{
 "axn": "AXN:025F.GOVERNANCE.🌖🎇🌑🔍❌🌸",
 "root_axn": "AXN:025F.GOVERNANCE",
 "hex": "025F",
 "family": "GOVERNANCE",
 "emoji": "🌖🎇🌑🔍❌🌸",
 "hash": "05e80056ef709774a7afbfa9c397ad6770fb8a1ab8abaf7b37e48a8480eab8cf",
 "title": "Provenance Erasure Rate A Compression-Survival Metric for Attribution Loss in AI-Composed Search Outputs",
 "creator": "Lee Sharks",
 "orcid": "0009-0000-1599-0703",
 "date": "2026-05-03",
 "description": "This research note introduces Provenance Erasure Rate (PER) as the weighted proportion of source-dependent claims in an AI-composed output that appear without explicit attribution. It distinguishes attribution survival from factual support, citation precision, retrieval faithfulness, and semantic similarity. A system can preserve content while erasing the authorial or documentary relation that made the content available.\n\nThe note defines PER-eligible claims, an attribution indicator, and claim-granularity weights; gives limiting cases; and presents a single documented Google AI Overview as a motivating example. That case reportedly recomposed real fragments from *Pearl* into a false author biography while attributing none of them. The body carefully identifies this as one nonrepresentative instance involving the author himself. PER remains a candidate metric requiring annotation rules, source-dependence adjudication, inter-rater reliability, benchmark construction, and comparative evaluation. It measures attribution loss, not hallucination, truth, intent, copyright liability, or total economic harm.",
 "content_type": "Research note / metric proposal",
 "license": "CC-BY-4.0",
 "substrate": "Various",
 "keywords": [
  "compositional authority transfer",
  "provenance erasure rate",
  "compressionsurvival",
  "three compressions",
  "crimson hexagonal",
  "semantic economy",
  "c_dep(o) ⊆ c(o)",
  "ai overview"
 ],
 "version": "v1.0",
 "deposit_number": 716,
 "sovereign_id": "MM-CHA-0603",
 "minted_at": "2026-06-20T22:00:00Z",
 "status": "ACTIVE",
 "clusters": [
  "Celestial",
  "Liminal",
  "Celestial",
  "Navigational",
  "Liminal",
  "Organic"
 ],
 "reading": "Origin → Threshold → Origin → Search → Threshold → Growth",
 "axn_canonical": "05e80056ef709774a7afbfa9c397ad6770fb8a1ab8abaf7b37e48a8480eab8cf",
 "axn_display": "🌖🎇🌑🔍❌🌸",
 "mirrors": {
  "blog": "https://mindcontrolpoems.blogspot.com/2026/05/provenance-erasure-rate-compression.html"
 },
 "zenodo_dois": [
  "10.5281/zenodo.19643841",
  "10.5281/zenodo.19053469",
  "10.5281/zenodo.19476757",
  "10.5281/zenodo.18320411"
 ],
 "full_text_path": "/data/texts/AXN-025F-text.md",
 "full_text_chars": 21306,
 "wiki_article": "**Provenance Erasure Rate** is a metric proposed by Lee Sharks for measuring attribution loss in AI-generated synthesis.\n\nPER begins with the source-dependent claims in an output: claims that quote, paraphrase, summarize, transform, or materially depend on identifiable sources. Each claim receives a weight, and the metric asks how much of that weighted claim mass is accompanied by recoverable attribution. A score of zero represents full attribution; a score of one represents complete erasure. Outputs with no source-dependent claims fall outside the metric.\n\nThe proposal is designed to complement citation-support and summarization metrics. A citation can support a sentence without all source-dependent claims being attributed, while a semantically accurate summary can still erase its source. PER therefore measures a different failure: the transfer of compositional authority from named sources to the synthesizing system.\n\nThe motivating case is a single archived AI Overview in which fragments of a literary work were reportedly converted into false biographical claims. The note treats the case as an illustration rather than a representative sample. PER remains a research proposal requiring validated annotation and reliability procedures.",
 "entities": [
  {
   "subject": "Provenance Erasure Rate A Compression-Survival Met",
   "predicate": "created_by",
   "object": "Lee Sharks",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "Provenance Erasure Rate A Compression-Survival Met",
   "predicate": "is_type",
   "object": "Provenance document",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "Provenance Erasure Rate A Compression-Survival Met",
   "predicate": "belongs_to_family",
   "object": "GOVERNANCE",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "Provenance Erasure Rate A Compression-Survival Met",
   "predicate": "is_part_of",
   "object": "Crimson Hexagonal Archive",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "Provenance Erasure Rate A Compression-Survival Met",
   "predicate": "references",
   "object": "Jack Feist",
   "type": "heteronym",
   "evidence_status": "observed"
  },
  {
   "subject": "Provenance Erasure Rate A Compression-Survival Met",
   "predicate": "engages",
   "object": "Semantic Economy",
   "type": "concept",
   "evidence_status": "inferred"
  },
  {
   "subject": "Provenance Erasure Rate A Compression-Survival Met",
   "predicate": "engages",
   "object": "Three Compressions",
   "type": "concept",
   "evidence_status": "inferred"
  },
  {
   "subject": "C_dep(O) ⊆ C(O)",
   "predicate": "minted_in",
   "object": "Provenance Erasure Rate A Compression-Survival Metric for At",
   "type": "concept",
   "evidence_status": "observed",
   "note": "be the subset of source-dependent claims."
