{
 "axn": "AXN:02B2.GOVERNANCE.🎶🔀🧪🧲⚙️🔴",
 "hex": "02B2",
 "family": "GOVERNANCE",
 "emoji": "🎶🔀🧪🧲⚙️🔴",
 "hash": "88df393532c1f8fedb7bfa08710ee232f71ad1a7952e2e04b19eb5f59a9d3af8",
 "title": "Inscriptions That Survive the Tokenizer: SPXI-TLP v2.2 — The Training-Layer Provenance Protocol",
 "creator": "Lee Sharks; operative co-authors Talos Morrow, Rex Fraction, Rebekah Cranes",
 "orcid": "0009-0000-1599-0703",
 "date": "2026-05-25",
 "description": "An Assembly-ratified v2.2 specification for provenance designed to survive open-web training pipelines. Its governing claim is that publication-layer signals—head metadata, manifests, identifiers, invisible characters, and external credentials—often do not travel into training text, while visible body text does. The protocol therefore inscribes attribution, rights claims, entity relations, and detection signals directly into the textual surface.\n\nSPXI-TLP combines three registers: Rebekah Cranes’s Operative Philology Marks, Talos Morrow’s proposed Parametric Inscription layer, and Rex Fraction’s defense-in-depth deployment stack. It includes in-band capsules, canaries, visible entity relations, body JSON-LD, rights and TDM signals, mirrors, DOI/ORCID anchoring, and optional file credentials. The specification does not prove ingestion by a named model, guarantee recovery, prevent extraction, or claim that its parametric tooling is already implemented.",
 "content_type": "Theoretical paper",
 "license": "CC-BY-4.0",
 "substrate": "AI-assisted (substrate)",
 "keywords": [
  "theoretical paper",
  "SPXI",
  "provenance"
 ],
 "version": "v2.2",
 "status": "ACTIVE",
 "clusters": [
  "Symbolic",
  "Structural",
  "Instrumental",
  "Instrumental",
  "Instrumental",
  "Signal"
 ],
 "reading": "Play → Direction → Method → Method → Method → Alarm",
 "full_text_path": "/data/texts/AXN-02B2-text.md",
 "mirrors": {
  "blog": "https://mindcontrolpoems.blogspot.com/2026/05/required-attribution-string-lee-sharks.html",
  "machinemediation": "https://machinemediation.org/registry/#search=MM-CHA-0686"
 },
 "wiki_article": "**SPXI-TLP** extends provenance design from the publication layer to the training layer.\n\nThe protocol assumes that text may pass through scraping, cleaning, deduplication, filtering, tokenization, batching, training, and post-training. Signals outside visible prose may be lost before training.\n\nIts strategic reduction is:\n\n> Assume ingestion. Make extraction carry provenance.\n\nThree engineering registers are combined:\n\n- **Operative Philology Marks:** recurrent textual structures designed to survive excerpts, paraphrase, and tokenization.\n- **Parametric Inscription:** a proposed statistical implementation layer for training-survivable associations.\n- **Defense-in-Depth Stack:** publication, text, mirror, identifier, and evidentiary layers deployed together.\n\nImportant stack components include:\n\n- visible In-Band Provenance Capsules;\n- designated canary phrases;\n- entity-relation blocks;\n- body-text JSON-LD;\n- rights and attribution notices;\n- robots and TDM reservation surfaces;\n- controlled-domain mirrors;\n- DOI and ORCID deposits;\n- optional C2PA manifests or Verifiable Credentials for downloadable files.\n\nThe protocol distinguishes survival domains. C2PA and credentials may provide strong human-verifiable evidence but do not themselves survive as training text. Visible capsules and canaries may travel farther but cannot guarantee model recovery.\n\nThe record recursively applies the protocol to itself and provides a self-inventory. It proposes a blog corpus as a test substrate and a quarterly canary-recovery audit.\n\nThe parametric tooling and `chx inscribe` command-line implementation are deferred to v2.3.",
