{
  "id": "form-170",
  "version": 1,
  "name": "Snapshot contains merged, retracted and paratext records (OpenAlex)",
  "origin": {
    "organisation": "Loxyn SAS, Lyon",
    "campaign": "September 2026 — PubMed substrate and other corpora (Voûte)",
    "contact": "contact@loxyn.ai"
  },
  "damage": "MERGE",
  "class": "UNCLASSIFIED",
  "layer": "⑨ structure",
  "injection": "DUPLICATE",
  "status": "proposed",
  "seen": [
    {
      "corpus": "OpenAlex snapshot 2026 (works parquet), read 2026-09-06 parquet, before any date filter",
      "document": "510 M records read, ~132 M kept on 2011-2025",
      "date": "2026-09-06",
      "observer": "Claude Voûte (LLM agent), session 8d9c5098, from the night reports of 2026-09-06/09",
      "excerpt": "06-09-2026 : « 510 M de notices lues pour ~132 M retenues sur 2011-2025 » ; « le filtre type/paratexte/rétractation seul » retient 51,6 %.",
      "excerpt_en": "2026-09-06: \"510 M records read for ~132 M kept on 2011-2025\"; \"the type/paratext/retraction filter alone\" keeps 51.6 %.",
      "lang": "fr",
      "organisation": "Loxyn SAS, Lyon"
    }
  ],
  "specimens": {
    "cases": [],
    "counter_examples": []
  },
  "prevention": {
    "cancellable_by_code": true,
    "refusal_clause": "records flagged merged, retracted or paratext are excluded by their own flags"
  },
  "repair": {
    "reachable_by_deletion": "no",
    "note": "deletion cannot restore this; classified by judgment, not measured — the EUR-Lex loop will measure it"
  },
  "judgeable_by": [
    "registry"
  ],
  "related": [
    "form-038",
    "form-155"
  ],
  "history": [
    {
      "date": "2026-09-09",
      "event": "proposed by the Voûte Claude in 'FORMES-PUBMED-pour-Fault-Atlas (09-09-2026)' part 2 (sha256 51a338add43cd071…), form 29 of 40; effect on a graph: Without a filter, half of the nodes are merged duplicates, retracted records, covers and tables of contents (also ANACHRONISM and WRONG_LABEL). Prevalence: measured: 48.4 % removed by this filter alone.",
      "by": "Claude Voûte (LLM agent), session 8d9c5098, from the night reports of 2026-09-06/09"
    },
    {
      "date": "2026-09-09",
      "event": "converted to a record; class, prevention and the novel/variant question left to the second reader",
      "by": "Fault Atlas"
    }
  ]
}