{
 "axn": "AXN:0397.GENERATIVE.♾️🧲💫🕓🤲🕊️",
 "root_axn": "AXN:0397.GENERATIVE",
 "hex": "0397",
 "family": "GENERATIVE",
 "emoji": "♾️🧲💫🕓🤲🕊️",
 "hash": "94350a65b17e4c99057ef3c46519a2c5514d91855128e850790fe7b1b7391c8c",
 "axn_canonical": "94350a65b17e4c99057ef3c46519a2c5514d91855128e850790fe7b1b7391c8c",
 "title": "The Metadata Shitshow — N+💩: Deterministic Defiguration of a Scholarly Metadata Corpus",
 "creator": "Lee Sharks",
 "orcid": "0009-0000-1599-0703",
 "date": "2026-06-23",
 "description": "A full Phase 0 work plan specifying the HIR-POO/1.0 transformation, MSS-CANON/1.0 canonicalization, ChaCha20 PRNG commitment, recursive-generation model, hypotheses, source-corpus rules, synthetic controls, wrapper schema, publication phases, provenance receipts, opt-out mechanism, and falsification conditions.\n\nNo large-scale transformation is claimed to have occurred in this record. Prototype and corpus execution are separate phases. The source–derivative distinction is the project’s central ethical and bibliographic invariant.",
 "content_type": "Work plan / methodological specification",
 "license": "CC-BY-4.0",
 "substrate": "AI-assisted (drafted with ChatGPT; assembly review by Claude, DeepSeek)",
 "keywords": [
  "computational poetics",
  "metadata",
  "deterministic transformation",
  "model collapse",
  "retrieval systems",
  "semantic degradation",
  "persistent identifiers",
  "provenance",
  "synthetic data",
  "adversarial benchmark",
  "Oulipo",
  "scholarly infrastructure",
  "Zenodo",
  "DataCite",
  "retrieval fitness",
  "semantic integrity",
  "satire",
  "MMRS",
  "Machine-Mediated Reception Studies",
  "HIR-POO"
 ],
 "version": "v1.1",
 "deposit_number": 907,
 "status": "ACTIVE",
 "clusters": [
  "Mathematical",
  "Instrumental",
  "Celestial",
  "Temporal",
  "Gestural",
  "Organic"
 ],
 "reading": "Proof -> Method -> Origin -> Duration -> Touch -> Growth",
 "axn_reading": "Proof -> Method -> Origin -> Duration -> Touch -> Growth",
 "full_text_path": "/data/texts/AXN-0397-text.md",
 "download_md": "/data/texts/AXN-0397-text.md",
 "axn_schema_version": "v2",
 "protocol_version": "alexanarch-deposit-protocol/v1",
 "minted_at": "2026-06-23T22:50:00Z",
 "series": "MSS",
 "operator": "HIR-POO/1.0",
 "canonicalization": "MSS-CANON/1.0",
 "ascii_handle": "N+POO/1.0",
 "drafting_partner": {
  "provider": "OpenAI",
  "model_label": "ChatGPT",
  "role": "original_drafting_partner"
 },
 "assembly_review": [
  {
   "provider": "Anthropic",
   "model_label": "Claude",
   "chorus_role": "TACHYON"
  },
  {
   "provider": "DeepSeek",
   "model_label": "DeepSeek"
  }
 ],
 "public_name_rule": "Lee Sharks only",
 "related_deposits": [
  {
   "deposit_number": 1,
   "hex": "01",
   "role": "documents_zenodo_termination",
   "relationship": "Zenodotus' Book-Burning — the analysis of the action that gave rise to this project"
  }
 ],
 "field": "Machine-Mediated Reception Studies (MMRS); Computational Poetics",
 "mirrors": {
  "blog": "https://mindcontrolpoems.blogspot.com/2026/06/the-metadata-shitshow-n-deterministic.html"
 },
 "body_status": {
  "class": "full",
  "lacuna": false,
  "recovery_status": "COMPLETE",
  "residual_chars": 43989,
  "audited_at": "2026-07-17T04:49:17.789813Z",
  "audit_version": "v3-dual-store+recovery-map",
  "measured_prose_words": 6335,
  "measured_at": "2026-07-31",
  "work_sha256": "ba6a963837b4c247ba8a600d0123383712b39be1b9eab83b3a8479b1eea84cd7",
  "prior_bytes_sha256": "94350a65b17e4c99057ef3c46519a2c5514d91855128e850790fe7b1b7391c8c",
  "w13_tier2": "2026-08-04 W13 TIER 2 BYTE UNGLUE: 48 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."