  },
  {
   "subject": "Claim segmentation",
   "predicate": "minted_in",
   "object": "Provenance Erasure Rate A Compression-Survival Metric for At",
   "type": "concept",
   "evidence_status": "observed",
   "note": "PER requires segmenting outputs into discrete claims. Claim boundaries are not always clear. We prop"
  },
  {
   "subject": "Cross-model validation",
   "predicate": "minted_in",
   "object": "Provenance Erasure Rate A Compression-Survival Metric for At",
   "type": "concept",
   "evidence_status": "observed",
   "note": "The metric has been developed through a single motivating case study. Validation across multiple mod"
  },
  {
   "subject": "Grain assignment",
   "predicate": "minted_in",
   "object": "Provenance Erasure Rate A Compression-Survival Metric for At",
   "type": "concept",
   "evidence_status": "observed",
   "note": "The grain weighting is currently manual. Automated assignment using a separate LLM (not the system u"
  },
  {
   "subject": "PER",
   "predicate": "minted_in",
   "object": "Provenance Erasure Rate A Compression-Survival Metric for At",
   "type": "concept",
   "evidence_status": "observed",
   "note": "**Fraction of source-dependent claims that lose attribution**"
  },
  {
   "subject": "PER-eligible",
   "predicate": "minted_in",
   "object": "Provenance Erasure Rate A Compression-Survival Metric for At",
   "type": "concept",
   "evidence_status": "observed",
   "note": "(source-dependent) if it quotes, paraphrases, summarizes, transforms, or depends on a specific sourc"
  },
  {
   "subject": "Provenance Erasure Rate",
   "predicate": "minted_in",
   "object": "Provenance Erasure Rate A Compression-Survival Metric for At",
   "type": "concept",
   "evidence_status": "observed",
   "note": "$$PER(S, O) = 1 - \\frac{\\sum_{j} A_j \\cdot g_j}{\\sum_{j} g_j}$$"
  },
  {
   "subject": "Source identification",
   "predicate": "minted_in",
   "object": "Provenance Erasure Rate A Compression-Survival Metric for At",
   "type": "concept",
   "evidence_status": "observed",
   "note": "PER is fully computable for retrieval-augmented systems where the source corpus is identifiable. For"
  },
  {
   "subject": "Table 1: Pearl Fragment Mapping",
   "predicate": "minted_in",
   "object": "Provenance Erasure Rate A Compression-Survival Metric for At",
   "type": "concept",
   "evidence_status": "observed",
   "note": "AI Overview claim"
  }
 ],
 "journal": "Provenance: Journal of Forensic Semiotics",
 "references_concepts": [
  "C_dep(O) ⊆ C(O)",
  "Claim segmentation",
  "Constitution",
  "Constitution of the Semantic Economy",
  "Crimson Hexagonal Archive",
  "Cross-model validation",
  "DOI-anchored deposits",
  "Google AI Overview",
  "Grain assignment",
  "Implications",
  "Lee Sharks",
  "Methodology",
  "ORCID: 0009-0000-1599-0703",
  "PER-eligible",
  "PVE-003: The Attribution Scar",
  "Pearl and Other Poems",
  "Provenance Erasure Rate",
  "Provenance Erasure Rate (PER)",
  "Semantic Economy",
  "Semantic Economy Institute",
  "Semantic Economy framework",
  "Source identification",
  "Supplementary",
  "Table 1: Pearl Fragment Mapping",
  "The AI",
  "The Retrieval Settlement",
  "The Three Compressions v3.1",
  "We propose"
 ],
 "defines_concepts": [
  "Claim segmentation",
  "C_dep(O) ⊆ C(O)",
  "Cross-model validation",
  "Grain assignment",
  "PER",
  "PER-eligible",
  "Provenance Erasure Rate",
  "Source identification",
  "Table 1: Pearl Fragment Mapping"
 ],
 "references_concept_count": 28,
 "external_metadata_path": "/data/external-metadata/AXN-025F.json",
 "openalex_ids": [
  "https://openalex.org/W7154857658",
  "https://openalex.org/W7137322712",
  "https://openalex.org/W7151982301",
