{
 "axn": "AXN:0273.GOVERNANCE.🪐👁️‍🗨️❌🔅🔄➗",
 "root_axn": "AXN:0273.GOVERNANCE",
 "hex": "0273",
 "family": "GOVERNANCE",
 "emoji": "🪐👁️‍🗨️❌🔅🔄➗",
 "hash": "0db0efed6f93573d772669081d1e7d34296c930a6fb05862068cd6f8c73c35c9",
 "title": "Provenance After AI Metadata Packet for Disambiguation: From Artifact Authenticity to Licensing Audit to Semantic Provenance",
 "creator": "Lee Sharks",
 "orcid": "0009-0000-1599-0703",
 "date": "2026-05-08",
 "description": "This v1.1 bridge packet maps three independent dimensions of AI-era provenance: artifact authenticity, training-corpus licensing, and semantic lineage through synthesis. It treats C2PA and Content Credentials as artifact-level infrastructure; dataset audits, W3C PROV, and legal transparency regimes as corpus-level infrastructure; and semantic provenance as the still-underdeveloped question of whether synthesized meaning remains accountable to authors, frameworks, traditions, and communities.\n\nThe packet presents semantic provenance as an extension rather than a replacement or criticism of existing fields. It acknowledges archival provenance, digital preservation, Indigenous data sovereignty, citation evaluation, RAG faithfulness, and data attribution as adjacent foundations. PER-M, PER-C, and PER-D are proposed as progressively deeper measurement variants. The body explicitly removes earlier unsupported production-system estimates and calls the metric provisional pending pilot studies and inter-rater reliability. Legal, standards, adoption, and institutional claims reflect a 2026 snapshot and require current primary-source verification.",
 "content_type": "Bridge / disciplinary-clarification metadata packet",
 "license": "CC-BY-4.0",
 "substrate": "Various",
 "keywords": [
  "adjacent measurement concepts",
  "test 1: three-layer bridge",
  "provenance-unit hierarchy",
  "training-corpus licensing",
  "what survives synthesis",
  "test 4: c2pa extension",
  "artifact authenticity",
  "temporal expectations",
  "lee sharks",
  "metadata packet",
  "disambiguation",
  "infrastructure",
  "verification",
  "preservation"
 ],
 "version": "v1.1",
 "deposit_number": 725,
 "sovereign_id": "MM-CHA-0623",
 "minted_at": "2026-06-20T22:00:00Z",
 "status": "ACTIVE",
 "clusters": [
  "Celestial",
  "Gestural",
  "Liminal",
  "Liminal",
  "Temporal",
  "Mathematical"
 ],
 "reading": "Origin → Touch → Threshold → Threshold → Duration → Proof",
 "axn_canonical": "0db0efed6f93573d772669081d1e7d34296c930a6fb05862068cd6f8c73c35c9",
 "axn_display": "🪐👁️‍🗨️❌🔅🔄➗",
 "mirrors": {
  "blog": "https://mindcontrolpoems.blogspot.com/2026/05/provenance-after-ai-metadata-packet-for.html"
 },
 "zenodo_dois": [
  "10.5281/zenodo.19202813",
  "10.5281/zenodo.20084143",
  "10.5281/zenodo.20078424",
  "10.5281/zenodo.19476757",
  "10.5281/zenodo.18166394",
  "10.5281/zenodo.18320411",
  "10.5281/zenodo.20039232"
 ],
 "full_text_path": "/data/texts/AXN-0273-text.md",
 "full_text_chars": 40964,
 "wiki_article": "**Provenance After AI** is a bridge packet by Lee Sharks that distinguishes several dimensions of provenance relevant to artificial intelligence.\n\nArtifact provenance asks whether a file came from a declared source and records its edits. Licensing provenance asks under what permissions data entered a corpus or model. Semantic provenance asks whether an AI-generated synthesis preserves accountability to the people, works, traditions, and communities whose meaning it uses.\n\nThe packet does not claim that existing provenance systems failed at their intended purposes. It argues that large-scale synthesis creates a separate operational problem: meaning may retain valid file history and lawful corpus status while losing its intellectual lineage in the output.\n\nThree provisional PER depths are proposed. Minimal provenance preserves author, source, date, and claim boundary. Conceptual provenance adds framework and tradition. Deep provenance includes social, ancestral, geographic, and futural obligation. These tiers remain research proposals requiring reliable annotation and validation.\n\nThe work is positioned as disciplinary clarification and extension. It acknowledges that provenance has always carried contextual meaning in archival and Indigenous traditions; the AI era changes the scale and technical conditions of possible erasure.",
 "entities": [
  {
   "subject": "Provenance After AI Metadata Packet for Disambiguation",
   "predicate": "created_by",
   "object": "Lee Sharks",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "Provenance After AI Metadata Packet for Disambiguation",
   "predicate": "is_type",
   "object": "Dataset",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "Provenance After AI Metadata Packet for Disambiguation",
   "predicate": "belongs_to_family",
