{
  "schema": "vedokrok.public-item.v1",
  "release_id": "MHC-RPUB-20260920-75ad787a",
  "url": "/knowledge/carry-data-lineage-through-derived-outputs",
  "id": "MHC-D-RESEARCH-0428",
  "version": "0.1.0",
  "title": "Carry data lineage through derived outputs",
  "summary": "A number without lineage is difficult to debug once it becomes important.",
  "kind": "protocol",
  "body": "For consequential derived data, record the source snapshot, transformation version, material filters or joins and output identity. Propagate the lineage reference into downstream artifacts so an anomalous value can be traced back to the exact input and processing path. Treat manual edits as transformations too.",
  "limits": [
    "Complete lineage can be expensive; prioritize data whose errors would affect important decisions, compliance or recovery."
  ],
  "topics": [
    "union-provenance-verification"
  ],
  "intents": [],
  "source_ids": [
    "RS-FF258DEA21EDA7AB",
    "RS-3271B136C6377DC1"
  ],
  "evidence": [
    {
      "claim": "The 2026 provenance-neglect paper defines provenance broadly as the recorded history of data origin, collection, transformation, processing and handling over time.",
      "source_id": "RS-FF258DEA21EDA7AB",
      "role": "supports",
      "note": "The paper adapts provenance concepts to news verification; other domains may require additional lineage fields.",
      "locator": "Definition of provenance neglect and data provenance"
    },
    {
      "claim": "Current C2PA specifications use ingredients and actions to represent how prior assets contribute to a new asset and how it was transformed over time.",
      "source_id": "RS-3271B136C6377DC1",
      "role": "supports",
      "note": "A complete semantic data-lineage system may need domain-specific transformations beyond media-oriented C2PA assertions.",
      "locator": "Assertions, actions and ingredients"
    }
  ],
  "use_when": [
    "A table, dashboard, model input or exported file is derived through several data-processing steps."
  ],
  "avoid_when": [
    "Complete lineage can be expensive; prioritize data whose errors would affect important decisions, compliance or recovery."
  ],
  "example": "A KPI workbook records the source query revision and extraction timestamp so a suspicious total can be reproduced after the source table changes.",
  "check": "A reviewer can reproduce or explain a derived value without guessing which source version and transformation produced it.",
  "steps": [
    "The exact source snapshot or extraction time is identifiable.",
    "Transformation code or rule version is recorded.",
    "Material filters, joins or manual edits are visible.",
    "The output has a stable identity.",
    "Downstream consumers retain a link to the lineage record."
  ],
  "sources": [
    {
      "id": "RS-FF258DEA21EDA7AB",
      "title": "The Original Sins of Algorithmic Authenticity Verification: Provenance Neglect and Model Collapse in AI-Mediated News and Information",
      "url": "https://www.tandfonline.com/doi/full/10.1080/08838151.2026.2691175"
    },
    {
      "id": "RS-3271B136C6377DC1",
      "title": "Content Credentials Specification 2.4",
      "url": "https://spec.c2pa.org/specifications/specifications/2.4/specs/ContentCredentials.html"
    }
  ],
  "relations": [
    {
      "from": "MHC-D-RESEARCH-0428",
      "to": "MHC-D-RESEARCH-0350",
      "type": "useful_with",
      "url": "/knowledge/reconcile-what-changed-after-a-bulk-write"
    }
  ],
  "collections": [
    {
      "id": "RC-3F875FF96207B5CE",
      "title": "Trace where information came from before deciding whether to trust it",
      "url": "/collections/trace-where-information-came-from-before-deciding-whether-to-trust-it"
    }
  ]
}