{
  "id": "workflow:dataset-versioning-governance",
  "_kind": "Workflow",
  "_file": "workflows/workflows/workflows-data-science-deep.yaml",
  "_cluster": "workflows",
  "attributes": {
    "displayName": "Dataset Versioning Governance",
    "workflowKind": "governance",
    "triggerType": "continuous",
    "typicalCadence": "continuous",
    "complexity": "cross-team",
    "description": "Governs the versioning lifecycle of ML training and evaluation datasets —\nenforcing DVC or LakeFS versioning policies, validating that dataset\nlineage metadata tracks transformations and source provenance, auditing\nstorage deduplication, managing access controls per dataset sensitivity\ntier, and ensuring reproducibility by linking model artifacts to exact\ndataset versions. Excludes dataset creation and labeling.\n"
  },
  "outgoingEdges": [
    {
      "from": "workflow:dataset-versioning-governance",
      "to": "role:ml-engineer",
      "kind": "involves_role",
      "attributes": {}
    },
    {
      "from": "workflow:dataset-versioning-governance",
      "to": "role:data-scientist",
      "kind": "involves_role",
      "attributes": {}
    },
    {
      "from": "workflow:dataset-versioning-governance",
      "to": "role:platform-engineer",
      "kind": "involves_role",
      "attributes": {}
    },
    {
      "from": "workflow:dataset-versioning-governance",
      "to": "skill-area:python-data-pipelines",
      "kind": "requires_skill_area",
      "attributes": {}
    },
    {
      "from": "workflow:dataset-versioning-governance",
      "to": "skill-area:ml-fine-tuning",
      "kind": "requires_skill_area",
      "attributes": {}
    },
    {
      "from": "workflow:dataset-versioning-governance",
      "to": "domain:data-science",
      "kind": "applies_to_domain",
      "attributes": {}
    },
    {
      "from": "workflow:dataset-versioning-governance",
      "to": "domain:ml-ops",
      "kind": "applies_to_domain",
      "attributes": {}
    },
    {
      "from": "workflow:dataset-versioning-governance",
      "to": "responsibility:data-quality-monitoring",
      "kind": "triggers_responsibility",
      "attributes": {}
    },
    {
      "from": "workflow:dataset-versioning-governance",
      "to": "responsibility:review-architecture-changes",
      "kind": "triggers_responsibility",
      "attributes": {}
    },
    {
      "from": "workflow:dataset-versioning-governance",
      "to": "org-unit:ml-platform-team",
      "kind": "performed_by_org_unit",
      "attributes": {}
    },
    {
      "from": "workflow:dataset-versioning-governance",
      "to": "org-unit:data-platform-team",
      "kind": "performed_by_org_unit",
      "attributes": {}
    }
  ],
  "incomingEdges": []
}