier for a thing	NamedThing
name	0..1 String	A human-readable name for a thing	NamedThing
description	0..1 String	A human-readable description for a thing	NamedThing

Usages

used by	used in	type	used
DatasetCollection	resources	range	Dataset
Dataset	resources	range	Dataset
Dataset	parent_datasets	range	Dataset
DataSubset	resources	range	Dataset
DataSubset	parent_datasets	range	Dataset

Aliases

data resource
data file
data package

Identifier and Mapping Information

Schema Source

from schema: https://w3id.org/bridge2ai/data-sheets-schema

Mappings

Mapping Type	Mapped Value
self	dcat:Distribution
native	data_sheets_schema:Dataset
exact	schema:DataDownload

LinkML Source

Direct

name: Dataset
description: A single component of related observations and/or information that can
  be read, manipulated, transformed, and otherwise interpreted.
from_schema: https://w3id.org/bridge2ai/data-sheets-schema
aliases:
- data resource
- data file
- data package
exact_mappings:
- schema:DataDownload
is_a: Information
slots:
- bytes
- dialect
- encoding
- format
- hash
- md5
- media_type
- path
- sha256
- external_resources
- resources
slot_usage:
  external_resources:
    name: external_resources
    range: ExternalResource
    inlined_as_list: true
  resources:
    name: resources
    description: Sub-resources or component datasets that are part of this dataset.
      Allows datasets to contain nested resource structures.
    inlined_as_list: true
attributes:
  purposes:
    name: purposes
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: Purpose
    multivalued: true
    inlined: true
    inlined_as_list: true
  tasks:
    name: tasks
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: Task
    multivalued: true
    inlined: true
    inlined_as_list: true
  addressing_gaps:
    name: addressing_gaps
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: AddressingGap
    multivalued: true
    inlined: true
    inlined_as_list: true
  creators:
    name: creators
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: Creator
    multivalued: true
    inlined: true
    inlined_as_list: true
  funders:
    name: funders
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: FundingMechanism
    multivalued: true
    inlined: true
    inlined_as_list: true
  subsets:
    name: subsets
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    exact_mappings:
    - schema:distribution
    rank: 1000
    slot_uri: dcat:distribution
    domain_of:
    - Dataset
    range: DataSubset
    multivalued: true
    inlined: true
    inlined_as_list: true
  instances:
    name: instances
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: Instance
    multivalued: true
    inlined: true
    inlined_as_list: true
  anomalies:
    name: anomalies
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: DataAnomaly
    multivalued: true
    inlined: true
    inlined_as_list: true
  known_biases:
    name: known_biases
    description: Known biases present in the dataset that may affect fairness, representativeness,
      or model performance. Uses BiasTypeEnum for standardized bias categorization
      mapped to the AI Ontology (AIO).
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: DatasetBias
    multivalued: true
    inlined: true
    inlined_as_list: true
  known_limitations:
    name: known_limitations
    description: Known limitations of the dataset that may affect its use or interpretation.
      Distinct from biases (systematic errors) and anomalies (data quality issues).
