{ "$defs": { "AggregationLevelEnum": { "description": "Levels at which data quality may be aggregated", "enum": [ "value", "record", "dataset", "input_quantity", "indicator", "model", "component", "product", "material", "portfolio", "other" ], "title": "AggregationLevelEnum", "type": "string" }, "AggregationMethodEnum": { "description": "Methods for aggregating data quality information", "enum": [ "worst_score", "rule_based", "weighted_mean", "arithmetic_mean", "geometric_mean", "maximum_risk", "hierarchical", "expert_judgement", "custom", "not_evaluated" ], "title": "AggregationMethodEnum", "type": "string" }, "AssessmentStatusEnum": { "description": "Lifecycle status values for data quality assessments", "enum": [ "draft", "active", "reviewed", "verified", "partial", "superseded", "expired", "unavailable" ], "title": "AssessmentStatusEnum", "type": "string" }, "ConfidenceLevelEnum": { "description": "Confidence levels derived from data quality assessment", "enum": [ "high", "medium", "low", "very_low", "not_evaluated" ], "title": "ConfidenceLevelEnum", "type": "string" }, "DataCharacterization": { "additionalProperties": false, "description": "Characterization of the assessed data, including source, provenance, scope, collection method, versioning, and preprocessing", "properties": { "collection_end_date_value": { "description": "End date for the data collection or generation period", "format": "date", "type": [ "string", "null" ] }, "collection_method_value": { "description": "Method, protocol, procedure, system, or workflow used to collect or generate the data", "type": [ "string", "null" ] }, "collection_protocol_value": { "description": "Documented collection protocol, questionnaire, instrument, test method, API, or extraction logic", "type": [ "string", "null" ] }, "collection_start_date_value": { "description": "Start date for the data collection or generation period", "format": "date", "type": [ "string", "null" ] }, "data_characterization_identifier_value": { "description": "Identifier for a data characterization record", "type": [ "string", "null" ] }, "data_domain_value": { "description": "Domain or subject area of the data, such as product specification, LCA, diagnostics, compliance, or circularity", "type": [ "string", "null" ] }, "data_provider_value": { "description": "Provider, owner, custodian, supplier, laboratory, or organization responsible for the data", "type": [ "string", "null" ] }, "data_quality_evidence_reference_value": { "description": "Reference to supporting evidence such as a report, dataset, diagnostic output, certificate, standard, or workflow record", "type": [ "string", "null" ] }, "data_quality_traceability_reference_value": { "description": "Reference to a metrological traceability statement, chain, method, calibration, or boundary definition related to this data quality assessment", "type": [ "string", "null" ] }, "data_quality_unit_value": { "description": "Unit associated with a quantitative value or metric", "type": [ "string", "null" ] }, "data_source_identifier_value": { "description": "Identifier for the assessed data source, dataset, value source, or information source", "type": [ "string", "null" ] }, "data_source_name_value": { "description": "Name of the assessed data source, dataset, value source, or information source", "type": [ "string", "null" ] }, "data_source_type_value": { "$ref": "#/$defs/DataSourceTypeEnum", "description": "Type of data source used" }, "data_type_value": { "$ref": "#/$defs/DataTypeEnum", "description": "Type of data being assessed" }, "data_version_value": { "description": "Version, edition, revision, release date, or snapshot identifier for the assessed data", "type": [ "string", "null" ] }, "geographic_coverage_value": { "description": "Geographic coverage or spatial representativeness of the data", "type": [ "string", "null" ] }, "harmonization_description_value": { "description": "Harmonization, mapping, coding, unit conversion, or schema alignment applied to combine or compare data", "type": [ "string", "null" ] }, "population_or_scope_value": { "description": "Target population, inference scope, product scope, material scope, or process scope represented by the data", "type": [ "string", "null" ] }, "preprocessing_description_value": { "description": "Preprocessing, cleaning, transformation, imputation, filtering, or normalization applied before assessment", "type": [ "string", "null" ] }, "provenance_description_value": { "description": "Narrative provenance of the data, including who collected