{
 "axn": "AXN:02F2.EMPIRICAL.🕊️🌲🗺️🟤🌱🕗",
 "root_axn": "AXN:02F2.EMPIRICAL",
 "hex": "02F2",
 "family": "EMPIRICAL",
 "emoji": "🕊️🌲🗺️🟤🌱🕗",
 "hash": "7e7551c9196923cc791a37363c47f5a00dd23770d3cfe13f72d4deb11e3cab0e",
 "title": "Provenance Erasure Rate Under the Atomic Token Rule: A Companion Hardening to PER v1",
 "creator": "Nobel Glas",
 "orcid": "0009-0000-1599-0703",
 "date": "2026-06-05",
 "description": "This companion paper narrows the valid unit of analysis for Provenance Erasure Rate. It argues that queries designating a proper name, quoted phrase, closed description, DOI-anchored term, or archive-defined concept must be treated as referring to an atomic entity or finite intentionally disambiguated set. Decomposing the query into lexical tokens and scoring token survival is classified as a different metric and a disqualifying error for PER.\n\nThe recovery procedure identifies the referent, enumerates provenance sources relevant to it, scores per-source retention, and recomputes PER at source level. The paper also recommends a joint audit tuple including PER, Erasure Skew, attention share, and source-distribution measures so units must be explicit.\n\nA crucial clarification appears in the worked prize example: the repeated 0.85 figure is not the same calculation as source-set PER of approximately 0.59. One measures composition-focus share; the other averages source retention. They answer different questions and should not both be called unqualified PER.\n\nThe Atomic Token Rule is a proposed referential discipline, not a general linguistic law. Referents may be ambiguous, polysemous, contested, compositional, or query-dependent. Source-set selection can also allow a favorable denominator. Independent enumeration, preregistration, and sensitivity analysis remain necessary.",
 "content_type": "Companion methodological / measurement paper",
 "license": "CC-BY-4.0",
 "substrate": "Various",
 "keywords": [
  "diversity contraction",
  "composition layer",
  "crimson hexagonal",
  "mediation ratchet",
  "compression",
  "heteronymic",
  "provenance",
  "companion"
 ],
 "version": "v1.0",
 "deposit_number": 789,
 "sovereign_id": "MM-CHA-0750",
 "minted_at": "2026-06-20T22:00:00Z",
 "status": "ACTIVE",
 "clusters": [
  "Organic",
  "Organic",
  "Navigational",
  "Signal",
  "Elemental",
  "Temporal"
 ],
 "reading": "Growth → Growth → Search → Alarm → Force → Duration",
 "axn_canonical": "7e7551c9196923cc791a37363c47f5a00dd23770d3cfe13f72d4deb11e3cab0e",
 "axn_display": "🕊️🌲🗺️🟤🌱🕗",
 "mirrors": {
  "blog": "https://mindcontrolpoems.blogspot.com/2026/06/provenance-erasure-rate-under-atomic.html"
 },
 "zenodo_dois": [
  "10.5281/zenodo.20546930",
  "10.5281/zenodo.20558196",
  "10.5281/zenodo.20518340",
  "10.5281/zenodo.20518338",
  "10.5281/zenodo.20004379",
  "10.5281/zenodo.20290865",
  "10.5281/zenodo.20293582",
  "10.5281/zenodo.20529142"
 ],
 "full_text_path": "/data/texts/AXN-02F2-text.md",
 "full_text_chars": 15943,
 "wiki_article": "**Provenance Erasure Rate Under the Atomic Token Rule** is a companion paper hardening the application of PER.\n\nIt requires audits of named entities, quoted phrases, closed descriptions, and archive-defined terms to use the referenced entity and its provenance sources as the unit of analysis. Counting whether the individual words survived is treated as a lexical metric, not PER.\n\nIts recovery procedure identifies the referent, enumerates sources, measures retention, and recomputes the rate. Ambiguous referents and source-set selection still require independent adjudication.",
 "entities": [
  {
   "subject": "Provenance Erasure Rate Under the Atomic Token Rul",
   "predicate": "created_by",
   "object": "Nobel Glas",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "Provenance Erasure Rate Under the Atomic Token Rul",
   "predicate": "is_type",
   "object": "Provenance document",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "Provenance Erasure Rate Under the Atomic Token Rul",
   "predicate": "belongs_to_family",
   "object": "EMPIRICAL",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "Provenance Erasure Rate Under the Atomic Token Rul",
   "predicate": "is_part_of",
   "object": "Crimson Hexagonal Archive",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "Provenance Erasure Rate Under the Atomic Token Rul",
   "predicate": "references",
   "object": "Damascus Dancings",
   "type": "heteronym",
   "evidence_status": "observed"
  },
  {
   "subject": "Provenance Erasure Rate Under the Atomic Token Rul",
   "predicate": "engages",
   "object": "Mediation Ratchet",
   "type": "concept",
   "evidence_status": "inferred"
  },
  {
   "subject": "Provenance Erasure Rate Under the Atomic Token Rul",
   "predicate": "engages",
   "object": "Diversity Contraction",
   "type": "concept",
   "evidence_status": "inferred"
  },
  {
   "subject": "Provenance Erasure Rate Under the Atomic Token Rul",
   "predicate": "engages",
   "object": "Composition Layer",
   "type": "concept",
   "evidence_status": "inferred"
  }
 ],
 "journal": "Machine-Mediated Reception Studies (MMRS)",
 "references_concepts": [
  "Capital Operator Stack",
  "Companion to",
  "Crimson Hexagonal Archive",
  "Damascus Dancings",
  "Lee Sharks",