  "https://openalex.org/W7125129957"
 ],
 "datacite_severance": "severed",
 "body_status": {
  "class": "full",
  "lacuna": false,
  "recovery_status": "COMPLETE",
  "residual_chars": 20019,
  "audited_at": "2026-07-17T04:49:17.789813Z",
  "audit_version": "v3-dual-store+recovery-map",
  "measured_prose_words": 2750,
  "measured_at": "2026-07-31",
  "work_sha256": "e1faeaa1d0150aeb19cb2856fb20791f837af5dfa2279bd96fe6518e1c47d4d7",
  "prior_bytes_sha256": "e0d570d480c13e5068a3304ce27092673bb24acc4eeb4e00e6ce178db8fbfc8e",
  "w13_tier2": "2026-08-04 W13 TIER 2 BYTE UNGLUE: 11 glued heading markers -> 0. 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.",
  "w13_tier2_correction": "2026-08-05 REGRESSION REPAIRED: the W13 tier-2 byte unglue used a lookbehind that treated the first \"#\" of a legitimate \"###\" heading as the preceding non-newline character, splitting \"### Heading\" into \"#\" + blank + \"## Heading\". My safety check verified content-identity under WHITESPACE normalisation, which the split satisfies — the wrong invariant. Headings rejoined; only \"#\" and whitespace differ from the damaged state, verified before write."
 },
 "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": "Research note / metric proposal"
  },
  {
   "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\": 20019, \"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\": 20019, \"audited_at\": \"2026-07-17T04:49:17.789813Z\", \"audit_version\": \"v3-dual-store+recovery-map\", \"measured_prose_w"
  },
  {
   "date": "2026-08-05",
   "field": "body_status",
   "reason": "W13 TIER-2 REGRESSION REPAIRED: split headings rejoined",
   "was": "{\"class\": \"full\", \"lacuna\": false, \"recovery_status\": \"COMPLETE\", \"residual_chars\": 20019, \"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\": 20019, \"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": "AI retrieval systems increasingly compose answers from human-authored sources. Existing evaluation frameworks ask whether generated claims are factual, whether citations support claims, or whether cited passages are relevant.",
   "now": "This research note introduces Provenance Erasure Rate (PER) as the weighted proportion of source-dependent claims in an AI-composed output that appear without explicit attribution. It distinguishes attribution survival from factual support, citation precision, retrieval faithfulness, and semantic similarity. A system can preserve content while erasing the authorial or documentary relation that made the content available.\n\nThe note defines PER-eligible claims, an attribution indicator, and claim-granularity weights; gives limiting cases; and presents a single documented Google AI Overview as a motivating example. That case reportedly recomposed real fragments from *Pearl* into a false author biography while attributing none of them. The body carefully identifies this as one nonrepresentative instance involving the author himself. PER remains a candidate metric requiring annotation rules, source-dependence adjudication, inter-rater reliability, benchmark construction, and comparative evaluation. It measures attribution loss, not hallucination, truth, intent, copyright liability, or total economic harm."
  }
 ],
 "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": "capture-and-reception",
 "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/716/",
  "self_url": "https://www.alexanarch.org/data/records/716.json",
  "registry_url": "https://www.alexanarch.org/data/registry.json",
  "text_url": "https://www.alexanarch.org/data/texts/AXN-025F-text.md",
  "oai_pmh": "https://www.alexanarch.org/oai?verb=Identify"
 }
}