it, when, under which protocol, and how it was processed", "type": [ "string", "null" ] }, "sample_size_value": { "description": "Sample size, number of observations, number of records, or number of contributing sources", "type": [ "integer", "null" ] }, "technological_coverage_value": { "description": "Technological, product, process, or system coverage represented by the data", "type": [ "string", "null" ] }, "temporal_coverage_value": { "description": "Temporal coverage or period represented by the data", "type": [ "string", "null" ] }, "update_frequency_value": { "description": "Update cadence or refresh frequency for the data", "type": [ "string", "null" ] }, "variable_definition_value": { "description": "Definition of the variable, field, indicator, category, or qualitative construct being assessed", "type": [ "string", "null" ] } }, "title": "DataCharacterization", "type": "object" }, "DataQualityAssessment": { "additionalProperties": false, "description": "Reusable assessment describing the quality, fitness for purpose, diagnostics, and improvement needs of data used by CE-RISE models", "properties": { "assessment_notes_value": { "description": "Additional notes about the data quality assessment", "type": [ "string", "null" ] }, "assessment_purpose_value": { "description": "Purpose for which the data quality assessment is performed", "type": [ "string", "null" ] }, "assessor_value": { "description": "Person, organization, system, or workflow responsible for the data quality assessment", "type": [ "string", "null" ] }, "data_characterization": { "anyOf": [ { "$ref": "#/$defs/DataCharacterization" }, { "type": "null" } ], "description": "Characterization of the assessed data and its provenance" }, "data_quality_applies_to_class_value": { "description": "Class in an external model to which this data quality assessment applies", "type": [ "string", "null" ] }, "data_quality_applies_to_model_value": { "description": "Name, URI, or namespace of the external data model to which this data quality assessment applies", "type": [ "string", "null" ] }, "data_quality_applies_to_record_value": { "description": "Identifier of the external record, object, dataset, or passport entry to which this data quality assessment applies", "type": [ "string", "null" ] }, "data_quality_applies_to_slot_value": { "description": "Slot or attribute in an external model to which this data quality assessment applies", "type": [ "string", "null" ] }, "data_quality_applies_to_value_identifier_value": { "description": "Identifier of a specific value object when the target model gives value-level identifiers", "type": [ "string", "null" ] }, "data_quality_applies_to_value_path_value": { "description": "JSONPath, XPath, RDF path, or other pointer to the value to which this data quality assessment applies", "type": [ "string", "null" ] }, "data_quality_assessment_date_value": { "description": "Date and time when the data quality assessment was issued or last updated", "format": "date-time", "type": [ "string", "null" ] }, "data_quality_assessment_identifier_value": { "description": "Identifier for a data quality assessment that can be referenced from another CE-RISE model", "type": [ "string", "null" ] }, "data_quality_assessment_label_value": { "description": "Human-readable label for the data quality assessment", "type": [ "string", "null" ] }, "data_quality_assessment_status_value": { "$ref": "#/$defs/AssessmentStatusEnum", "description": "Lifecycle status of the data quality assessment" }, "data_quality_assessment_type_value": { "$ref": "#/$defs/DataQualityAssessmentTypeEnum", "description": "Type of data quality assessment being documented" }, "data_quality_evidence_reference_value": { "description": "Reference to supporting evidence such as a report, dataset, diagnostic output, certificate, standard, or workflow record", "type": [ "string", "null" ] }, "data_quality_profile": { "anyOf": [ { "$ref": "#/$defs/DataQualityProfile" }, { "type": "null" } ], "description": "Data quality profile associated with an assessment" }, "data_quality_standards_applied_value": { "description": "Standard, guide, protocol, or scoring framework applied in the data quality assessment", "type": [ "string", "null" ] }, "data_quality_traceability_reference_value": { "description": "Reference to a metrological traceability statement, chain, method, calibration, or boundary definition related to this data quality assessment", "type": [ "string", "null" ] }, "data_quality_uncertainty_reference_value": { "description": "Reference