{
  "schema": "vedokrok.public-item.v1",
  "release_id": "MHC-RPUB-20260920-75ad787a",
  "url": "/knowledge/deduplicate-before-spending-attention-on-screening",
  "id": "MHC-D-RESEARCH-0513",
  "version": "0.1.0",
  "title": "Deduplicate before spending attention on screening",
  "summary": "Reading the same paper three times is not triangulation.",
  "kind": "checklist",
  "body": "Normalize obvious identifiers such as DOI, title and author/year, then merge duplicate records before substantive screening. Preserve links to all retrieval routes so you know which search found the record. Review ambiguous near-duplicates manually instead of deleting them by title similarity alone.",
  "limits": [
    "Conference papers, preprints and journal versions can be materially different; do not merge distinct versions blindly."
  ],
  "topics": [
    "union-research-search-strategy"
  ],
  "intents": [],
  "source_ids": [
    "RS-58E7CC33EB856484"
  ],
  "evidence": [
    {
      "claim": "TARCiS recommends deduplicating supplementary citation-search results before screening.",
      "source_id": "RS-58E7CC33EB856484",
      "role": "supports",
      "note": "Deduplication can mistakenly merge distinct records when metadata is poor.",
      "locator": "Recommendation 7"
    }
  ],
  "use_when": [
    "Results come from several databases, searches or citation rounds."
  ],
  "avoid_when": [
    "Conference papers, preprints and journal versions can be materially different; do not merge distinct versions blindly."
  ],
  "example": "The same AI paper found in Scopus, Google Scholar and forward citations becomes one screening record with three provenance routes.",
  "check": "Screening workload counts unique records rather than repeated database entries.",
  "checklist": [
    "Stable identifiers are used where available.",
    "Exact duplicates are merged before screening.",
    "Retrieval-source metadata is preserved.",
    "Near-duplicate titles receive manual review.",
    "Different reports from one underlying study are not automatically treated as independent studies."
  ],
  "sources": [
    {
      "id": "RS-58E7CC33EB856484",
      "title": "Guidance on terminology, application, and reporting of citation searching: the TARCiS statement",
      "url": "https://www.bmj.com/content/385/bmj-2023-078384"
    }
  ],
  "relations": [
    {
      "from": "MHC-D-RESEARCH-0513",
      "to": "MHC-D-RESEARCH-0517",
      "type": "use_before",
      "url": "/knowledge/screen-against-explicit-inclusion-criteria-not-relevance-vibes"
    }
  ],
  "collections": [
    {
      "id": "RC-F645BF33EA699D13",
      "title": "Search for evidence as a reproducible process, not a lucky query",
      "url": "/collections/search-for-evidence-as-a-reproducible-process-not-a-lucky-query"
    }
  ]
}