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: DatasetLimitation
    multivalued: true
    inlined: true
    inlined_as_list: true
  confidential_elements:
    name: confidential_elements
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: Confidentiality
    multivalued: true
    inlined: true
    inlined_as_list: true
  content_warnings:
    name: content_warnings
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: ContentWarning
    multivalued: true
    inlined: true
    inlined_as_list: true
  subpopulations:
    name: subpopulations
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: Subpopulation
    multivalued: true
    inlined: true
    inlined_as_list: true
  sensitive_elements:
    name: sensitive_elements
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: SensitiveElement
    multivalued: true
    inlined: true
    inlined_as_list: true
  acquisition_methods:
    name: acquisition_methods
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: InstanceAcquisition
    multivalued: true
    inlined: true
    inlined_as_list: true
  collection_mechanisms:
    name: collection_mechanisms
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: CollectionMechanism
    multivalued: true
    inlined: true
    inlined_as_list: true
  sampling_strategies:
    name: sampling_strategies
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    - Instance
    range: SamplingStrategy
    multivalued: true
    inlined: true
    inlined_as_list: true
  data_collectors:
    name: data_collectors
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: DataCollector
    multivalued: true
    inlined: true
    inlined_as_list: true
  collection_timeframes:
    name: collection_timeframes
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: CollectionTimeframe
    multivalued: true
    inlined: true
    inlined_as_list: true
  missing_data_documentation:
    name: missing_data_documentation
    description: Documentation of missing data patterns and handling strategies.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: MissingDataDocumentation
    multivalued: true
    inlined: true
    inlined_as_list: true
  raw_data_sources:
    name: raw_data_sources
    description: Description of raw data sources before preprocessing.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: RawDataSource
    multivalued: true
    inlined: true
    inlined_as_list: true
  ethical_reviews:
    name: ethical_reviews
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: EthicalReview
    multivalued: true
    inlined: true
    inlined_as_list: true
  data_protection_impacts:
    name: data_protection_impacts
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: DataProtectionImpact
    multivalued: true
    inlined: true
    inlined_as_list: true
  human_subject_research:
    name: human_subject_research
    description: Information about whether dataset involves human subjects research,
      including IRB approval, ethics review, and regulatory compliance.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: HumanSubjectResearch
    inlined: true
  informed_consent:
    name: informed_consent
    description: Details about informed consent procedures, including consent type,
      documentation, and withdrawal mechanisms.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: InformedConsent
    multivalued: true
    inlined: true
    inlined_as_list: true
  participant_privacy:
    name: participant_privacy
    description: Privacy protections and anonymization procedures for human research
      participants, including reidentification risk assessment.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: ParticipantPrivacy
    multivalued: true
    inlined: true
    inlined_as_list: true
  participant_compensation:
    name: participant_compensation
    description: Compensation or incentives provided to human research participants.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: HumanSubjectCompensation
    inlined: true
  vulnerable_populations:
    name: vulnerable_populations
    description: Information about protections for vulnerable populations (e.g., minors,
      pregnant women, prisoners) including special safeguards and assent procedures.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: VulnerablePopulations
    inlined: true
  preprocessing_strategies:
    name: preprocessing_strategies
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: PreprocessingStrategy
    multivalued: true
    inlined: true
    inlined_as_list: true
  cleaning_strategies:
    name: cleaning_strategies
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: CleaningStrategy
    multivalued: true
    inlined: true
    inlined_as_list: true
  labeling_strategies:
    name: labeling_strategies
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: LabelingStrategy
    multivalued: true
    inlined: true
    inlined_as_list: true
  raw_sources:
    name: raw_sources
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: RawData
    multivalued: true
    inlined: true
    inlined_as_list: true
  imputation_protocols:
    name: imputation_protocols
    description: Data imputation methodology and techniques.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: ImputationProtocol
    multivalued: true
    inlined: true
    inlined_as_list: true
  annotation_analyses:
    name: annotation_analyses
    description: Analysis of annotation quality and inter-annotator agreement.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: AnnotationAnalysis
    multivalued: true
    inlined: true
    inlined_as_list: true
  machine_annotation_tools:
    name: machine_annotation_tools
    description: Automated annotation tools used in dataset creation.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: MachineAnnotationTools