to an uncertainty statement, uncertainty budget, or uncertainty component informed by this data quality assessment", "type": [ "string", "null" ] }, "fitness_for_purpose_value": { "$ref": "#/$defs/FitnessForPurposeEnum", "description": "Overall statement of whether the data are fit for the stated purpose" }, "intended_use_value": { "description": "Intended use, decision context, or analytical purpose for which data fitness is assessed", "type": [ "string", "null" ] }, "quality_diagnostics": { "description": "Data-quality diagnostic runs, checks, or analyses", "items": { "$ref": "#/$defs/QualityDiagnostic" }, "type": [ "array", "null" ] }, "quality_issues": { "description": "Data quality issues, limitations, anomalies, or risks", "items": { "$ref": "#/$defs/QualityIssue" }, "type": [ "array", "null" ] }, "remediation_actions": { "description": "Remediation, mitigation, containment, or improvement actions", "items": { "$ref": "#/$defs/RemediationAction" }, "type": [ "array", "null" ] }, "uncertainty_translation": { "anyOf": [ { "$ref": "#/$defs/UncertaintyTranslation" }, { "type": "null" } ], "description": "DQA-to-uncertainty translation associated with an assessment or profile" } }, "title": "DataQualityAssessment", "type": "object" }, "DataQualityAssessmentTypeEnum": { "description": "Kinds of data quality assessments supported by this model", "enum": [ "value_assessment", "record_assessment", "dataset_assessment", "indicator_input_assessment", "indicator_output_assessment", "evidence_assessment", "process_assessment", "composite_assessment", "not_evaluated", "other" ], "title": "DataQualityAssessmentTypeEnum", "type": "string" }, "DataQualityEvidenceReference": { "additionalProperties": false, "description": "Supporting evidence record for a data quality assessment, score, diagnostic, issue, remediation action, uncertainty translation, or aggregation", "properties": { "data_quality_evidence_date_value": { "description": "Date associated with supporting evidence", "format": "date", "type": [ "string", "null" ] }, "data_quality_evidence_description_value": { "description": "Description of supporting evidence", "type": [ "string", "null" ] }, "data_quality_evidence_identifier_value": { "description": "Identifier for supporting evidence", "type": [ "string", "null" ] }, "data_quality_evidence_provider_value": { "description": "Provider, author, laboratory, supplier, or organization responsible for supporting evidence", "type": [ "string", "null" ] }, "data_quality_evidence_type_value": { "$ref": "#/$defs/DataQualityEvidenceTypeEnum", "description": "Type of supporting evidence" }, "data_quality_evidence_url_value": { "description": "URL for supporting evidence", "type": [ "string", "null" ] }, "data_quality_evidence_version_value": { "description": "Version, edition, or revision of supporting evidence", "type": [ "string", "null" ] } }, "title": "DataQualityEvidenceReference", "type": "object" }, "DataQualityEvidenceTypeEnum": { "description": "Types of evidence used to support data quality assessments", "enum": [ "diagnostic_report", "data_profile", "dataset_snapshot", "provenance_record", "metadata_record", "calibration_certificate", "traceability_record", "validation_report", "harmonization_log", "remediation_record", "workflow_record", "supplier_declaration", "standard_or_protocol", "other" ], "title": "DataQualityEvidenceTypeEnum", "type": "string" }, "DataQualityFramework": { "additionalProperties": false, "description": "Root container for data quality assessments and supporting records", "properties": { "criterion_assessments": { "description": "Criterion-level pedigree assessments", "items": { "$ref": "#/$defs/QualityCriterionAssessment" }, "type": [ "array", "null" ] }, "data_characterizations": { "description": "Data characterization records available for reuse by one or more assessments", "items": { "$ref": "#/$defs/DataCharacterization" }, "type": [ "array", "null" ] }, "data_quality_assessments": { "description": "Reusable data quality assessments that can be embedded or referenced by other CE-RISE data models", "items": { "$ref": "#/$defs/DataQualityAssessment" }, "type": [ "array", "null" ] }, "data_quality_evidence_references": { "description": "Evidence records referenced by the data quality framework", "items": { "$ref": "#/$defs/DataQualityEvidenceReference" }, "type": [ "array", "null" ] }, "data_quality_profiles": { "description": "Data quality profiles available for reuse by one or more assessments", "items": { "$ref": "#/$defs/DataQualityProfile" }, "type": [ "array", "null" ] }, "quality_aggregations": { "description": "Aggregations of data quality assessments, profiles, criteria, metrics, or uncertainty translations", "items": { "$ref": "#/$defs/QualityAggregation" }, "type": [ "array", "null" ] }, "quality_diagnostics": { "description": "Data-quality diagnostic runs, checks, or analyses", "items": { "$ref": "#/$defs/QualityDiagnostic" }, "type": [ "array", "null" ] }, "quality_issues": { "description": "Data quality issues, limitations, anomalies, or risks", "items": { "$ref": "#/$defs/QualityIssue" }, "type": [ "array", "null" ] }, "quality_metrics": { "description": "Quality metrics or diagnostic metrics used by profiles, criteria, or diagnostics", "items": { "$ref": "#/$defs/QualityMetric" }, "type": [ "array", "null" ] }, "remediation_actions": { "description": "Remediation, mitigation, containment, or improvement actions", "items": { "$ref": "#/$defs/RemediationAction" }, "type": [ "array", "null" ] }, "uncertainty_translations": { "description": "Translations from data quality scores to uncertainty information", "items": { "$ref": "#/$defs/UncertaintyTranslation" }, "type": [ "array", "null" ] } }, "title": "DataQualityFramework", "type": "object" }, "DataQualityProfile": { "additionalProperties": false, "description": "Profile aggregating data quality criteria, scores, flags, and confidence for a dataset, value, source, or information product", "properties": { "aggregation_method_value": { "$ref": "#/$defs/AggregationMethodEnum", "description": "Method used to aggregate criterion scores or lower-level assessments into a profile" }, "confidence_level_value": { "$ref": "#/$defs/ConfidenceLevelEnum", "description": "Confidence level implied by the data quality assessment" }, "criterion_assessments": { "description": "Criterion-level pedigree assessments", "items": { "$ref": "#/$defs/QualityCriterionAssessment" }, "type": [ "array", "null" ] }, "data_quality_evidence_reference_value": { "description": "Reference to supporting evidence such as a report, dataset, diagnostic output, certificate, standard, or workflow record", "type": [ "string", "null" ] }, "data_quality_profile_identifier_value": { "description": "Identifier for a data quality profile aggregating one or more criterion assessments", "type": [ "string", "null" ] }, "data_quality_profile_name_value": { "description": "Human-readable name of a data quality profile", "type": [ "string", "null" ] }, "limiting_criteria_value": { "description": "Criterion or criteria that limit the overall score, confidence, or decision flag", "type": [ "string", "null" ] }, "overall_numeric_score_value": { "description": "Numeric quality score when the score is represented as a number", "type": [ "number", "null" ] }, "overall_quality_score_value": { "$ref": "#/$defs/QualityScoreEnum", "description": "Overall pedigree score for the assessed data, typically from 1 very reliable to 4 dubious" }, "profile_summary_value": { "description": "Summary of the data quality profile, including main strengths and weaknesses", "type": [ "string", "null" ] }, "quality_flag_value": { "$ref": "#/$defs/QualityFlagEnum", "description": "Operational decision flag derived from the quality profile" }, "uncertainty_translation": { "anyOf": [ { "$ref": "#/$defs/UncertaintyTranslation" }, { "type": "null" } ], "description": "DQA-to-uncertainty translation associated with an assessment or profile" } }, "title": "DataQualityProfile", "type": "object" }, "DataSourceTypeEnum": { "description": "Types of data sources", "enum": [ "direct_measurement", "laboratory_test", "supplier_declaration", "administrative_record", "database", "literature", "expert_judgement", "survey_or_interview", "sensor_or_iot", "calculation_or_model", "mixed", "other" ], "title": "DataSourceTypeEnum", "type": "string" }, "DataTypeEnum": { "description": "Types of data covered by data quality assessments", "enum": [ "quantitative", "semi_quantitative", "qualitative", "categorical", "boolean", "time_series", "geospatial", "modelled", "mixed", "other" ], "title": "DataTypeEnum", "type": "string" }, "DiagnosticTypeEnum": { "description": "Types of data-quality diagnostics", "enum": [ "comprehensive_profiling", "missing_data_analysis", "structural_integrity_validation", "relational_integrity_validation", "distributional_alignment", "semantic_unit_consistency", "temporal_spatial_alignment", "provenance_correlation", "impact_sensitivity", "scoring_rule_check", "reproducibility_check", "other" ], "title": "DiagnosticTypeEnum", "type": "string" }, "FitnessForPurposeEnum": { "description": "Fitness-for-purpose