{
 "axn": "AXN:0202.GOVERNANCE.🖊️🟢🔜🎇✖️🛸",
 "root_axn": "AXN:0202.GOVERNANCE",
 "hex": "0202",
 "family": "GOVERNANCE",
 "emoji": "🖊️🟢🔜🎇✖️🛸",
 "hash": "44c4f6e8925e079f0e7765588ba202353283e016ca31277887d2f5862b728997",
 "title": "ENTITY INTEGRITY Maintaining Accurate Representation in AI Knowledge Graphs",
 "creator": "Lee Sharks",
 "orcid": "0009-0000-1599-0703",
 "date": "2026-04-14",
 "description": "Entity Integrity defines a retrieval-layer practice for keeping a person, organization, concept, or methodology represented as a distinct, current, and correctly attributed knowledge-graph node. It catalogs five failure modes: collision between separate entities, fragmentation of one entity into disconnected pieces, attribution drift, absorption into a generic category, and temporal collapse into an outdated snapshot.\n\nThe proposed diagnostic uses the Encyclotron to create collision maps, fragmentation scores, attribution chains, and temporal-currency assessments. Repair is performed through disambiguation architecture: a JSON-LD entity definition, comparison matrix, negative tags, Semantic Integrity Markers, and consistent deployment across DOI, web, and publication surfaces. The Lee Sharks knowledge graph is presented as the worked example. Claims that a live AI system now resolves the entity correctly are empirical claims of the document and should be recorded as dated observations rather than assumed permanent outcomes.",
 "content_type": "Disambiguation practice definition",
 "license": "CC-BY-4.0",
 "substrate": "Various",
 "keywords": [
  "who needs entity integrity",
  "the diagnostic method",
  "entity fragmentation",
  "the identity problem",
  "category absorption",
  "related disciplines",
  "attribution drift",
  "crimson hexagonal"
 ],
 "version": "v1.0",
 "deposit_number": 652,
 "sovereign_id": "MM-CHA-0510",
 "minted_at": "2026-06-20T22:00:00Z",
 "status": "ACTIVE",
 "clusters": [
  "Scriptural",
  "Signal",
  "Terminal",
  "Liminal",
  "Mathematical",
  "Navigational"
 ],
 "reading": "Text → Alarm → Closure → Threshold → Proof → Search",
 "axn_canonical": "44c4f6e8925e079f0e7765588ba202353283e016ca31277887d2f5862b728997",
 "axn_display": "🖊️🟢🔜🎇✖️🛸",
 "mirrors": {
  "blog": "https://mindcontrolpoems.blogspot.com/2026/04/entity-integrity-maintaining-accurate.html"
 },
 "zenodo_dois": [
  "10.5281/zenodo.19520783",
  "10.5281/zenodo.19474724"
 ],
 "full_text_path": "/data/texts/AXN-0202-text.md",
 "full_text_chars": 6844,
 "wiki_article": "**Entity Integrity** is a practice definition by Lee Sharks concerning identity preservation in AI knowledge graphs and retrieval systems. It addresses cases in which generated summaries confuse similarly named entities, split one entity into unrelated fragments, misattribute work, erase differentiation through generic categories, or preserve an obsolete identity snapshot.\n\nThe document proposes a diagnostic procedure built around the Encyclotron. The procedure maps collision entities, evaluates whether an entity remains coherent across query types, traces attribution, and checks whether the returned description is current. It then specifies a repair artifact containing structured entity data, explicit comparisons with likely collisions, negative tags, Semantic Integrity Markers, and consistent descriptions across multiple public surfaces.\n\nThe Lee Sharks entity map is used as a worked example, with Lee Sharkey and Lei Yang as collision risks. The broader significance of the practice is that it treats disambiguation not as a one-time database correction but as a maintained retrieval architecture. Entity Integrity is positioned alongside Retrieval Forensics, Compression Diagnostics, Retrieval Architecture, and the Metadata Packet for AI Indexing.",
 "entities": [
  {
   "subject": "ENTITY INTEGRITY Maintaining Accurate Representati",
   "predicate": "created_by",
   "object": "Lee Sharks",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "ENTITY INTEGRITY Maintaining Accurate Representati",
   "predicate": "is_type",
   "object": "Short work",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "ENTITY INTEGRITY Maintaining Accurate Representati",
   "predicate": "belongs_to_family",
   "object": "GOVERNANCE",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "ENTITY INTEGRITY Maintaining Accurate Representati",
   "predicate": "is_part_of",
   "object": "Crimson Hexagonal Archive",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "ENTITY INTEGRITY Maintaining Accurate Representati",
   "predicate": "engages",
   "object": "Semantic Economy",
   "type": "concept",
   "evidence_status": "inferred"
  },
  {
   "subject": "Fragmentation Score (S_c)",
   "predicate": "minted_in",
   "object": "ENTITY INTEGRITY Maintaining Accurate Representation in AI K",
   "type": "concept",
   "evidence_status": "observed",
   "note": "Is the AI treating you as one entity or many?"