    multivalued: true
    inlined: true
    inlined_as_list: true
  existing_uses:
    name: existing_uses
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: ExistingUse
    multivalued: true
    inlined: true
    inlined_as_list: true
  use_repository:
    name: use_repository
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: UseRepository
    multivalued: true
    inlined: true
    inlined_as_list: true
  other_tasks:
    name: other_tasks
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: OtherTask
    multivalued: true
    inlined: true
    inlined_as_list: true
  future_use_impacts:
    name: future_use_impacts
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: FutureUseImpact
    multivalued: true
    inlined: true
    inlined_as_list: true
  discouraged_uses:
    name: discouraged_uses
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: DiscouragedUse
    multivalued: true
    inlined: true
    inlined_as_list: true
  intended_uses:
    name: intended_uses
    description: Explicit intended and recommended uses for this dataset. Complements
      future_use_impacts by focusing on positive applications.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: IntendedUse
    multivalued: true
    inlined: true
    inlined_as_list: true
  prohibited_uses:
    name: prohibited_uses
    description: Explicitly prohibited or forbidden uses for this dataset. Stronger
      than discouraged_uses - these are not permitted.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: ProhibitedUse
    multivalued: true
    inlined: true
    inlined_as_list: true
  distribution_formats:
    name: distribution_formats
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: DistributionFormat
    multivalued: true
    inlined: true
    inlined_as_list: true
  distribution_dates:
    name: distribution_dates
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: DistributionDate
    multivalued: true
    inlined: true
    inlined_as_list: true
  license_and_use_terms:
    name: license_and_use_terms
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: LicenseAndUseTerms
    inlined: true
  ip_restrictions:
    name: ip_restrictions
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: IPRestrictions
    inlined: true
  regulatory_restrictions:
    name: regulatory_restrictions
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    - ExportControlRegulatoryRestrictions
    range: ExportControlRegulatoryRestrictions
    inlined: true
  maintainers:
    name: maintainers
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: Maintainer
    multivalued: true
    inlined: true
    inlined_as_list: true
  errata:
    name: errata
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: Erratum
    multivalued: true
    inlined: true
    inlined_as_list: true
  updates:
    name: updates
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: UpdatePlan
    inlined: true
  retention_limit:
    name: retention_limit
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: RetentionLimits
    inlined: true
  version_access:
    name: version_access
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: VersionAccess
    inlined: true
  extension_mechanism:
    name: extension_mechanism
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: ExtensionMechanism
    inlined: true
  variables:
    name: variables
    description: Metadata describing individual variables, fields, or columns in the
      dataset.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    exact_mappings:
    - schema:variableMeasured
    rank: 1000
    slot_uri: schema:variableMeasured
    domain_of:
    - Dataset
    range: VariableMetadata
    multivalued: true
    inlined: true
    inlined_as_list: true
  is_deidentified:
    name: is_deidentified
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: Deidentification
    inlined: true
  is_tabular:
    name: is_tabular
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: boolean
  citation:
    name: citation
    description: Recommended citation for this dataset in DataCite or BibTeX format.
      Provides a standard way to cite the dataset in publications.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    exact_mappings:
    - schema:citation
    rank: 1000
    slot_uri: schema:citation
    domain_of:
    - Dataset
    range: string
  parent_datasets:
    name: parent_datasets
    description: Parent datasets that this dataset is part of or derived from. Enables
      hierarchical dataset composition (hasPart/isPartOf relationships).
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    exact_mappings:
    - schema:isPartOf
    rank: 1000
    slot_uri: schema:isPartOf
    domain_of:
    - Dataset
    range: Dataset
    multivalued: true
    inlined: true
    inlined_as_list: true
  related_datasets:
    name: related_datasets
    description: Related datasets with typed relationships (e.g., supplements, derives
      from, is version of). Use DatasetRelationship class to specify relationship
      types.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    domain_of:
    - Dataset
    range: DatasetRelationship
    multivalued: true
    inlined: true
    inlined_as_list: true
class_uri: dcat:Distribution

Induced

name: Dataset
description: A single component of related observations and/or information that can
  be read, manipulated, transformed, and otherwise interpreted.
from_schema: https://w3id.org/bridge2ai/data-sheets-schema
aliases:
- data resource
- data file
- data package
exact_mappings:
- schema:DataDownload
is_a: Information
slot_usage:
  external_resources:
    name: external_resources
    range: ExternalResource
    inlined_as_list: true
  resources:
    name: resources
    description: Sub-resources or component datasets that are part of this dataset.