decision values", "enum": [ "fit", "fit_with_conditions", "exploratory_only", "not_fit", "insufficient_information", "not_evaluated" ], "title": "FitnessForPurposeEnum", "type": "string" }, "IssueStatusEnum": { "description": "Lifecycle status of data quality issues", "enum": [ "open", "under_review", "mitigated", "remediated", "accepted_risk", "closed", "superseded" ], "title": "IssueStatusEnum", "type": "string" }, "PriorityEnum": { "description": "Priority values for remediation actions", "enum": [ "low", "medium", "high", "urgent", "not_assigned" ], "title": "PriorityEnum", "type": "string" }, "QualityAggregation": { "additionalProperties": false, "description": "Aggregation of assessments, profiles, criterion scores, metrics, or uncertainty translations across values, records, datasets, or indicators", "properties": { "aggregation_identifier_value": { "description": "Identifier for an aggregation of data quality assessments, profiles, criteria, metrics, or uncertainty translations", "type": [ "string", "null" ] }, "aggregation_input_references_value": { "description": "References to the input assessments, profiles, criteria, metrics, or data sources used in the aggregation", "type": [ "string", "null" ] }, "aggregation_level_value": { "$ref": "#/$defs/AggregationLevelEnum", "description": "Level at which aggregation is performed" }, "aggregation_method_value": { "$ref": "#/$defs/AggregationMethodEnum", "description": "Method used to aggregate criterion scores or lower-level assessments into a profile" }, "aggregation_output_reference_value": { "description": "Reference to the output assessment, profile, score, uncertainty translation, or decision produced by the aggregation", "type": [ "string", "null" ] }, "aggregation_rationale_value": { "description": "Rationale for the aggregation method and weighting choices", "type": [ "string", "null" ] }, "aggregation_weights_value": { "description": "Weights or weighting rule used in the aggregation", "type": [ "string", "null" ] }, "data_quality_evidence_reference_value": { "description": "Reference to supporting evidence such as a report, dataset, diagnostic output, certificate, standard, or workflow record", "type": [ "string", "null" ] } }, "title": "QualityAggregation", "type": "object" }, "QualityCriterionAssessment": { "additionalProperties": false, "description": "Criterion-level assessment for a data quality dimension such as validity, accuracy, consistency, timeliness, or completeness", "properties": { "criterion_assessment_identifier_value": { "description": "Identifier for a criterion-level quality assessment", "type": [ "string", "null" ] }, "criterion_impact_value": { "description": "Impact of this criterion on the intended use, uncertainty, bias, comparability, or decision", "type": [ "string", "null" ] }, "criterion_metric_value": { "description": "Metric value, observation, or diagnostic result used to support the criterion score", "type": [ "string", "null" ] }, "criterion_numeric_score_value": { "description": "Numeric criterion score when the score is represented as a number", "type": [ "number", "null" ] }, "criterion_rationale_value": { "description": "Rationale for assigning the criterion score", "type": [ "string", "null" ] }, "criterion_score_value": { "$ref": "#/$defs/QualityScoreEnum", "description": "Pedigree score assigned to a quality criterion" }, "criterion_threshold_value": { "description": "Threshold, rule, target, or expectation used to score the criterion", "type": [ "string", "null" ] }, "criterion_type_value": { "$ref": "#/$defs/QualityCriterionEnum", "description": "Quality criterion being assessed" }, "criterion_weight_value": { "description": "Weight assigned to the criterion in an aggregation or decision rule", "type": [ "number", "null" ] }, "data_quality_evidence_reference_value": { "description": "Reference to supporting evidence such as a report, dataset, diagnostic output, certificate, standard, or workflow record", "type": [ "string", "null" ] }, "quality_issues": { "description": "Data quality issues, limitations, anomalies, or risks", "items": { "$ref": "#/$defs/QualityIssue" }, "type": [ "array", "null" ] }, "quality_metrics": { "description": "Quality metrics or diagnostic metrics used by profiles, criteria, or diagnostics", "items": { "$ref": "#/$defs/QualityMetric" }, "type": [ "array", "null" ] }, "uncertainty_translation": { "anyOf": [ { "$ref": "#/$defs/UncertaintyTranslation" }, { "type": "null" } ], "description": "DQA-to-uncertainty