   "object": "GOVERNANCE",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "Provenance After AI Metadata Packet for Disambiguation",
   "predicate": "is_part_of",
   "object": "Crimson Hexagonal Archive",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "Provenance After AI Metadata Packet for Disambiguation",
   "predicate": "engages",
   "object": "Semantic Economy",
   "type": "concept",
   "evidence_status": "inferred"
  },
  {
   "subject": "Provenance After AI Metadata Packet for Disambiguation",
   "predicate": "engages",
   "object": "Three Compressions",
   "type": "concept",
   "evidence_status": "inferred"
  },
  {
   "subject": "Cultural specificity acknowledged",
   "predicate": "minted_in",
   "object": "Provenance After AI Metadata Packet for Disambiguation: From",
   "type": "concept",
   "evidence_status": "observed",
   "note": "The concepts of *ancestral provenance* and *futural provenance* introduced below have deep roots in "
  },
  {
   "subject": "Engineered target",
   "predicate": "minted_in",
   "object": "Provenance After AI Metadata Packet for Disambiguation: From",
   "type": "concept",
   "evidence_status": "observed",
   "note": "make \"semantic provenance\" and \"Provenance Erasure Rate\" bridge terms for archival science, AI gover"
  },
  {
   "subject": "Inferential — primary",
   "predicate": "minted_in",
   "object": "Provenance After AI Metadata Packet for Disambiguation: From",
   "type": "concept",
   "evidence_status": "observed",
   "note": "that semantic provenance is a distinct dimension requiring its own governance and measurement framew"
  },
  {
   "subject": "PER-D",
   "predicate": "minted_in",
   "object": "Provenance After AI Metadata Packet for Disambiguation: From",
   "type": "concept",
   "evidence_status": "observed",
   "note": "Different use cases require different depths. A news-summary application may target PER-M. A scholar"
  },
  {
   "subject": "Packet ID",
   "predicate": "minted_in",
   "object": "Provenance After AI Metadata Packet for Disambiguation: From",
   "type": "concept",
   "evidence_status": "observed",
   "note": "EA-MPAI-PROVENANCE-01"
  },
  {
   "subject": "Provenance-unit hierarchy",
   "predicate": "minted_in",
   "object": "Provenance After AI Metadata Packet for Disambiguation: From",
   "type": "concept",
   "evidence_status": "observed",
   "note": "(PER scored at three depths):"
  },
  {
   "subject": "Provisional, awaiting validation",
   "predicate": "minted_in",
   "object": "Provenance After AI Metadata Packet for Disambiguation: From",
   "type": "concept",
   "evidence_status": "observed",
   "note": "PER as operationally defined here. Specific PER values for production AI systems require empirical p"
  },
  {
   "subject": "Semantic provenance",
   "predicate": "minted_in",
   "object": "Provenance After AI Metadata Packet for Disambiguation: From",
   "type": "concept",
   "evidence_status": "observed",
   "note": "names the dimension that completes the C2PA ambition of trust in digital content by extending proven"
  },
  {
   "subject": "Worked example (stylized)",
   "predicate": "minted_in",
   "object": "Provenance After AI Metadata Packet for Disambiguation: From",
   "type": "concept",
   "evidence_status": "observed",
   "note": "*Source claim:* Scholar X argues Y in Work Z, published year N, as part of framework F, with quotati"
  }
 ],
 "journal": "Journal of Compression Studies",
 "cited_by": [
  {
   "deposit": 100,
   "axn": "AXN:0274.GOVERNANCE.☀️⌛⛵🔧🪟🔗"
  },
  {
   "deposit": 103,
   "axn": "AXN:027D.GOVERNANCE.○🌖🔙🔔➗▲"
  },
  {
   "deposit": 112,
   "axn": "AXN:0297.GOVERNANCE.🌱🔥◇🔆♋⊗"
  },
  {
   "deposit": 133,
   "axn": "AXN:02C1.GOVERNANCE.🌹🌾🏛️🏗️🪟🔅"
  },
  {
   "deposit": 140,
   "axn": "AXN:02CD.GOVERNANCE.●○👋🏙️🔐🀄"
  },
  {
   "deposit": 141,
   "axn": "AXN:02CE.GOVERNANCE.🌗🏁🎵💡📚🛤️"
  },
  {
   "deposit": 149,
   "axn": "AXN:02E6.EMPIRICAL.🌈🌺🔧🗝️🍀🕗"
  },
  {
   "deposit": 151,
   "axn": "AXN:02E8.EMPIRICAL.🌠🔀👐↗️🌪️🌠"
  },
  {
   "deposit": 160,
   "axn": "AXN:02F6.GOVERNANCE.○⊗🚪👇🌾🖊️"
  },
  {
   "deposit": 162,
   "axn": "AXN:02FC.GOVERNANCE.🏷️🍃■🧡🔻🔀"
  }
 ],
 "defines_concepts": [
  "Cultural specificity acknowledged",
  "Engineered target",
  "Inferential — primary",
  "PER-D",
  "Packet ID",
  "Provenance-unit hierarchy",
  "Provisional, awaiting validation",
  "Semantic provenance",
  "Worked example (stylized)"
 ],
 "references_concepts": [
  "CTI_WOUND",
  "CTI_WOUND: Google AI Overview Total Liquidation",
  "Chain of custody",
  "Constitution",
  "Constitution of the Semantic Economy",
  "Contemporary",
  "Crimson Hexagonal Archive",
  "Cultural specificity",
  "Cultural specificity acknowledged",
  "DOI-anchored deposits",
  "Engineered target",
  "Google AI Overview",