      Allows datasets to contain nested resource structures.
    inlined_as_list: true
attributes:
  purposes:
    name: purposes
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: purposes
    owner: Dataset
    domain_of:
    - Dataset
    range: Purpose
    multivalued: true
    inlined: true
    inlined_as_list: true
  tasks:
    name: tasks
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: tasks
    owner: Dataset
    domain_of:
    - Dataset
    range: Task
    multivalued: true
    inlined: true
    inlined_as_list: true
  addressing_gaps:
    name: addressing_gaps
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: addressing_gaps
    owner: Dataset
    domain_of:
    - Dataset
    range: AddressingGap
    multivalued: true
    inlined: true
    inlined_as_list: true
  creators:
    name: creators
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: creators
    owner: Dataset
    domain_of:
    - Dataset
    range: Creator
    multivalued: true
    inlined: true
    inlined_as_list: true
  funders:
    name: funders
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: funders
    owner: Dataset
    domain_of:
    - Dataset
    range: FundingMechanism
    multivalued: true
    inlined: true
    inlined_as_list: true
  subsets:
    name: subsets
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    exact_mappings:
    - schema:distribution
    rank: 1000
    slot_uri: dcat:distribution
    alias: subsets
    owner: Dataset
    domain_of:
    - Dataset
    range: DataSubset
    multivalued: true
    inlined: true
    inlined_as_list: true
  instances:
    name: instances
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: instances
    owner: Dataset
    domain_of:
    - Dataset
    range: Instance
    multivalued: true
    inlined: true
    inlined_as_list: true
  anomalies:
    name: anomalies
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: anomalies
    owner: Dataset
    domain_of:
    - Dataset
    range: DataAnomaly
    multivalued: true
    inlined: true
    inlined_as_list: true
  known_biases:
    name: known_biases
    description: Known biases present in the dataset that may affect fairness, representativeness,
      or model performance. Uses BiasTypeEnum for standardized bias categorization
      mapped to the AI Ontology (AIO).
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: known_biases
    owner: Dataset
    domain_of:
    - Dataset
    range: DatasetBias
    multivalued: true
    inlined: true
    inlined_as_list: true
  known_limitations:
    name: known_limitations
    description: Known limitations of the dataset that may affect its use or interpretation.
      Distinct from biases (systematic errors) and anomalies (data quality issues).
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: known_limitations
    owner: Dataset
    domain_of:
    - Dataset
    range: DatasetLimitation
    multivalued: true
    inlined: true
    inlined_as_list: true
  confidential_elements:
    name: confidential_elements
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: confidential_elements
    owner: Dataset
    domain_of:
    - Dataset
    range: Confidentiality
    multivalued: true
    inlined: true
    inlined_as_list: true
  content_warnings:
    name: content_warnings
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: content_warnings
    owner: Dataset
    domain_of:
    - Dataset
    range: ContentWarning
    multivalued: true
    inlined: true
    inlined_as_list: true
  subpopulations:
    name: subpopulations
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: subpopulations
    owner: Dataset
    domain_of:
    - Dataset
    range: Subpopulation
    multivalued: true
    inlined: true
    inlined_as_list: true
  sensitive_elements:
    name: sensitive_elements
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: sensitive_elements
    owner: Dataset
    domain_of:
    - Dataset
    range: SensitiveElement
    multivalued: true
    inlined: true
    inlined_as_list: true
  acquisition_methods:
    name: acquisition_methods
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: acquisition_methods
    owner: Dataset
    domain_of:
    - Dataset
    range: InstanceAcquisition
    multivalued: true
    inlined: true
    inlined_as_list: true
  collection_mechanisms:
    name: collection_mechanisms
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: collection_mechanisms
    owner: Dataset
    domain_of:
    - Dataset
    range: CollectionMechanism
    multivalued: true
    inlined: true
    inlined_as_list: true
  sampling_strategies:
    name: sampling_strategies
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: sampling_strategies
    owner: Dataset
    domain_of:
    - Dataset
    - Instance
    range: SamplingStrategy
    multivalued: true
    inlined: true
    inlined_as_list: true