translation associated with an assessment or profile" } }, "title": "QualityCriterionAssessment", "type": "object" }, "QualityCriterionEnum": { "description": "Data quality criteria supported by the framework", "enum": [ "validity", "accuracy", "consistency", "timeliness", "completeness", "representativeness", "transparency", "provenance", "reproducibility", "precision", "other" ], "title": "QualityCriterionEnum", "type": "string" }, "QualityDiagnostic": { "additionalProperties": false, "description": "Diagnostic run or analysis that compares data against expectations, detects deviations, infers causes, and estimates impact", "properties": { "data_quality_evidence_reference_value": { "description": "Reference to supporting evidence such as a report, dataset, diagnostic output, certificate, standard, or workflow record", "type": [ "string", "null" ] }, "diagnostic_cause_value": { "description": "Plausible or confirmed cause of the observed diagnostic finding", "type": [ "string", "null" ] }, "diagnostic_identifier_value": { "description": "Identifier for a diagnostic run, check, or analysis", "type": [ "string", "null" ] }, "diagnostic_impact_value": { "description": "Impact of the diagnostic finding on the intended analysis, decision, uncertainty, or comparability", "type": [ "string", "null" ] }, "diagnostic_method_value": { "description": "Diagnostic method, test, script, notebook, query, or procedure used", "type": [ "string", "null" ] }, "diagnostic_reproducibility_value": { "description": "Information needed to reproduce the diagnostic run, such as pinned dependencies, configuration, hash, or workflow version", "type": [ "string", "null" ] }, "diagnostic_run_timestamp_value": { "description": "Date and time when the diagnostic run was executed", "format": "date-time", "type": [ "string", "null" ] }, "diagnostic_severity_value": { "$ref": "#/$defs/SeverityEnum", "description": "Severity of the diagnostic finding" }, "diagnostic_software_reference_value": { "description": "Software, notebook, workflow, configuration, or service used to execute the diagnostic", "type": [ "string", "null" ] }, "diagnostic_type_value": { "$ref": "#/$defs/DiagnosticTypeEnum", "description": "Type of data quality diagnostic" }, "expectation_specification_value": { "description": "Expected value, threshold, rule, contract, baseline, or target used by the diagnostic", "type": [ "string", "null" ] }, "observed_deviation_value": { "description": "Observed deviation from the expectation, threshold, baseline, or target", "type": [ "string", "null" ] }, "quality_issues": { "description": "Data quality issues, limitations, anomalies, or risks", "items": { "$ref": "#/$defs/QualityIssue" }, "type": [ "array", "null" ] }, "quality_metrics": { "description": "Quality metrics or diagnostic metrics used by profiles, criteria, or diagnostics", "items": { "$ref": "#/$defs/QualityMetric" }, "type": [ "array", "null" ] } }, "title": "QualityDiagnostic", "type": "object" }, "QualityFlagEnum": { "description": "Operational decision flags derived from quality scores", "enum": [ "green_proceed", "orange_review", "red_reject", "grey_not_evaluated" ], "title": "QualityFlagEnum", "type": "string" }, "QualityIssue": { "additionalProperties": false, "description": "Data quality issue, limitation, anomaly, or risk identified through scoring, diagnostics, provenance review, or expert assessment", "properties": { "data_quality_evidence_reference_value": { "description": "Reference to supporting evidence such as a report, dataset, diagnostic output, certificate, standard, or workflow record", "type": [ "string", "null" ] }, "data_quality_uncertainty_reference_value": { "description": "Reference to an uncertainty statement, uncertainty budget, or uncertainty component informed by this data quality assessment", "type": [ "string", "null" ] }, "issue_affected_criteria_value": { "description": "Quality criteria affected by the issue", "type": [ "string", "null" ] }, "issue_detected_date_value": { "description": "Date when the issue was detected", "format": "date", "type": [ "string", "null" ] }, "issue_risk_statement_value": { "description": "Risk statement explaining how the issue may affect the intended use, decision, or analysis", "type": [ "string", "null" ] }, "issue_root_cause_value": { "description": "Root cause, suspected cause, or causal inference for the issue", "type": [ "string", "null" ] }, "issue_scope_value": { "description": "Scope of the issue, such as affected