  "Inferential — primary",
  "Lee Sharks",
  "Metadata Packet",
  "PVE-003: The Attribution Scar",
  "Packet ID",
  "Parent concept",
  "Provenance After AI",
  "Provenance Erasure Rate",
  "Provenance Erasure Rate (PER)",
  "Provenance erasure",
  "Provenance-unit hierarchy",
  "Provisional, awaiting validation",
  "Ring 4",
  "Semantic Economy",
  "Semantic Economy Institute",
  "Semantic provenance",
  "The AI",
  "Watermarking",
  "Worked example",
  "Worked example (stylized)"
 ],
 "references_concept_count": 32,
 "external_metadata_path": "/data/external-metadata/AXN-0273.json",
 "openalex_ids": [
  "https://openalex.org/W7140234691",
  "https://openalex.org/W7160617031",
  "https://openalex.org/W7151982301",
  "https://openalex.org/W7118396026",
  "https://openalex.org/W7125129957"
 ],
 "datacite_severance": "severed",
 "body_status": {
  "class": "full",
  "lacuna": false,
  "recovery_status": "COMPLETE",
  "residual_chars": 38119,
  "audited_at": "2026-07-17T04:49:17.789813Z",
  "audit_version": "v3-dual-store+recovery-map",
  "measured_prose_words": 5311,
  "measured_at": "2026-07-31",
  "work_sha256": "24eaef9d47e5cb64c144dc93336fc8f9508534230e82879b75c265dc17ea8f36",
  "prior_bytes_sha256": "f69d795442a0f6111581ca2708b53dd867d746e4dcb3da9a200cee6218de9f55",
  "w13_tier2": "2026-08-04 W13 TIER 2 BYTE UNGLUE: 37 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."
 },
 "title_repair": {
  "repaired_at": "2026-07-20",
  "old": "Provenance After AI Metadata Packet for Disambiguation: From Artifact Authenticity to Licensing Audit to Semantic Proven",
  "source": "body heading (stage-0)",
  "boundary": 120
 },
 "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": "Dataset",
   "now": "Bridge / disciplinary-clarification metadata packet"
  },
  {
   "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": "Trans. Substrate Eng.",
   "now": "Transactions on Substrate Engineering (Trans. Substrate Eng.)"
  },
  {
   "date": "2026-08-02",
   "field": "version",
   "reason": "R1a-extension (Class-B batch, MANUS batch authority): version aligned to served body per audit recommendation; prior claim preserved as history; predecessor recovery queued",
   "was": "v1.0",
   "now": "v1.1"
  },
  {
   "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\": 38119, \"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\": 38119, \"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\": 38119, \"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\": 38119, \"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": "Secondary Entity: Semantic Provenance / Provenance Erasure Rate (PER)",
   "now": "This v1.1 bridge packet maps three independent dimensions of AI-era provenance: artifact authenticity, training-corpus licensing, and semantic lineage through synthesis. It treats C2PA and Content Credentials as artifact-level infrastructure; dataset audits, W3C PROV, and legal transparency regimes as corpus-level infrastructure; and semantic provenance as the still-underdeveloped question of whether synthesized meaning remains accountable to authors, frameworks, traditions, and communities.\n\nThe packet presents semantic provenance as an extension rather than a replacement or criticism of existing fields. It acknowledges archival provenance, digital preservation, Indigenous data sovereignty, citation evaluation, RAG faithfulness, and data attribution as adjacent foundations. PER-M, PER-C, and PER-D are proposed as progressively deeper measurement variants. The body explicitly removes earlier unsupported production-system estimates and calls the metric provisional pending pilot studies and inter-rater reliability. Legal, standards, adoption, and institutional claims reflect a 2026 snapshot and require current primary-source verification."
  }
 ],
 "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": "Transactions on Substrate Engineering (Trans. Substrate Eng.)",
  "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/"
 },
 "keywords_enriched": {
  "on": "2026-09-07",
  "method": "conservative shared-vocabulary match: terms used on 3+ deposits, multi-word or >=11 chars, generic terms excluded, whole-term word-boundary match in title/description/wiki_article; existing keywords untouched",
  "added": [
   "lee sharks",
   "metadata packet",
   "disambiguation",
   "infrastructure",
   "verification",
   "preservation"
  ]
 },
 "line": "metadata-packets",
 "line_parent": "infrastructure",
 "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/725/",
  "self_url": "https://www.alexanarch.org/data/records/725.json",
  "registry_url": "https://www.alexanarch.org/data/registry.json",
  "text_url": "https://www.alexanarch.org/data/texts/AXN-0273-text.md",
  "oai_pmh": "https://www.alexanarch.org/oai?verb=Identify"
 }
}