  data_collectors:
    name: data_collectors
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: data_collectors
    owner: Dataset
    domain_of:
    - Dataset
    range: DataCollector
    multivalued: true
    inlined: true
    inlined_as_list: true
  collection_timeframes:
    name: collection_timeframes
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: collection_timeframes
    owner: Dataset
    domain_of:
    - Dataset
    range: CollectionTimeframe
    multivalued: true
    inlined: true
    inlined_as_list: true
  missing_data_documentation:
    name: missing_data_documentation
    description: Documentation of missing data patterns and handling strategies.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: missing_data_documentation
    owner: Dataset
    domain_of:
    - Dataset
    range: MissingDataDocumentation
    multivalued: true
    inlined: true
    inlined_as_list: true
  raw_data_sources:
    name: raw_data_sources
    description: Description of raw data sources before preprocessing.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: raw_data_sources
    owner: Dataset
    domain_of:
    - Dataset
    range: RawDataSource
    multivalued: true
    inlined: true
    inlined_as_list: true
  ethical_reviews:
    name: ethical_reviews
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: ethical_reviews
    owner: Dataset
    domain_of:
    - Dataset
    range: EthicalReview
    multivalued: true
    inlined: true
    inlined_as_list: true
  data_protection_impacts:
    name: data_protection_impacts
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: data_protection_impacts
    owner: Dataset
    domain_of:
    - Dataset
    range: DataProtectionImpact
    multivalued: true
    inlined: true
    inlined_as_list: true
  human_subject_research:
    name: human_subject_research
    description: Information about whether dataset involves human subjects research,
      including IRB approval, ethics review, and regulatory compliance.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: human_subject_research
    owner: Dataset
    domain_of:
    - Dataset
    range: HumanSubjectResearch
    inlined: true
  informed_consent:
    name: informed_consent
    description: Details about informed consent procedures, including consent type,
      documentation, and withdrawal mechanisms.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: informed_consent
    owner: Dataset
    domain_of:
    - Dataset
    range: InformedConsent
    multivalued: true
    inlined: true
    inlined_as_list: true
  participant_privacy:
    name: participant_privacy
    description: Privacy protections and anonymization procedures for human research
      participants, including reidentification risk assessment.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: participant_privacy
    owner: Dataset
    domain_of:
    - Dataset
    range: ParticipantPrivacy
    multivalued: true
    inlined: true
    inlined_as_list: true
  participant_compensation:
    name: participant_compensation
    description: Compensation or incentives provided to human research participants.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: participant_compensation
    owner: Dataset
    domain_of:
    - Dataset
    range: HumanSubjectCompensation
    inlined: true
  vulnerable_populations:
    name: vulnerable_populations
    description: Information about protections for vulnerable populations (e.g., minors,
      pregnant women, prisoners) including special safeguards and assent procedures.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: vulnerable_populations
    owner: Dataset
    domain_of:
    - Dataset
    range: VulnerablePopulations
    inlined: true
  preprocessing_strategies:
    name: preprocessing_strategies
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: preprocessing_strategies
    owner: Dataset
    domain_of:
    - Dataset
    range: PreprocessingStrategy
    multivalued: true
    inlined: true
    inlined_as_list: true
  cleaning_strategies:
    name: cleaning_strategies
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: cleaning_strategies
    owner: Dataset
    domain_of:
    - Dataset
    range: CleaningStrategy
    multivalued: true
    inlined: true
    inlined_as_list: true
  labeling_strategies:
    name: labeling_strategies
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: labeling_strategies
    owner: Dataset
    domain_of:
    - Dataset
    range: LabelingStrategy
    multivalued: true
    inlined: true
    inlined_as_list: true
  raw_sources:
    name: raw_sources
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: raw_sources
    owner: Dataset
    domain_of:
    - Dataset
    range: RawData
    multivalued: true
    inlined: true
    inlined_as_list: true
  imputation_protocols:
    name: imputation_protocols
