{
  "tool_id": "art-452-build-ai-training-data-lineage-record",
  "tool_version": "1.0.0",
  "display_name": "AI Training-Data Lineage Record",
  "mcp_name": "build_ai_training_data_lineage_record",
  "mandate_type": "compliance_mandate",
  "wave": 66,
  "gpu": false,
  "url": "https://ainumbers.co/chaingraph/art-452-build-ai-training-data-lineage-record.html",
  "description": "Composes a hash-chained ML training-data lineage record: dataset identity, dataset version, upstream source dataset references, a declared collection/governance method, and an OPTIONAL reference to an existing OCG receipt for the training-run compute (tool identity, execution hash, kernel digest -- never re-embedded). Chains to a prior lineage record via sha256_prev_lineage_hash. Maps to EU AI Act Art 10 (data and data governance) + Annex IV 2(d) technical-documentation elements (data provenance, collection, labelling, cleaning); SR 11-7 model risk management data-lineage practice as the US domestic analog. Documents dataset lineage only -- does not validate dataset quality, bias, or representativeness. Not build_ai_decision_log_record (art-236, per-inference decision chain) and not build_ai_workpaper_record (art-380, audit workpaper over a receipt).",
  "input_schema_ref": "chaingraph/art-452-build-ai-training-data-lineage-record.html#manifest",
  "consumes": [],
  "feeds": [],
  "status": "live",
  "conformance_fixtures": true,
  "compute_capability": "server",
  "compute_images": [{"system":"sha256-source","image_id":"sha256:fd23920a354af2d91e43fa946991d108f2d99c7a9565ba3dbca922aba445e5ad","valid_from":"2026-07-10"},{"system":"risc0","image_id":"sha256:a1a0bc89b5b1febaeda3519f6dbade0fa5ac16beeb143c4e1b01689573567bc6","valid_from":"2026-07-23"}],
  "compute_proof_ready": "ready",
  "compute_proof": {
    "type": "ZkVmReceipt",
    "system": "risc0",
    "receiptFormat": "groth16-bn254",
    "imageId": "sha256:a1a0bc89b5b1febaeda3519f6dbade0fa5ac16beeb143c4e1b01689573567bc6",
    "seal": "DbLn4f1O/b1GmYDwBx/Zuxc/giU/4/1UDriy0epMnlwjCGDZvDtuT0mNK+6SaSTT3i9Rd9+0pKFc97zGAsm3Cw6iE0n59nt6R/3JF3kayrphwmvf+UGmfDyN+X1qy0SAFa8Bd+aIL9fD04DVZKXmzoMp7bmYumrlkytxWFQ90FYTGuUQ6I+CjPOpGzvaYXso7H8BwcUsI5hnKvpBu5P96AuAI+sKuNJPnKphzr7R5m3ytZbdTQ9oVqL9z9yZbm+LGlpW9ysM8uB5H3Gof+si8HcF4mEfwb3cCKQNQEIMXV4FpSPN0aiBk+OZ3gyYMFoU4vLdYRZX1XD2NotVJgGKeg==",
    "journal": {
      "chaingraph_version": "0.4.0",
      "kernel_digest": "sha256:fd23920a354af2d91e43fa946991d108f2d99c7a9565ba3dbca922aba445e5ad",
      "output": {
        "chain_position": "first",
        "checks": [
          {
            "check": "dataset_id_present",
            "detail": "ds-credit-decisioning-2026q2",
            "pass": true
          },
          {
            "check": "dataset_version_present",
            "detail": "1.0.0",
            "pass": true
          },
          {
            "check": "collection_method_valid",
            "detail": "internal_transaction_records",
            "pass": true
          },
          {
            "check": "referenced_receipt_valid_if_present",
            "detail": "not referenced",
            "pass": true
          },
          {
            "check": "prev_lineage_hash_valid_if_present",
            "detail": "ok",
            "pass": true
          }
        ],
        "collection_method": "internal_transaction_records",
        "dataset_id": "ds-credit-decisioning-2026q2",
        "dataset_version": "1.0.0",
        "governance_notes": "Sourced from internal core-banking transaction extracts, deduplicated and de-identified prior to model training per firm data-governance policy.",
        "operator_id": "mrm-data-governance-team",
        "record_status": "COMPLETE",
        "referenced_receipt": null,
        "regulatory_basis": "EU AI Act (Reg. 2024/1689) Art 10 (data and data governance), Annex IV 2(d) (technical documentation: data provenance, collection, labelling, cleaning); SR 26-2 model risk management data-lineage practice (US domestic analog; supersedes SR 11-7 from 2026-04-17)",
        "retention_months": 12,
        "scope_note": "Documents dataset lineage and governance metadata for a training run. Does NOT validate dataset quality, bias, or representativeness -- those remain a firm judgment call outside this kernel's deterministic boundary.",
        "sha256_prev_lineage_hash": null,
        "source_dataset_ids": [
          "ds-core-banking-txn-log-2024-2026"
        ],
        "table_version": "EU-AIA-ART10-2024-1689-R1",
        "zero_pii_notice": "dataset_id and source_dataset_ids are STRUCTURAL catalog identifiers only. This kernel never ingests, stores, or echoes dataset contents -- zero PII by construction."
      }
    }
  }
}