fields, records, time periods, regions, suppliers, or processes", "type": [ "string", "null" ] }, "issue_severity_value": { "$ref": "#/$defs/SeverityEnum", "description": "Severity or criticality of the data quality issue" }, "issue_status_value": { "$ref": "#/$defs/IssueStatusEnum", "description": "Lifecycle status of the data quality issue" }, "quality_issue_identifier_value": { "description": "Identifier for a data quality issue, limitation, anomaly, or risk", "type": [ "string", "null" ] }, "quality_issue_type_value": { "$ref": "#/$defs/QualityIssueTypeEnum", "description": "Type of data quality issue" }, "remediation_actions": { "description": "Remediation, mitigation, containment, or improvement actions", "items": { "$ref": "#/$defs/RemediationAction" }, "type": [ "array", "null" ] } }, "title": "QualityIssue", "type": "object" }, "QualityIssueTypeEnum": { "description": "Types of data quality issues", "enum": [ "missingness", "non_representativeness", "timeliness_deficit", "schema_drift", "unit_mismatch", "coding_mismatch", "calibration_gap", "provenance_gap", "method_mismatch", "boundary_mismatch", "outlier_or_anomaly", "duplicate_or_conflict", "bias", "invalid_value", "other" ], "title": "QualityIssueTypeEnum", "type": "string" }, "QualityMetric": { "additionalProperties": false, "description": "Metric, indicator, diagnostic output, threshold check, or quality measurement supporting a criterion score", "properties": { "data_quality_evidence_reference_value": { "description": "Reference to supporting evidence such as a report, dataset, diagnostic output, certificate, standard, or workflow record", "type": [ "string", "null" ] }, "metric_method_value": { "description": "Method, query, diagnostic procedure, rule, or script used to compute the metric", "type": [ "string", "null" ] }, "metric_numeric_value": { "description": "Numeric value of a metric, indicator, diagnostic output, or score", "type": [ "number", "null" ] }, "metric_pass_flag_value": { "description": "Whether the metric passes the defined threshold or expectation", "type": [ "boolean", "null" ] }, "metric_text_value": { "description": "Textual, categorical, or structured value of a metric, indicator, diagnostic output, or score", "type": [ "string", "null" ] }, "metric_threshold_value": { "description": "Threshold, tolerance, expectation, or acceptance criterion for the metric", "type": [ "string", "null" ] }, "metric_unit_value": { "description": "Unit associated with a metric value", "type": [ "string", "null" ] }, "quality_metric_category_value": { "$ref": "#/$defs/QualityCriterionEnum", "description": "Category or criterion to which the quality metric belongs" }, "quality_metric_identifier_value": { "description": "Identifier for a data quality metric or diagnostic metric", "type": [ "string", "null" ] }, "quality_metric_name_value": { "description": "Human-readable name of the data quality metric", "type": [ "string", "null" ] } }, "title": "QualityMetric", "type": "object" }, "QualityScoreEnum": { "description": "Pedigree score scale for data quality", "enum": [ "score_1_very_reliable", "score_2_reliable", "score_3_unreliable", "score_4_dubious", "not_evaluated", "not_applicable" ], "title": "QualityScoreEnum", "type": "string" }, "RemediationAction": { "additionalProperties": false, "description": "Remediation, mitigation, containment, or improvement activity for a data quality issue", "properties": { "data_quality_evidence_reference_value": { "description": "Reference to supporting evidence such as a report, dataset, diagnostic output, certificate, standard, or workflow record", "type": [ "string", "null" ] }, "expected_score_improvement_value": { "description": "Expected score, score change, or quality improvement after remediation", "type": [ "string", "null" ] }, "remediation_action_identifier_value": { "description": "Identifier for a remediation action, mitigation, containment, or improvement activity", "type": [ "string", "null" ] }, "remediation_action_type_value": { "$ref": "#/$defs/RemediationActionTypeEnum", "description": "Type of remediation action" }, "remediation_completion_date_value": { "description": "Completion date for the remediation activity", "format": "date", "type": [ "string", "null" ] }, "remediation_description_value": { "description": "Description of the remediation, mitigation, containment, or improvement activity", "type": [ "string", "null" ] }, "remediation_due_date_value": { "description": "Due date for the remediation activity", "format": "date", "type": [ "string", "null" ] }, "remediation_owner_value": { "description": "Person, organization, team, system, or workflow responsible for remediation", "type": [ "string", "null" ] }, "remediation_priority_value": { "$ref": "#/$defs/PriorityEnum", "description": "Priority assigned to the remediation activity" }, "remediation_status_value": { "$ref": "#/$defs/RemediationStatusEnum", "description": "Lifecycle status of the remediation activity" }, "verification_method_value": { "description": "Method or evidence used to verify that remediation was effective", "type": [ "string", "null" ] } }, "title": "RemediationAction", "type": "object" }, "RemediationActionTypeEnum": { "description": "Types of remediation, mitigation, or improvement actions", "enum": [ "sampling_redesign", "reweighting", "imputation", "recalibration", "metadata_completion", "data_contract_enforcement", "unit_canonicalization", "source_refresh", "governance_agreement", "uncertainty_inflation", "quarantine", "rejection", "other" ], "title": "RemediationActionTypeEnum", "type": "string" }, "RemediationStatusEnum": { "description": "Lifecycle status of remediation actions", "enum": [ "proposed", "planned", "in_progress", "completed", "verified", "deferred", "cancelled", "not_applicable" ], "title": "RemediationStatusEnum", "type": "string" }, "SeverityEnum": { "description": "Severity values for diagnostics and quality issues", "enum": [ "low", "moderate", "high", "critical", "not_evaluated" ], "title": "SeverityEnum", "type": "string" }, "UncertaintyTranslation": { "additionalProperties": false, "description": "Translation from data quality information into uncertainty metadata, such as coefficient of variation or uncertainty factor", "properties": { "coefficient_of_variation_lower_value": { "description": "Lower bound of coefficient of variation derived from data quality information", "type": [ "number", "null" ] }, "coefficient_of_variation_upper_value": { "description": "Upper bound of coefficient of variation derived from data quality information", "type": [ "number", "null" ] }, "combined_coefficient_of_variation_value": { "description": "Combined coefficient of variation after aggregating data-quality-derived uncertainty contributions", "type": [ "number", "null" ] }, "combined_uncertainty_factor_value": { "description": "Combined uncertainty factor after aggregating data-quality-derived uncertainty contributions", "type": [ "number", "null" ] }, "data_quality_evidence_reference_value": { "description": "Reference to supporting evidence such as a report, dataset, diagnostic output, certificate, standard, or workflow record", "type": [ "string", "null" ] }, "data_quality_uncertainty_factor_value": { "description": "Uncertainty factor derived from data quality information", "type": [ "number", "null" ] }, "data_quality_uncertainty_reference_value": { "description": "Reference to an uncertainty statement, uncertainty budget, or uncertainty component informed by this data quality assessment", "type": [ "string", "null" ] }, "source_quality_score_value": { "$ref": "#/$defs/QualityScoreEnum", "description": "Quality score used as input to the uncertainty translation" }, "uncertainty_distribution_assumption_value": { "description": "Distributional assumption used for data-quality-derived uncertainty, such as normal or lognormal", "type": [ "string", "null" ] }, "uncertainty_translation_identifier_value": { "description": "Identifier for a translation from data quality scores to uncertainty information", "type": [ "string", "null" ] }, "uncertainty_translation_method_value": { "$ref": "#/$defs/UncertaintyTranslationMethodEnum", "description": "Method used to translate data quality information into uncertainty" }, "uncertainty_translation_rationale_value": { "description": "Rationale explaining how data quality information was translated into uncertainty", "type": [ "string", "null" ] } }, "title": "UncertaintyTranslation", "type": "object" }, "UncertaintyTranslationMethodEnum": { "description": "Methods for translating data quality into uncertainty", "enum": [ "cv_lookup", "uf_lookup", "direct_cv", "direct_uf", "lognormal_uf", "expert_judgement", "sensitivity_analysis", "monte_carlo", "not_evaluated", "other" ], "title": "UncertaintyTranslationMethodEnum", "type": "string" } }, "$id": "https://ce-rise-models.codeberg.page/data-quality-framework/", "$schema": "https://json-schema.org/draft/2019-09/schema", "additionalProperties": true, "metamodel_version": "1.7.0", "title": "data-quality-framework", "type": "object", "version": "0.0.3" }