    description: Data imputation methodology and techniques.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: imputation_protocols
    owner: Dataset
    domain_of:
    - Dataset
    range: ImputationProtocol
    multivalued: true
    inlined: true
    inlined_as_list: true
  annotation_analyses:
    name: annotation_analyses
    description: Analysis of annotation quality and inter-annotator agreement.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: annotation_analyses
    owner: Dataset
    domain_of:
    - Dataset
    range: AnnotationAnalysis
    multivalued: true
    inlined: true
    inlined_as_list: true
  machine_annotation_tools:
    name: machine_annotation_tools
    description: Automated annotation tools used in dataset creation.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: machine_annotation_tools
    owner: Dataset
    domain_of:
    - Dataset
    range: MachineAnnotationTools
    multivalued: true
    inlined: true
    inlined_as_list: true
  existing_uses:
    name: existing_uses
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: existing_uses
    owner: Dataset
    domain_of:
    - Dataset
    range: ExistingUse
    multivalued: true
    inlined: true
    inlined_as_list: true
  use_repository:
    name: use_repository
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: use_repository
    owner: Dataset
    domain_of:
    - Dataset
    range: UseRepository
    multivalued: true
    inlined: true
    inlined_as_list: true
  other_tasks:
    name: other_tasks
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: other_tasks
    owner: Dataset
    domain_of:
    - Dataset
    range: OtherTask
    multivalued: true
    inlined: true
    inlined_as_list: true
  future_use_impacts:
    name: future_use_impacts
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: future_use_impacts
    owner: Dataset
    domain_of:
    - Dataset
    range: FutureUseImpact
    multivalued: true
    inlined: true
    inlined_as_list: true
  discouraged_uses:
    name: discouraged_uses
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: discouraged_uses
    owner: Dataset
    domain_of:
    - Dataset
    range: DiscouragedUse
    multivalued: true
    inlined: true
    inlined_as_list: true
  intended_uses:
    name: intended_uses
    description: Explicit intended and recommended uses for this dataset. Complements
      future_use_impacts by focusing on positive applications.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: intended_uses
    owner: Dataset
    domain_of:
    - Dataset
    range: IntendedUse
    multivalued: true
    inlined: true
    inlined_as_list: true
  prohibited_uses:
    name: prohibited_uses
    description: Explicitly prohibited or forbidden uses for this dataset. Stronger
      than discouraged_uses - these are not permitted.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: prohibited_uses
    owner: Dataset
    domain_of:
    - Dataset
    range: ProhibitedUse
    multivalued: true
    inlined: true
    inlined_as_list: true
  distribution_formats:
    name: distribution_formats
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: distribution_formats
    owner: Dataset
    domain_of:
    - Dataset
    range: DistributionFormat
    multivalued: true
    inlined: true
    inlined_as_list: true
  distribution_dates:
    name: distribution_dates
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: distribution_dates
    owner: Dataset
    domain_of:
    - Dataset
    range: DistributionDate
    multivalued: true
    inlined: true
    inlined_as_list: true
  license_and_use_terms:
    name: license_and_use_terms
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: license_and_use_terms
    owner: Dataset
    domain_of:
    - Dataset
    range: LicenseAndUseTerms
    inlined: true
  ip_restrictions:
    name: ip_restrictions
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: ip_restrictions
    owner: Dataset
    domain_of:
    - Dataset
    range: IPRestrictions
    inlined: true
  regulatory_restrictions:
    name: regulatory_restrictions
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: regulatory_restrictions
    owner: Dataset
    domain_of:
    - Dataset
    - ExportControlRegulatoryRestrictions
    range: ExportControlRegulatoryRestrictions
    inlined: true
  maintainers:
    name: maintainers
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: maintainers
    owner: Dataset
    domain_of:
    - Dataset
    range: Maintainer
    multivalued: true
    inlined: true
    inlined_as_list: true
  errata:
    name: errata
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: errata
    owner: Dataset
    domain_of:
    - Dataset
    range: Erratum
    multivalued: true
    inlined: true
    inlined_as_list: true
  updates:
    name: updates
