{
  "purpose": "Synthetic teaching fixtures for reconciling an AI document-to-embedding pipeline handoff",
  "generated_on": "2026-08-24",
  "generator": "scripts/generate_ai_pipeline_handoff_fixtures.py",
  "duckdb_version": "v1.5.3",
  "scenario": {
    "documents_normalization_run": "norm-042",
    "embeddings_declared_source_run": "norm-041",
    "documents_ids": [
      "doc-001",
      "doc-002",
      "doc-004"
    ],
    "embeddings_ids": [
      "doc-001",
      "doc-002",
      "doc-003"
    ],
    "shared_matching_text_revision_ids": [
      "doc-002"
    ],
    "shared_stale_text_revision_ids": [
      "doc-001"
    ],
    "embedding_model_revision": "synthetic-3d-demo-v1",
    "embedding_dimensions": 3
  },
  "evidence_artifacts": [
    {
      "name": "generate_ai_pipeline_handoff_fixtures.py",
      "role": "fixture_generator",
      "bytes": 16497,
      "sha256": "7e8e447cab8a555f48971e8c3e6c55f7d71c381be88b438d4552ad3485614ddd"
    },
    {
      "name": "ai-pipeline-handoff-audit.sql",
      "role": "audit_sql_bundle",
      "bytes": 5855,
      "sha256": "3e6793689006b8c96babb67004fc942774475af9f1bd9b87d69e63a43aeccead"
    }
  ],
  "local_identity_findings": {
    "documents": {
      "rows": 3,
      "missing_document_ids": 0,
      "duplicate_document_ids": 0,
      "blank_text_rows": 0,
      "missing_text_revision_rows": 0,
      "missing_normalization_run_rows": 0,
      "missing_source_uri_rows": 0,
      "missing_source_revision_rows": 0,
      "missing_license_rows": 0,
      "non_synthetic_rows": 0
    },
    "embeddings": {
      "rows": 3,
      "missing_document_ids": 0,
      "duplicate_document_ids": 0,
      "missing_source_run_rows": 0,
      "missing_text_revision_rows": 0,
      "missing_embedding_run_rows": 0,
      "missing_model_revision_rows": 0,
      "unexpected_model_revision_rows": 0,
      "observed_model_revisions": 1,
      "missing_source_uri_rows": 0,
      "missing_source_revision_rows": 0,
      "missing_license_rows": 0,
      "missing_embedding_rows": 0,
      "wrong_dimension_rows": 0,
      "non_finite_rows": 0,
      "zero_vector_rows": 0,
      "non_synthetic_rows": 0
    }
  },
  "cross_stage_findings": {
    "orphan_embeddings": 1,
    "documents_without_embeddings": 1,
    "mismatched_source_run_rows": 2,
    "mismatched_text_revision_rows": 1
  },
  "failing_ids": [
    {
      "document_id": "doc-001",
      "issue": "source_normalization_run_mismatch"
    },
    {
      "document_id": "doc-001",
      "issue": "text_revision_mismatch"
    },
    {
      "document_id": "doc-002",
      "issue": "source_normalization_run_mismatch"
    },
    {
      "document_id": "doc-003",
      "issue": "orphan_embedding"
    },
    {
      "document_id": "doc-004",
      "issue": "document_without_embedding"
    }
  ],
  "limitations": [
    "Tiny synthetic teaching data; not representative of production volume or distributions",
    "The three-dimensional vectors are invented and were not produced by an embedding model",
    "The example run IDs, timestamps, source URLs, revisions, and license labels are illustrative",
    "These checks cover identity and declared lineage, not semantic quality, consent, privacy, legal fitness, or model suitability",
    "Native DuckDB generated the evidence; the repository test separately executes every published SQL statement in the shipped DuckDB-WASM build"
  ],
  "files": [
    {
      "name": "ai-pipeline-documents.parquet",
      "role": "normalized_documents_fixture",
      "bytes": 2032,
      "sha256": "04224164c6cf520359d9a8e4ef0ada743a4e483df988258ebceb3673019b4247",
      "schema": [
        {
          "name": "document_id",
          "type": "VARCHAR",
          "nullable": "YES"
        },
        {
          "name": "normalized_text",
          "type": "VARCHAR",
          "nullable": "YES"
        },
        {
          "name": "text_revision",
          "type": "VARCHAR",
          "nullable": "YES"
        },
        {
          "name": "normalization_run_id",
          "type": "VARCHAR",
          "nullable": "YES"
        },
        {
          "name": "source_uri",
          "type": "VARCHAR",
          "nullable": "YES"
        },
        {
          "name": "source_revision",
          "type": "VARCHAR",
          "nullable": "YES"
        },
        {
          "name": "license",
          "type": "VARCHAR",
          "nullable": "YES"
        },
        {
          "name": "normalized_at",
          "type": "TIMESTAMP",
          "nullable": "YES"
        },
        {
          "name": "is_synthetic",
          "type": "BOOLEAN",
          "nullable": "YES"
        }
      ],
      "expected_local_findings": {
        "rows": 3,
        "missing_document_ids": 0,
        "duplicate_document_ids": 0,
        "blank_text_rows": 0,
        "missing_text_revision_rows": 0,
        "missing_normalization_run_rows": 0,
        "missing_source_uri_rows": 0,
        "missing_source_revision_rows": 0,
        "missing_license_rows": 0,
        "non_synthetic_rows": 0
      }
    },
    {
      "name": "ai-pipeline-embeddings.parquet",
      "role": "embeddings_fixture",
      "bytes": 2138,
      "sha256": "8253195df3f13bbf273aa999e28e85955d41fa1fe49e6d15bb7d23e148316a9b",
      "schema": [
        {
          "name": "document_id",
          "type": "VARCHAR",
          "nullable": "YES"
        },
        {
          "name": "text_revision",
          "type": "VARCHAR",
          "nullable": "YES"
        },
        {
          "name": "source_normalization_run_id",
          "type": "VARCHAR",
          "nullable": "YES"
        },
        {
          "name": "embedding_run_id",
          "type": "VARCHAR",
          "nullable": "YES"
        },
        {
          "name": "embedding_model_revision",
          "type": "VARCHAR",
          "nullable": "YES"
        },
        {
          "name": "embedding",
          "type": "DOUBLE[]",
          "nullable": "YES"
        },
        {
          "name": "source_uri",
          "type": "VARCHAR",
          "nullable": "YES"
        },
        {
          "name": "source_revision",
          "type": "VARCHAR",
          "nullable": "YES"
        },
        {
          "name": "license",
          "type": "VARCHAR",
          "nullable": "YES"
        },
        {
          "name": "embedded_at",
          "type": "TIMESTAMP",
          "nullable": "YES"
        },
        {
          "name": "is_synthetic",
          "type": "BOOLEAN",
          "nullable": "YES"
        }
      ],
      "expected_local_findings": {
        "rows": 3,
        "missing_document_ids": 0,
        "duplicate_document_ids": 0,
        "missing_source_run_rows": 0,
        "missing_text_revision_rows": 0,
        "missing_embedding_run_rows": 0,
        "missing_model_revision_rows": 0,
        "unexpected_model_revision_rows": 0,
        "observed_model_revisions": 1,
        "missing_source_uri_rows": 0,
        "missing_source_revision_rows": 0,
        "missing_license_rows": 0,
        "missing_embedding_rows": 0,
        "wrong_dimension_rows": 0,
        "non_finite_rows": 0,
        "zero_vector_rows": 0,
        "non_synthetic_rows": 0
      }
    }
  ]
}