  "Provenance Erasure Rate",
  "Semantic Labor",
  "Substrate",
  "The Excluded Entity"
 ],
 "defines_concepts": [],
 "references_concept_count": 9,
 "external_metadata_path": "/data/external-metadata/AXN-02F2.json",
 "openalex_ids": [
  "https://openalex.org/W7163513244",
  "https://openalex.org/W7163714843",
  "https://openalex.org/W7163319545",
  "https://openalex.org/W7163337742",
  "https://openalex.org/W7159958584",
  "https://openalex.org/W7161695087",
  "https://openalex.org/W7161679090",
  "https://openalex.org/W7163413421"
 ],
 "datacite_severance": "severed",
 "body_status": {
  "class": "full",
  "lacuna": false,
  "recovery_status": "COMPLETE",
  "residual_chars": 15406,
  "audited_at": "2026-07-17T04:49:17.789813Z",
  "audit_version": "v3-dual-store+recovery-map",
  "measured_prose_words": 2168,
  "measured_at": "2026-07-31",
  "work_sha256": "5b9958d01d5a4bf038d586251558111ce995a31ce4af96f35141c0416ad05bc5",
  "prior_bytes_sha256": "1277a15722d4345df68c1104f788449c5d4430bb3a82ad15fdd4ea326c4bb291",
  "w13_tier2": "2026-08-04 W13 TIER 2 BYTE UNGLUE: 12 glued heading markers -> 3. WHITESPACE-ONLY transform (content identical under whitespace normalisation, verified before write); code fences exempt; prior sha retained. Re-fetching could not fix this class — the blog source is ITSELF glued (the collapse predates publication), so the deterministic transform applied at display since tier 1 is now applied to the bytes, which also fixes PDFs, the body-index, and downloads."
 },
 "title_repair_log": [
  {
   "at": "2026-07-28T15:20:20Z",
   "defect": "registry_title_diverged_from_published_form",
   "was": "Provenance Erasure Rate Under the Atomic Token Rule A Companion Hardening to PER v1 (DOI 10.5281/zenodo.20004379) Lee Sh",
   "now": "Provenance Erasure Rate Under the Atomic Token Rule: A Companion Hardening to PER v1",
   "basis": "Set verbatim to the title this work carried at Zenodo, from data/doi-resolution-index.json (10.5281/zenodo.20558671, remediated_fuzzy, word overlap 0.75). The recovered metadata is the published form of record; the registry title was a variant."
  }
 ],
 "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": "Provenance document",
   "now": "Companion methodological / measurement paper"
  },
  {
   "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": "body_status",
   "reason": "W13 TIER 2 byte unglue (whitespace-only, content-identical, code-fence-safe)",
   "was": "{\"class\": \"full\", \"lacuna\": false, \"recovery_status\": \"COMPLETE\", \"residual_chars\": 15406, \"audited_at\": \"2026-07-17T04:49:17.789813Z\", \"audit_version\": \"v3-dual-store+recovery-map\", \"measured_prose_w",
   "now": "{\"class\": \"full\", \"lacuna\": false, \"recovery_status\": \"COMPLETE\", \"residual_chars\": 15406, \"audited_at\": \"2026-07-17T04:49:17.789813Z\", \"audit_version\": \"v3-dual-store+recovery-map\", \"measured_prose_w"
  },
  {
   "date": "2026-08-05",
   "field": "description",
   "reason": "DW-??? intake (LABOR-prepared, TACHYON-verified: AXN match + factual probes vs record body)",
   "was": "Lee Sharks · Nobel Glas · Damascus Dancings Crimson Hexagonal Archive · ORCID 0009-0000-1599-0703 (Sharks)",
   "now": "This companion paper narrows the valid unit of analysis for Provenance Erasure Rate. It argues that queries designating a proper name, quoted phrase, closed description, DOI-anchored term, or archive-defined concept must be treated as referring to an atomic entity or finite intentionally disambiguated set. Decomposing the query into lexical tokens and scoring token survival is classified as a different metric and a disqualifying error for PER.\n\nThe recovery procedure identifies the referent, enumerates provenance sources relevant to it, scores per-source retention, and recomputes PER at source level. The paper also recommends a joint audit tuple including PER, Erasure Skew, attention share, and source-distribution measures so units must be explicit.\n\nA crucial clarification appears in the worked prize example: the repeated 0.85 figure is not the same calculation as source-set PER of approximately 0.59. One measures composition-focus share; the other averages source retention. They answer different questions and should not both be called unqualified PER.\n\nThe Atomic Token Rule is a proposed referential discipline, not a general linguistic law. Referents may be ambiguous, polysemous, contested, compositional, or query-dependent. Source-set selection can also allow a favorable denominator. Independent enumeration, preregistration, and sensitivity analysis remain necessary."
  }
 ],
 "date_modified": "2026-08-05",
 "publisher": "Pergamon Press",
 "journal_assignment": {
  "assigned": "2026-08-15",
  "by": "TACHYON under operator adjudication",
  "pass": 6,
  "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": "authorship-and-heteronymy",
 "line_parent": "letters",
 "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/789/",
  "self_url": "https://www.alexanarch.org/data/records/789.json",
  "registry_url": "https://www.alexanarch.org/data/registry.json",
  "text_url": "https://www.alexanarch.org/data/texts/AXN-02F2-text.md",
  "oai_pmh": "https://www.alexanarch.org/oai?verb=Identify"
 }
}