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: updates
    owner: Dataset
    domain_of:
    - Dataset
    range: UpdatePlan
    inlined: true
  retention_limit:
    name: retention_limit
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: retention_limit
    owner: Dataset
    domain_of:
    - Dataset
    range: RetentionLimits
    inlined: true
  version_access:
    name: version_access
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: version_access
    owner: Dataset
    domain_of:
    - Dataset
    range: VersionAccess
    inlined: true
  extension_mechanism:
    name: extension_mechanism
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: extension_mechanism
    owner: Dataset
    domain_of:
    - Dataset
    range: ExtensionMechanism
    inlined: true
  variables:
    name: variables
    description: Metadata describing individual variables, fields, or columns in the
      dataset.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    exact_mappings:
    - schema:variableMeasured
    rank: 1000
    slot_uri: schema:variableMeasured
    alias: variables
    owner: Dataset
    domain_of:
    - Dataset
    range: VariableMetadata
    multivalued: true
    inlined: true
    inlined_as_list: true
  is_deidentified:
    name: is_deidentified
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: is_deidentified
    owner: Dataset
    domain_of:
    - Dataset
    range: Deidentification
    inlined: true
  is_tabular:
    name: is_tabular
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: is_tabular
    owner: Dataset
    domain_of:
    - Dataset
    range: boolean
  citation:
    name: citation
    description: Recommended citation for this dataset in DataCite or BibTeX format.
      Provides a standard way to cite the dataset in publications.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    exact_mappings:
    - schema:citation
    rank: 1000
    slot_uri: schema:citation
    alias: citation
    owner: Dataset
    domain_of:
    - Dataset
    range: string
  parent_datasets:
    name: parent_datasets
    description: Parent datasets that this dataset is part of or derived from. Enables
      hierarchical dataset composition (hasPart/isPartOf relationships).
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    exact_mappings:
    - schema:isPartOf
    rank: 1000
    slot_uri: schema:isPartOf
    alias: parent_datasets
    owner: Dataset
    domain_of:
    - Dataset
    range: Dataset
    multivalued: true
    inlined: true
    inlined_as_list: true
  related_datasets:
    name: related_datasets
    description: Related datasets with typed relationships (e.g., supplements, derives
      from, is version of). Use DatasetRelationship class to specify relationship
      types.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: related_datasets
    owner: Dataset
    domain_of:
    - Dataset
    range: DatasetRelationship
    multivalued: true
    inlined: true
    inlined_as_list: true
  bytes:
    name: bytes
    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: Dataset
    domain_of:
    - Dataset
    range: integer
  dialect:
    name: dialect
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: dialect
    owner: Dataset
    domain_of:
    - Dataset
    range: string
  encoding:
    name: encoding
    description: the character encoding of the data
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcat:mediaType
    alias: encoding
    owner: Dataset
    domain_of:
    - Dataset
    range: EncodingEnum
  format:
    name: format
    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: Dataset
    domain_of:
    - Dataset
    range: FormatEnum
  hash:
    name: hash
    description: hash of the data
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:identifier
    alias: hash
    owner: Dataset
    domain_of:
    - Dataset
    range: string
  md5:
    name: md5
    description: md5 hash of the data
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:identifier
    alias: md5
    owner: Dataset
    domain_of:
    - Dataset
    range: string
  media_type:
    name: media_type
    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: Dataset
    domain_of:
    - Dataset
    range: MediaTypeEnum
  path:
    name: path
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: schema:contentUrl
    alias: path
    owner: Dataset
    domain_of:
    - Dataset
    range: string
  sha256:
    name: sha256
    description: sha256 hash of the data
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:identifier
    alias: sha256
    owner: Dataset
    domain_of:
    - Dataset
    range: string
  external_resources:
    name: external_resources
    description: Links or identifiers for external resources. Can be used either as
      a list of ExternalResource objects (in Dataset) or as a list of URL strings
      (within ExternalResource class).