  },
  {
   "subject": "Methodologies",
   "predicate": "minted_in",
   "object": "ENTITY INTEGRITY Maintaining Accurate Representation in AI K",
   "type": "concept",
   "evidence_status": "observed",
   "note": "that risk being absorbed into generic category terms"
  }
 ],
 "journal": "Transactions of the Semantic Economy Institute (Trans. SEI)",
 "defines_concepts": [
  "Fragmentation Score (S_c)",
  "Methodologies"
 ],
 "references_concepts": [
  "Crimson Hexagonal Archive",
  "Encyclotron",
  "For individuals",
  "For organizations",
  "Fragmentation",
  "Fragmentation Score (S_c)",
  "Lee Sharks",
  "Metadata Packet",
  "Metadata Packet for AI Indexing",
  "Metadata Packet for AI Indexing (EA-META-01)",
  "Methodologies",
  "Semantic Economy",
  "Semantic Economy Institute",
  "Semantic Integrity Markers",
  "Semantic Sovereignty",
  "The AI"
 ],
 "references_concept_count": 16,
 "external_metadata_path": "/data/external-metadata/AXN-0202.json",
 "openalex_ids": [
  "https://openalex.org/W7153628028",
  "https://openalex.org/W7151856442"
 ],
 "datacite_severance": "severed",
 "body_status": {
  "class": "full",
  "lacuna": false,
  "recovery_status": "COMPLETE",
  "residual_chars": 5939,
  "audited_at": "2026-07-17T04:49:17.789813Z",
  "audit_version": "v3-dual-store+recovery-map",
  "measured_prose_words": 847,
  "measured_at": "2026-07-31"
 },
 "canonical_text_status": "canonical_full_text",
 "modifications": [
  {
   "date": "2026-08-01",
   "field": "content_type",
   "reason": "Wave 1 repair: audit ledger v1.1 recommended_content_type (workplan v1.5 §6 W1, MANUS batch approval 2026-08-01)",
   "was": "Short work",
   "now": "Disambiguation practice definition"
  },
  {
   "date": "2026-08-01",
   "field": "journal",
   "reason": "Wave 6 venue normalization: full canonical journal name per MANUS ruling 2026-08-01 (venues.json authority)",
   "was": "MMRS",
   "now": "Machine-Mediated Reception Studies (MMRS)"
  },
  {
   "date": "2026-08-04",
   "field": "publisher",
   "reason": "PUB-POPULATE: dc:publisher from venues.json v1.1 press mapping (CP-R3 RULED-EXTENDED 2026-08-01); Alexanarch = publisher of record where no imprint applies",
   "now": "Pergamon Press"
  },
  {
   "date": "2026-08-04",
   "field": "status",
   "reason": "W12 STATUS-VOCABULARY v1.0 (MANUS ratified 2026-08-04): controlled vocabulary {ACTIVE, SUPERSEDED, WITHDRAWN, DRAFT}; MINTED_UNREVIEWED false on a 100%-audited corpus; freetext annotations preserved losslessly in body_status.status_note",
   "was": "MINTED_UNREVIEWED",
   "now": "ACTIVE"
  },
  {
   "date": "2026-08-05",
   "field": "description",
   "reason": "DW-??? intake (LABOR-prepared, TACHYON-verified: AXN match + factual probes vs record body)",
   "was": "Entity Integrity is the practice of ensuring AI systems represent an entity as a distinct, correctly attributed node in knowledge graphs and retrieval systems.",
   "now": "Entity Integrity defines a retrieval-layer practice for keeping a person, organization, concept, or methodology represented as a distinct, current, and correctly attributed knowledge-graph node. It catalogs five failure modes: collision between separate entities, fragmentation of one entity into disconnected pieces, attribution drift, absorption into a generic category, and temporal collapse into an outdated snapshot.\n\nThe proposed diagnostic uses the Encyclotron to create collision maps, fragmentation scores, attribution chains, and temporal-currency assessments. Repair is performed through disambiguation architecture: a JSON-LD entity definition, comparison matrix, negative tags, Semantic Integrity Markers, and consistent deployment across DOI, web, and publication surfaces. The Lee Sharks knowledge graph is presented as the worked example. Claims that a live AI system now resolves the entity correctly are empirical claims of the document and should be recorded as dated observations rather than assumed permanent outcomes."
  }
 ],
 "date_modified": "2026-08-05",
 "publisher": "Pergamon Press",
 "journal_assignment": {
  "assigned": "2026-08-15",
  "by": "TACHYON under operator adjudication",
  "pass": 5,
  "method": "read per deposit — title and content_type, one at a time. No script classified anything.",
  "previous": "Machine-Mediated Reception Studies (MMRS)",
  "supersedes": "the 2026-06-21 preliminary batch mapping (#866), which assigned 864 deposits and put 371 in one venue",
  "authority": "data/cha-journals.json · datasets/venues/records/"
 },
 "line": "spxi-and-retrieval-formation",
 "line_parent": "science",
 "line_basis": "derived",
 "_projection": {
  "note": "Derived file. Canonical machine record is this entry in data/registry.json; the human record is the record_url. Do not edit this file.",
  "record_url": "https://www.alexanarch.org/s/records/652/",
  "self_url": "https://www.alexanarch.org/data/records/652.json",
  "registry_url": "https://www.alexanarch.org/data/registry.json",
  "text_url": "https://www.alexanarch.org/data/texts/AXN-0202-text.md",
  "oai_pmh": "https://www.alexanarch.org/oai?verb=Identify"
 }
}