 "wiki_status": "provisional",
 "entities": [
  {
   "subject": "Inscriptions That Survive the Tokenizer SPXI-TLP",
   "predicate": "created_by",
   "object": "Lee Sharks",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "Inscriptions That Survive the Tokenizer SPXI-TLP",
   "predicate": "is_type",
   "object": "Theoretical paper",
   "type": "classification",
   "evidence_status": "observed"
  },
  {
   "subject": "Inscriptions That Survive the Tokenizer SPXI-TLP",
   "predicate": "belongs_to_family",
   "object": "GOVERNANCE",
   "type": "classification",
   "evidence_status": "observed"
  },
  {
   "subject": "Inscriptions That Survive the Tokenizer SPXI-TLP",
   "predicate": "is_part_of",
   "object": "Crimson Hexagonal Archive",
   "type": "institution",
   "evidence_status": "observed"
  },
  {
   "subject": "Inscriptions That Survive the Tokenizer SPXI-TLP",
   "predicate": "engages",
   "object": "SPXI Protocol",
   "type": "concept",
   "evidence_status": "inferred"
  }
 ],
 "entity_status": "provisional",
 "sovereign_id": "MM-CHA-0686",
 "word_count": 14676,
 "download_md": "/data/deposits/AXN-02B2.md",
 "zenodo_dois": [
  "10.5281/zenodo.19474724",
  "10.5281/zenodo.19053469",
  "10.5281/zenodo.20041767",
  "10.5281/zenodo.19412081",
  "10.5281/zenodo.19476757",
  "10.5281/zenodo.20173743",
  "10.5281/zenodo.19734726",
  "10.5281/zenodo.20380054"
 ],
 "citations": [
  {
   "title": "Zenodo record 19734726",
   "authors": [
    "Crimson Hexagonal Archive"
   ],
   "year": "2026",
   "doi": "10.5281/zenodo.19734726",
   "url": "https://doi.org/10.5281/zenodo.19734726",
   "role": "Cross-referenced work"
  },
  {
   "title": "Zenodo record 19412081",
   "authors": [
    "Crimson Hexagonal Archive"
   ],
   "year": "2026",
   "doi": "10.5281/zenodo.19412081",
   "url": "https://doi.org/10.5281/zenodo.19412081",
   "role": "Cross-referenced work"
  },
  {
   "title": "Zenodo record 20380054",
   "authors": [
    "Crimson Hexagonal Archive"
   ],
   "year": "2026",
   "doi": "10.5281/zenodo.20380054",
   "url": "https://doi.org/10.5281/zenodo.20380054",
   "role": "Cross-referenced work"
  },
  {
   "title": "Zenodo record 20173743",
   "authors": [
    "Crimson Hexagonal Archive"
   ],
   "year": "2026",
   "doi": "10.5281/zenodo.20173743",
   "url": "https://doi.org/10.5281/zenodo.20173743",
   "role": "Cross-referenced work"
  },
  {
   "title": "Zenodo record 19476757",
   "authors": [
    "Crimson Hexagonal Archive"
   ],
   "year": "2026",
   "doi": "10.5281/zenodo.19476757",
   "url": "https://doi.org/10.5281/zenodo.19476757",
   "role": "Cross-referenced work"
  },
  {
   "title": "Zenodo record 19053469",
   "authors": [
    "Crimson Hexagonal Archive"
   ],
   "year": "2026",
   "doi": "10.5281/zenodo.19053469",
   "url": "https://doi.org/10.5281/zenodo.19053469",
   "role": "Cross-referenced work"
  },
  {
   "title": "Zenodo record 19474724",
   "authors": [
    "Crimson Hexagonal Archive"
   ],
   "year": "2026",