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:references
    alias: external_resources
    owner: Dataset
    domain_of:
    - Dataset
    - ExternalResource
    range: ExternalResource
    multivalued: true
    inlined_as_list: true
  resources:
    name: resources
    description: Sub-resources or component datasets that are part of this dataset.
      Allows datasets to contain nested resource structures.
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    alias: resources
    owner: Dataset
    domain_of:
    - DatasetCollection
    - Dataset
    range: Dataset
    multivalued: true
    inlined_as_list: true
  compression:
    name: compression
    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: Dataset
    domain_of:
    - Information
    range: CompressionEnum
  conforms_to:
    name: conforms_to
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:conformsTo
    alias: conforms_to
    owner: Dataset
    domain_of:
    - Information
    range: string
  conforms_to_class:
    name: conforms_to_class
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:conformsTo
    alias: conforms_to_class
    owner: Dataset
    domain_of:
    - Information
    range: string
  conforms_to_schema:
    name: conforms_to_schema
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:conformsTo
    alias: conforms_to_schema
    owner: Dataset
    domain_of:
    - Information
    range: string
  created_by:
    name: created_by
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:creator
    alias: created_by
    owner: Dataset
    domain_of:
    - Information
    range: string
  created_on:
    name: created_on
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:created
    alias: created_on
    owner: Dataset
    domain_of:
    - Information
    range: datetime
  doi:
    name: doi
    description: digital object identifier
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:identifier
    alias: doi
    owner: Dataset
    domain_of:
    - Information
    range: string
    pattern: 10\.\d{4,}\/.+
  download_url:
    name: download_url
    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: Dataset
    domain_of:
    - Information
    range: uri
  issued:
    name: issued
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:issued
    alias: issued
    owner: Dataset
    domain_of:
    - Information
    range: datetime
  keywords:
    name: keywords
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcat:keyword
    alias: keywords
    owner: Dataset
    domain_of:
    - Information
    range: string
    multivalued: true
  language:
    name: language
    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: Dataset
    domain_of:
    - Information
    range: string
  last_updated_on:
    name: last_updated_on
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:modified
    alias: last_updated_on
    owner: Dataset
    domain_of:
    - Information
    range: datetime
  license:
    name: license
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:license
    alias: license
    owner: Dataset
    domain_of:
    - Software
    - Information
    range: string
  modified_by:
    name: modified_by
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:contributor
    alias: modified_by
    owner: Dataset
    domain_of:
    - Information
    range: string
  page:
    name: page
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcat:landingPage
    alias: page
    owner: Dataset
    domain_of:
    - Information
    range: string
  publisher:
    name: publisher
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:publisher
    alias: publisher
    owner: Dataset
    domain_of:
    - Information
    range: uriorcurie
  status:
    name: status
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:type
    alias: status
    owner: Dataset
    domain_of:
    - Information
    range: string
  title:
    name: title
    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: Dataset
    domain_of:
    - Information
    range: string
  version:
    name: version
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    rank: 1000
    slot_uri: dcterms:hasVersion
    alias: version
    owner: Dataset
    domain_of:
    - Software
    - Information
    range: string
  was_derived_from:
    name: was_derived_from
    from_schema: https://w3id.org/bridge2ai/data-sheets-schema
    exact_mappings:
    - dcterms:source
    rank: 1000
    slot_uri: prov:wasDerivedFrom
    alias: was_derived_from
    owner: Dataset
    domain_of:
    - Information
    range: string
  id:
    name: id
    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: Dataset
    domain_of:
    - NamedThing
    - DatasetProperty
    range: uriorcurie
    required: true
  name:
    name: name
    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: Dataset
    domain_of:
    - NamedThing
    - DatasetProperty
    range: string
  description:
    name: description
    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: Dataset
    domain_of:
    - NamedThing
    - DatasetProperty
    - DatasetRelationship
    range: string
class_uri: dcat:Distribution