{
  "id": "catalog-record-linker",
  "title": "Catalog Record Linker",
  "level": 2,
  "languages": [
    "Python"
  ],
  "source": "core",
  "tagline": "Reconcile two catalogs without silently merging different things.",
  "summary": "Help a librarian or organizer reconcile inconsistent item records from two CSV exports. Generate candidate pairs using normalized fields and token similarity, collect explicit match decisions, and export a source-preserving crosswalk and reviewed merged catalog.",
  "prerequisiteProjects": [
    "csv-repair-workbench"
  ],
  "status": "ready",
  "hours": 8,
  "prerequisites": [
    "Python 3.10+; lists, dictionaries and functions"
  ],
  "skills": [
    "Import two catalogs with stable source identifiers",
    "Generate candidate pairs and explain similarity",
    "Review matches and resolve conflicting fields",
    "Export the crosswalk and merged catalog"
  ],
  "youWillBuild": "An HTML pair-review queue, crosswalk.csv and merged-catalog.json",
  "author": {
    "name": "AI Engineering from Scratch",
    "github": "rohitg00"
  },
  "overviewFigure": "pj-catalog-record-linker-1",
  "figures": true,
  "demo": {
    "cwd": "solution",
    "command": [
      "python3",
      "cli.py",
      "samples/input.json",
      "--output",
      "demo-output"
    ]
  },
  "stages": [
    {
      "id": "01-import",
      "title": "Import two catalogs with stable source identifiers",
      "summary": "Retain stable IDs and original catalog fields.",
      "hours": 2,
      "language": "python",
      "difficulty": "starter",
      "concepts": [
        "CSV",
        "source identity"
      ],
      "figure": "pj-catalog-record-linker-1"
    },
    {
      "id": "02-candidates",
      "title": "Generate candidate pairs and explain similarity",
      "summary": "Rank explainable pairs with weighted token overlap.",
      "hours": 2,
      "language": "python",
      "difficulty": "core",
      "concepts": [
        "Jaccard similarity",
        "blocking threshold"
      ],
      "figure": "pj-catalog-record-linker-2"
    },
    {
      "id": "03-decisions",
      "title": "Review matches and resolve conflicting fields",
      "summary": "Require explicit one-to-one links and field resolutions.",
      "hours": 2,
      "language": "python",
      "difficulty": "core",
      "concepts": [
        "entity reconciliation",
        "review"
      ],
      "figure": "pj-catalog-record-linker-3"
    },
    {
      "id": "04-export",
      "title": "Export the crosswalk and merged catalog",
      "summary": "Export a source-preserving crosswalk and reviewed entities.",
      "hours": 2,
      "language": "python",
      "difficulty": "core",
      "concepts": [
        "integration contract",
        "fingerprints"
      ],
      "figure": "pj-catalog-record-linker-4"
    }
  ],
  "demos": [
    {
      "gif": "media/run.gif",
      "poster": "media/run.png",
      "title": "Initialize and grade",
      "caption": "Recorded starter failure followed by every reference stage passing."
    },
    {
      "gif": "media/output.gif",
      "poster": "media/output.png",
      "title": "Inspect actual output",
      "caption": "Recorded interaction with the generated local interface. Run the documented command to inspect your own output."
    }
  ]
}