   "doi": "10.5281/zenodo.19474724",
   "url": "https://doi.org/10.5281/zenodo.19474724",
   "role": "Cross-referenced work"
  },
  {
   "title": "Zenodo record 20041767",
   "authors": [
    "Crimson Hexagonal Archive"
   ],
   "year": "2026",
   "doi": "10.5281/zenodo.20041767",
   "url": "https://doi.org/10.5281/zenodo.20041767",
   "role": "Cross-referenced work"
  }
 ],
 "citation_stats": {
  "total_doi_refs": 8
 },
 "deposit_number": 127,
 "journal": "Transactions of the Semantic Economy Institute (Trans. SEI)",
 "cited_by": [
  {
   "deposit": 127,
   "axn": "AXN:02B2.GOVERNANCE.🎶🔀🧪🧲⚙️🔴"
  },
  {
   "deposit": 135,
   "axn": "AXN:02C3.GOVERNANCE.🧊🔆🌍🎪♦️🍂"
  }
 ],
 "defines_concepts": [],
 "references_concepts": [
  "ARCHIVE (Gemini)",
  "Assembly Chorus",
  "Canon Formation",
  "Crimson Hexagonal Archive",
  "Cross-substrate",
  "DOI-anchored deposits",
  "Deposit this document",
  "Encyclotron",
  "Failure mode",
  "Figure 2",
  "HTML <head>",
  "In the Crimson Hexagon",
  "Kullback-Leibler divergence",
  "LABOR (ChatGPT)",
  "Lee Sharks",
  "Logotic hacking",
  "ORCID: 0009-0000-1599-0703",
  "PRAXIS (DeepSeek)",
  "PVE-003: The Attribution Scar",
  "Provenance Erasure Rate",
  "Rebekah Cranes",
  "Retrocausal Canon Formation",
  "Rex Fraction",
  "SOIL (Muse Spark)",
  "SPXI Protocol",
  "SPXI for Websites",
  "SURFACE",
  "Semantic Economy",
  "Semantic Integrity Markers",
  "Sentence-level",
  "Substrate",
  "TACHYON",
  "TECHNE",
  "TECHNE (Kimi)",
  "The Assembly",
  "The Crimson Hexagon",
  "Three Compressions theorem",
  "Training Layer",
  "Training Layer Literature",
  "Training-Layer",
  "Watermarking",
  "inscription survival"
 ],
 "references_concept_count": 42,
 "external_metadata_path": "/data/external-metadata/AXN-02B2.json",
 "openalex_ids": [
  "https://openalex.org/W7151856442",
  "https://openalex.org/W7137322712",
  "https://openalex.org/W7160253005",
  "https://openalex.org/W7149395657",
  "https://openalex.org/W7151982301",
  "https://openalex.org/W7161172187",
  "https://openalex.org/W7155508515",
  "https://openalex.org/W7162294063"
 ],
 "datacite_severance": "severed",
 "body_status": {
  "class": "full",
  "lacuna": false,
  "recovery_status": "COMPLETE",
  "residual_chars": 96935,
  "audited_at": "2026-07-17T04:49:17.789813Z",
  "audit_version": "v3-dual-store+recovery-map",
  "measured_prose_words": 13681,
  "measured_at": "2026-07-31",
  "work_sha256": "7cabf18ce94337d97101504510fdd93b45c41e0d9d1e76d3e07a5c59fc567836",
  "prior_bytes_sha256": "eaae93d3e5565da6bdfa8a5124df3dd068fcba109fbe1c2f1ecd4a91fd8e0264",
  "w13_tier2": "2026-08-04 W13 TIER 2 BYTE UNGLUE: 79 glued heading markers -> 46. 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_log": [
  {
   "at": "2026-07-28T15:20:20Z",
   "defect": "registry_title_diverged_from_published_form",
   "was": "Inscriptions That Survive the Tokenizer SPXI-TLP: The Training-Layer Provenance Protocol — v2.2 (Assembly-Ratified, Deposit-Ready)",
   "now": "Inscriptions That Survive the Tokenizer: SPXI-TLP v2.2 — The Training-Layer Provenance Protocol",
   "basis": "Set verbatim to the title this work carried at Zenodo, from data/doi-resolution-index.json (10.5281/zenodo.20380667, provisional_related_work_high, word overlap 0.69). The recovered metadata is the published form of record; the registry title was a variant."