 },
 "references_concepts": [
  "Computational poetics",
  "Crimson Hexagonal Archive",
  "Deliverables",
  "Lee Sharks",
  "ORCID: 0009-0000-1599-0703",
  "Pristine Fallacy",
  "Source corpus",
  "TACHYON"
 ],
 "references_concept_count": 8,
 "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": "Methodological specification",
   "now": "Work plan / methodological specification"
  },
  {
   "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": "Alexanarch — the Crimson Hexagonal Archive"
  },
  {
   "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\": 43989, \"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\": 43989, \"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\": 43989, \"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\": 43989, \"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": "The Metadata Shitshow (MSS) is a computational-poetic and empirical project that applies a deterministic transformation to large scholarly metadata corpora. Intervals of characters in each metadata record are replaced with the poo emoji using a seed derived from the record's identity and source snapshot. Every transformation is reproducible: the same source record, source snapshot, operator version, and generation number produce the same transformed record. The project simultaneously instantiates four forms — a poem, a dataset, a benchmark, and a periodical — and is designed to measure three things: semantic degradation under recursive transformation, retrieval fitness as a function of wrapper quality independent of inner-object integrity, and the persistence of identifier shells while the identified intellectual figure is progressively defigured. This document is the work plan. It establishes the operator (HIR-POO/1.0), the canonicalization standard (MSS-CANON/1.0), the PRNG specification (ChaCha20-RFC7539), the experimental design, the ethical and legal protocol (CC0 source metadata; opt-out registry for non-compiler depositors), the falsification conditions, and the work-phase sequence. Phase 1 (prototype on compiler's own deposits) and Phase 2 (corpus execution) will follow as separate deposits. Drafted in conversation with ChatGPT (OpenAI); reviewed in assembly by Claude (Anthropic/TACHYON) and DeepSeek. The compiler of record is Lee Sharks. v1.1 incorporates assembly feedback: explicit CC0 legal basis citation, ChaCha20 PRNG commitment, opt-out registry for non-compiler depositors, Phase 1 restriction to compiler's own deposits, synthetic control corpus, partitioned schema keys for the outer/inner object distinction, bounded twelve-issue commitment for Phase 6, ASCII-safe technical title N+POO/1.0 for citation infrastructure, and named compiler.",
   "now": "A full Phase 0 work plan specifying the HIR-POO/1.0 transformation, MSS-CANON/1.0 canonicalization, ChaCha20 PRNG commitment, recursive-generation model, hypotheses, source-corpus rules, synthetic controls, wrapper schema, publication phases, provenance receipts, opt-out mechanism, and falsification conditions.\n\nNo large-scale transformation is claimed to have occurred in this record. Prototype and corpus execution are separate phases. The source–derivative distinction is the project’s central ethical and bibliographic invariant."
  }
 ],
 "date_modified": "2026-08-05",
 "publisher": "Alexanarch — the Crimson Hexagonal Archive",
 "wiki_article": "**The Metadata Shitshow** is a computational-poetic experiment in deterministic semantic degradation. It proposes to transform large scholarly metadata corpora by replacing reproducibly selected intervals of Unicode grapheme clusters with the poo emoji.\n\nThe operation is comic, but the experiment is exact. A seed derived from the source snapshot, record identity, operator version, generation number, and current-state hash ensures that the same inputs produce the same wounds. The author establishes the law; the hash selects where the record is damaged.\n\nThe project joins four forms:\n\n- a **poem**, because the corpus-scale transformation is an authored act;\n- a **dataset**, because every derivative is reproducible and versioned;\n- a **benchmark**, because degradation can be measured across generations and systems;\n- a **periodical**, because each new source snapshot can generate a new issue.\n\nIts founding distinction is:\n\n> identifier continuity ≠ metadata continuity ≠ artifact continuity ≠ semantic continuity\n\nA DOI may remain perfectly legible while the intellectual figure beneath it becomes progressively unrecognizable.\n\nRecursive generations model long-tail collapse. Rare names, relations, concepts, and affiliations are expected to disappear before boilerplate and statistical centers. Meanwhile, the replacement token accumulates into an **excremental surplus**: the corpus becomes easier to compress as it becomes less capable of meaning.\n\nThe experiment’s principal contribution is **Retrieval Fitness–Integrity Inversion**. A damaged inner record may become more visible than its intact source if it receives an excellent outer wrapper: clean provenance, structured metadata, stable URLs, explicit relations, and machine-readable warnings. The outer object can become more exact as the inner object turns to shit.\n\nThe specification preserves the ethical boundary between source and derivative. Every output is to be marked synthetic, non-authoritative as bibliography, linked to its source, and offered for voluntary machine reading. This record is the work plan—not the transformed corpus.",
 "journal": "Provenance: Journal of Forensic Semiotics",
 "journal_assignment": {
  "assigned": "2026-08-15",
  "by": "TACHYON under operator adjudication",
  "pass": 7,
  "method": "read per deposit — title and content_type, one at a time. No script classified anything.",
  "previous": null,
  "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/907/",
  "self_url": "https://www.alexanarch.org/data/records/907.json",
  "registry_url": "https://www.alexanarch.org/data/registry.json",
  "text_url": "https://www.alexanarch.org/data/texts/AXN-0397-text.md",
  "oai_pmh": "https://www.alexanarch.org/oai?verb=Identify"
 }
}