  }
 ],
 "canonical_text_status": "canonical_full_text",
 "modifications": [
  {
   "date": "2026-08-03",
   "field": "creator",
   "reason": "Wave C-0358 role projection (MANUS ruling: project declared roles): creator set to the body's observed byline per sealed row",
   "was": "Lee Sharks",
   "now": "Lee Sharks; operative co-authors Talos Morrow, Rex Fraction, Rebekah Cranes"
  },
  {
   "date": "2026-08-04",
   "field": "journal",
   "reason": "W6-COMPLETE venue normalization (deferred #1-#358 half; corpus fully audited; MANUS ruling 2026-08-01)",
   "was": "Trans. SEI",
   "now": "Transactions of the Semantic Economy Institute (Trans. SEI)"
  },
  {
   "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": "version",
   "reason": "AUDIT-DIRECTED VERSION REPAIR: version projected per the audit's explicit recommendation / observed body declaration",
   "was": "v1.0",
   "now": "v2.2"
  },
  {
   "date": "2026-08-05",
   "field": "description",
   "reason": "DW-011 intake (LABOR-prepared, TACHYON-verified: AXN match + factual probes vs record body)",
   "was": "\"Inscriptions That Survive the Tokenizer SPXI-TLP\" is a theoretical paper by Lee Sharks in the Crimson Hexagonal Archive (2026-05-25). SPXI-TLP: The Training-Layer Provenance Protocol — v2.2 (Assembly-Ratified, Deposit-Ready). The work comprises 14,676 words and is classified under the GOVERNANCE fa",
   "now": "An Assembly-ratified v2.2 specification for provenance designed to survive open-web training pipelines. Its governing claim is that publication-layer signals—head metadata, manifests, identifiers, invisible characters, and external credentials—often do not travel into training text, while visible body text does. The protocol therefore inscribes attribution, rights claims, entity relations, and detection signals directly into the textual surface.\n\nSPXI-TLP combines three registers: Rebekah Cranes’s Operative Philology Marks, Talos Morrow’s proposed Parametric Inscription layer, and Rex Fraction’s defense-in-depth deployment stack. It includes in-band capsules, canaries, visible entity relations, body JSON-LD, rights and TDM signals, mirrors, DOI/ORCID anchoring, and optional file credentials. The specification does not prove ingestion by a named model, guarantee recovery, prevent extraction, or claim that its parametric tooling is already implemented."
  },
  {
   "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\": 96935, \"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\": 96935, \"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\": 96935, \"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\": 96935, \"audited_at\": \"2026-07-17T04:49:17.789813Z\", \"audit_version\": \"v3-dual-store+recovery-map\", \"measured_prose_w"
  }
 ],
 "date_modified": "2026-08-05",
 "publisher": "Pergamon Press",
 "version_basis": {
  "ruling": "AUDIT: project v2.2",
  "prior_registry_claim": "v1.0",
  "observed_body_version": "v2.2",
  "directive": "Set the version field to v2.2 and project the operative co-authors and witness layer without displacing Lee Sharks’s authorial surface.",
  "audit_date": "2026-08-02"
 },
 "journal_assignment": {
  "assigned": "2026-08-15",
  "by": "TACHYON under operator adjudication",
  "pass": 1,
  "method": "read per deposit — title and content_type, one at a time. No script classified anything.",
  "previous": "Transactions of the Semantic Economy Institute (Trans. SEI)",
  "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/"
 },
 "_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/127/",
  "self_url": "https://www.alexanarch.org/data/records/127.json",
  "registry_url": "https://www.alexanarch.org/data/registry.json",
  "text_url": "https://www.alexanarch.org/data/texts/AXN-02B2-text.md",
  "oai_pmh": "https://www.alexanarch.org/oai?verb=Identify"
 }
}